Projeto_9_Transfer_learning_classificar_gatos_e_cachorros.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Projeto #9: Transfer learning classificar gatos e cachorros.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/DanielMSousa/curso-deeplearning-na-pratica/blob/main/Projeto_9_Transfer_learning_classificar_gatos_e_cachorros.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "JnKRe0p9h35K"
      },
      "source": [
        "# Projeto 9: Transfer learning para classificar gatos e cachorros "
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Ll4dJoqibSQL"
      },
      "source": [
        "- Aplicaremos transferência de aprendizagem para reusar os pesos da rede ResNet 50, que é famosa para tarefas de classificação de imagens\n",
        "- Um modelo pré-treinado no Imagenet da ResNet50 será carregada para classificar novas imagens de gatos e cachorros\n",
        "- O novo modelo consiste em duas partes: \n",
        "    - (1) rede neural base pré-treinada  \n",
        "    - (2) novas camadas densas\n",
        "- Citação: Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg and Li Fei-Fei. (* = equal contribution) ImageNet Large Scale Visual Recognition Challenge. arXiv:1409.0575, 2014.\n",
        "- Artigo: https://arxiv.org/abs/1409.0575\n",
        "- Base de dados: https://www.kaggle.com/tongpython/cat-and-dog"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "iKrREedvqzgV"
      },
      "source": [
        "{0: 'tench, Tinca tinca', 1: 'goldfish, Carassius auratus', 2: 'great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias', 3: 'tiger shark, Galeocerdo cuvieri', 4: 'hammerhead, hammerhead shark', 5: 'electric ray, crampfish, numbfish, torpedo', 6: 'stingray', 7: 'cock', 8: 'hen', 9: 'ostrich, Struthio camelus', 10: 'brambling, Fringilla montifringilla', 11: 'goldfinch, Carduelis carduelis', 12: 'house finch, linnet, Carpodacus mexicanus', 13: 'junco, snowbird', 14: 'indigo bunting, indigo finch, indigo bird, Passerina cyanea', 15: 'robin, American robin, Turdus migratorius', 16: 'bulbul', 17: 'jay', 18: 'magpie', 19: 'chickadee', 20: 'water ouzel, dipper', 21: 'kite', 22: 'bald eagle, American eagle, Haliaeetus leucocephalus', 23: 'vulture', 24: 'great grey owl, great gray owl, Strix nebulosa', 25: 'European fire salamander, Salamandra salamandra', 26: 'common newt, Triturus vulgaris', 27: 'eft', 28: 'spotted salamander, Ambystoma maculatum', 29: 'axolotl, mud puppy, Ambystoma mexicanum', 30: 'bullfrog, Rana catesbeiana', 31: 'tree frog, tree-frog', 32: 'tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui', 33: 'loggerhead, loggerhead turtle, Caretta caretta', 34: 'leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea', 35: 'mud turtle', 36: 'terrapin', 37: 'box turtle, box tortoise', 38: 'banded gecko', 39: 'common iguana, iguana, Iguana iguana', 40: 'American chameleon, anole, Anolis carolinensis', 41: 'whiptail, whiptail lizard', 42: 'agama', 43: 'frilled lizard, Chlamydosaurus kingi', 44: 'alligator lizard', 45: 'Gila monster, Heloderma suspectum', 46: 'green lizard, Lacerta viridis', 47: 'African chameleon, Chamaeleo chamaeleon', 48: 'Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis', 49: 'African crocodile, Nile crocodile, Crocodylus niloticus', 50: 'American alligator, Alligator mississipiensis', 51: 'triceratops', 52: 'thunder snake, worm snake, Carphophis amoenus', 53: 'ringneck snake, ring-necked snake, ring snake', 54: 'hognose snake, puff adder, sand viper', 55: 'green snake, grass snake', 56: 'king snake, kingsnake', 57: 'garter snake, grass snake', 58: 'water snake', 59: 'vine snake', 60: 'night snake, Hypsiglena torquata', 61: 'boa constrictor, Constrictor constrictor', 62: 'rock python, rock snake, Python sebae', 63: 'Indian cobra, Naja naja', 64: 'green mamba', 65: 'sea snake', 66: 'horned viper, cerastes, sand viper, horned asp, Cerastes cornutus', 67: 'diamondback, diamondback rattlesnake, Crotalus adamanteus', 68: 'sidewinder, horned rattlesnake, Crotalus cerastes', 69: 'trilobite', 70: 'harvestman, daddy longlegs, Phalangium opilio', 71: 'scorpion', 72: 'black and gold garden spider, Argiope aurantia', 73: 'barn spider, Araneus cavaticus', 74: 'garden spider, Aranea diademata', 75: 'black widow, Latrodectus mactans', 76: 'tarantula', 77: 'wolf spider, hunting spider', 78: 'tick', 79: 'centipede', 80: 'black grouse', 81: 'ptarmigan', 82: 'ruffed grouse, partridge, Bonasa umbellus', 83: 'prairie chicken, prairie grouse, prairie fowl', 84: 'peacock', 85: 'quail', 86: 'partridge', 87: 'African grey, African gray, Psittacus erithacus', 88: 'macaw', 89: 'sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita', 90: 'lorikeet', 91: 'coucal', 92: 'bee eater', 93: 'hornbill', 94: 'hummingbird', 95: 'jacamar', 96: 'toucan', 97: 'drake', 98: 'red-breasted merganser, Mergus serrator', 99: 'goose', 100: 'black swan, Cygnus atratus', 101: 'tusker', 102: 'echidna, spiny anteater, anteater', 103: 'platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus', 104: 'wallaby, brush kangaroo', 105: 'koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus', 106: 'wombat', 107: 'jellyfish', 108: 'sea anemone, anemone', 109: 'brain coral', 110: 'flatworm, platyhelminth', 111: 'nematode, nematode worm, roundworm', 112: 'conch', 113: 'snail', 114: 'slug', 115: 'sea slug, nudibranch', 116: 'chiton, coat-of-mail shell, sea cradle, polyplacophore', 117: 'chambered nautilus, pearly nautilus, nautilus', 118: 'Dungeness crab, Cancer magister', 119: 'rock crab, Cancer irroratus', 120: 'fiddler crab', 121: 'king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica', 122: 'American lobster, Northern lobster, Maine lobster, Homarus americanus', 123: 'spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish', 124: 'crayfish, crawfish, crawdad, crawdaddy', 125: 'hermit crab', 126: 'isopod', 127: 'white stork, Ciconia ciconia', 128: 'black stork, Ciconia nigra', 129: 'spoonbill', 130: 'flamingo', 131: 'little blue heron, Egretta caerulea', 132: 'American egret, great white heron, Egretta albus', 133: 'bittern', 134: 'crane', 135: 'limpkin, Aramus pictus', 136: 'European gallinule, Porphyrio porphyrio', 137: 'American coot, marsh hen, mud hen, water hen, Fulica americana', 138: 'bustard', 139: 'ruddy turnstone, Arenaria interpres', 140: 'red-backed sandpiper, dunlin, Erolia alpina', 141: 'redshank, Tringa totanus', 142: 'dowitcher', 143: 'oystercatcher, oyster catcher', 144: 'pelican', 145: 'king penguin, Aptenodytes patagonica', 146: 'albatross, mollymawk', 147: 'grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus', 148: 'killer whale, killer, orca, grampus, sea wolf, Orcinus orca', 149: 'dugong, Dugong dugon', 150: 'sea lion', 151: 'Chihuahua', 152: 'Japanese spaniel', 153: 'Maltese dog, Maltese terrier, Maltese', 154: 'Pekinese, Pekingese, Peke', 155: 'Shih-Tzu', 156: 'Blenheim spaniel', 157: 'papillon', 158: 'toy terrier', 159: 'Rhodesian ridgeback', 160: 'Afghan hound, Afghan', 161: 'basset, basset hound', 162: 'beagle', 163: 'bloodhound, sleuthhound', 164: 'bluetick', 165: 'black-and-tan coonhound', 166: 'Walker hound, Walker foxhound', 167: 'English foxhound', 168: 'redbone', 169: 'borzoi, Russian wolfhound', 170: 'Irish wolfhound', 171: 'Italian greyhound', 172: 'whippet', 173: 'Ibizan hound, Ibizan Podenco', 174: 'Norwegian elkhound, elkhound', 175: 'otterhound, otter hound', 176: 'Saluki, gazelle hound', 177: 'Scottish deerhound, deerhound', 178: 'Weimaraner', 179: 'Staffordshire bullterrier, Staffordshire bull terrier', 180: 'American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier', 181: 'Bedlington terrier', 182: 'Border terrier', 183: 'Kerry blue terrier', 184: 'Irish terrier', 185: 'Norfolk terrier', 186: 'Norwich terrier', 187: 'Yorkshire terrier', 188: 'wire-haired fox terrier', 189: 'Lakeland terrier', 190: 'Sealyham terrier, Sealyham', 191: 'Airedale, Airedale terrier', 192: 'cairn, cairn terrier', 193: 'Australian terrier', 194: 'Dandie Dinmont, Dandie Dinmont terrier', 195: 'Boston bull, Boston terrier', 196: 'miniature schnauzer', 197: 'giant schnauzer', 198: 'standard schnauzer', 199: 'Scotch terrier, Scottish terrier, Scottie', 200: 'Tibetan terrier, chrysanthemum dog', 201: 'silky terrier, Sydney silky', 202: 'soft-coated wheaten terrier', 203: 'West Highland white terrier', 204: 'Lhasa, Lhasa apso', 205: 'flat-coated retriever', 206: 'curly-coated retriever', 207: 'golden retriever', 208: 'Labrador retriever', 209: 'Chesapeake Bay retriever', 210: 'German short-haired pointer', 211: 'vizsla, Hungarian pointer', 212: 'English setter', 213: 'Irish setter, red setter', 214: 'Gordon setter', 215: 'Brittany spaniel', 216: 'clumber, clumber spaniel', 217: 'English springer, English springer spaniel', 218: 'Welsh springer spaniel', 219: 'cocker spaniel, English cocker spaniel, cocker', 220: 'Sussex spaniel', 221: 'Irish water spaniel', 222: 'kuvasz', 223: 'schipperke', 224: 'groenendael', 225: 'malinois', 226: 'briard', 227: 'kelpie', 228: 'komondor', 229: 'Old English sheepdog, bobtail', 230: 'Shetland sheepdog, Shetland sheep dog, Shetland', 231: 'collie', 232: 'Border collie', 233: 'Bouvier des Flandres, Bouviers des Flandres', 234: 'Rottweiler', 235: 'German shepherd, German shepherd dog, German police dog, alsatian', 236: 'Doberman, Doberman pinscher', 237: 'miniature pinscher', 238: 'Greater Swiss Mountain dog', 239: 'Bernese mountain dog', 240: 'Appenzeller', 241: 'EntleBucher', 242: 'boxer', 243: 'bull mastiff', 244: 'Tibetan mastiff', 245: 'French bulldog', 246: 'Great Dane', 247: 'Saint Bernard, St Bernard', 248: 'Eskimo dog, husky', 249: 'malamute, malemute, Alaskan malamute', 250: 'Siberian husky', 251: 'dalmatian, coach dog, carriage dog', 252: 'affenpinscher, monkey pinscher, monkey dog', 253: 'basenji', 254: 'pug, pug-dog', 255: 'Leonberg', 256: 'Newfoundland, Newfoundland dog', 257: 'Great Pyrenees', 258: 'Samoyed, Samoyede', 259: 'Pomeranian', 260: 'chow, chow chow', 261: 'keeshond', 262: 'Brabancon griffon', 263: 'Pembroke, Pembroke Welsh corgi', 264: 'Cardigan, Cardigan Welsh corgi', 265: 'toy poodle', 266: 'miniature poodle', 267: 'standard poodle', 268: 'Mexican hairless', 269: 'timber wolf, grey wolf, gray wolf, Canis lupus', 270: 'white wolf, Arctic wolf, Canis lupus tundrarum', 271: 'red wolf, maned wolf, Canis rufus, Canis niger', 272: 'coyote, prairie wolf, brush wolf, Canis latrans', 273: 'dingo, warrigal, warragal, Canis dingo', 274: 'dhole, Cuon alpinus', 275: 'African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus', 276: 'hyena, hyaena', 277: 'red fox, Vulpes vulpes', 278: 'kit fox, Vulpes macrotis', 279: 'Arctic fox, white fox, Alopex lagopus', 280: 'grey fox, gray fox, Urocyon cinereoargenteus', 281: 'tabby, tabby cat', 282: 'tiger cat', 283: 'Persian cat', 284: 'Siamese cat, Siamese', 285: 'Egyptian cat', 286: 'cougar, puma, catamount, mountain lion, painter, panther, Felis concolor', 287: 'lynx, catamount', 288: 'leopard, Panthera pardus', 289: 'snow leopard, ounce, Panthera uncia', 290: 'jaguar, panther, Panthera onca, Felis onca', 291: 'lion, king of beasts, Panthera leo', 292: 'tiger, Panthera tigris', 293: 'cheetah, chetah, Acinonyx jubatus', 294: 'brown bear, bruin, Ursus arctos', 295: 'American black bear, black bear, Ursus americanus, Euarctos americanus', 296: 'ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus', 297: 'sloth bear, Melursus ursinus, Ursus ursinus', 298: 'mongoose', 299: 'meerkat, mierkat', 300: 'tiger beetle', 301: 'ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle', 302: 'ground beetle, carabid beetle', 303: 'long-horned beetle, longicorn, longicorn beetle', 304: 'leaf beetle, chrysomelid', 305: 'dung beetle', 306: 'rhinoceros beetle', 307: 'weevil', 308: 'fly', 309: 'bee', 310: 'ant, emmet, pismire', 311: 'grasshopper, hopper', 312: 'cricket', 313: 'walking stick, walkingstick, stick insect', 314: 'cockroach, roach', 315: 'mantis, mantid', 316: 'cicada, cicala', 317: 'leafhopper', 318: 'lacewing, lacewing fly', 319: \"dragonfly, darning needle, devil's darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk\", 320: 'damselfly', 321: 'admiral', 322: 'ringlet, ringlet butterfly', 323: 'monarch, monarch butterfly, milkweed butterfly, Danaus plexippus', 324: 'cabbage butterfly', 325: 'sulphur butterfly, sulfur butterfly', 326: 'lycaenid, lycaenid butterfly', 327: 'starfish, sea star', 328: 'sea urchin', 329: 'sea cucumber, holothurian', 330: 'wood rabbit, cottontail, cottontail rabbit', 331: 'hare', 332: 'Angora, Angora rabbit', 333: 'hamster', 334: 'porcupine, hedgehog', 335: 'fox squirrel, eastern fox squirrel, Sciurus niger', 336: 'marmot', 337: 'beaver', 338: 'guinea pig, Cavia cobaya', 339: 'sorrel', 340: 'zebra', 341: 'hog, pig, grunter, squealer, Sus scrofa', 342: 'wild boar, boar, Sus scrofa', 343: 'warthog', 344: 'hippopotamus, hippo, river horse, Hippopotamus amphibius', 345: 'ox', 346: 'water buffalo, water ox, Asiatic buffalo, Bubalus bubalis', 347: 'bison', 348: 'ram, tup', 349: 'bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis', 350: 'ibex, Capra ibex', 351: 'hartebeest', 352: 'impala, Aepyceros melampus', 353: 'gazelle', 354: 'Arabian camel, dromedary, Camelus dromedarius', 355: 'llama', 356: 'weasel', 357: 'mink', 358: 'polecat, fitch, foulmart, foumart, Mustela putorius', 359: 'black-footed ferret, ferret, Mustela nigripes', 360: 'otter', 361: 'skunk, polecat, wood pussy', 362: 'badger', 363: 'armadillo', 364: 'three-toed sloth, ai, Bradypus tridactylus', 365: 'orangutan, orang, orangutang, Pongo pygmaeus', 366: 'gorilla, Gorilla gorilla', 367: 'chimpanzee, chimp, Pan troglodytes', 368: 'gibbon, Hylobates lar', 369: 'siamang, Hylobates syndactylus, Symphalangus syndactylus', 370: 'guenon, guenon monkey', 371: 'patas, hussar monkey, Erythrocebus patas', 372: 'baboon', 373: 'macaque', 374: 'langur', 375: 'colobus, colobus monkey', 376: 'proboscis monkey, Nasalis larvatus', 377: 'marmoset', 378: 'capuchin, ringtail, Cebus capucinus', 379: 'howler monkey, howler', 380: 'titi, titi monkey', 381: 'spider monkey, Ateles geoffroyi', 382: 'squirrel monkey, Saimiri sciureus', 383: 'Madagascar cat, ring-tailed lemur, Lemur catta', 384: 'indri, indris, Indri indri, Indri brevicaudatus', 385: 'Indian elephant, Elephas maximus', 386: 'African elephant, Loxodonta africana', 387: 'lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens', 388: 'giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca', 389: 'barracouta, snoek', 390: 'eel', 391: 'coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch', 392: 'rock beauty, Holocanthus tricolor', 393: 'anemone fish', 394: 'sturgeon', 395: 'gar, garfish, garpike, billfish, Lepisosteus osseus', 396: 'lionfish', 397: 'puffer, pufferfish, blowfish, globefish', 398: 'abacus', 399: 'abaya', 400: \"academic gown, academic robe, judge's robe\", 401: 'accordion, piano accordion, squeeze box', 402: 'acoustic guitar', 403: 'aircraft carrier, carrier, flattop, attack aircraft carrier', 404: 'airliner', 405: 'airship, dirigible', 406: 'altar', 407: 'ambulance', 408: 'amphibian, amphibious vehicle', 409: 'analog clock', 410: 'apiary, bee house', 411: 'apron', 412: 'ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin', 413: 'assault rifle, assault gun', 414: 'backpack, back pack, knapsack, packsack, rucksack, haversack', 415: 'bakery, bakeshop, bakehouse', 416: 'balance beam, beam', 417: 'balloon', 418: 'ballpoint, ballpoint pen, ballpen, Biro', 419: 'Band Aid', 420: 'banjo', 421: 'bannister, banister, balustrade, balusters, handrail', 422: 'barbell', 423: 'barber chair', 424: 'barbershop', 425: 'barn', 426: 'barometer', 427: 'barrel, cask', 428: 'barrow, garden cart, lawn cart, wheelbarrow', 429: 'baseball', 430: 'basketball', 431: 'bassinet', 432: 'bassoon', 433: 'bathing cap, swimming cap', 434: 'bath towel', 435: 'bathtub, bathing tub, bath, tub', 436: 'beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon', 437: 'beacon, lighthouse, beacon light, pharos', 438: 'beaker', 439: 'bearskin, busby, shako', 440: 'beer bottle', 441: 'beer glass', 442: 'bell cote, bell cot', 443: 'bib', 444: 'bicycle-built-for-two, tandem bicycle, tandem', 445: 'bikini, two-piece', 446: 'binder, ring-binder', 447: 'binoculars, field glasses, opera glasses', 448: 'birdhouse', 449: 'boathouse', 450: 'bobsled, bobsleigh, bob', 451: 'bolo tie, bolo, bola tie, bola', 452: 'bonnet, poke bonnet', 453: 'bookcase', 454: 'bookshop, bookstore, bookstall', 455: 'bottlecap', 456: 'bow', 457: 'bow tie, bow-tie, bowtie', 458: 'brass, memorial tablet, plaque', 459: 'brassiere, bra, bandeau', 460: 'breakwater, groin, groyne, mole, bulwark, seawall, jetty', 461: 'breastplate, aegis, egis', 462: 'broom', 463: 'bucket, pail', 464: 'buckle', 465: 'bulletproof vest', 466: 'bullet train, bullet', 467: 'butcher shop, meat market', 468: 'cab, hack, taxi, taxicab', 469: 'caldron, cauldron', 470: 'candle, taper, wax light', 471: 'cannon', 472: 'canoe', 473: 'can opener, tin opener', 474: 'cardigan', 475: 'car mirror', 476: 'carousel, carrousel, merry-go-round, roundabout, whirligig', 477: \"carpenter's kit, tool kit\", 478: 'carton', 479: 'car wheel', 480: 'cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM', 481: 'cassette', 482: 'cassette player', 483: 'castle', 484: 'catamaran', 485: 'CD player', 486: 'cello, violoncello', 487: 'cellular telephone, cellular phone, cellphone, cell, mobile phone', 488: 'chain', 489: 'chainlink fence', 490: 'chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour', 491: 'chain saw, chainsaw', 492: 'chest', 493: 'chiffonier, commode', 494: 'chime, bell, gong', 495: 'china cabinet, china closet', 496: 'Christmas stocking', 497: 'church, church building', 498: 'cinema, movie theater, movie theatre, movie house, picture palace', 499: 'cleaver, meat cleaver, chopper', 500: 'cliff dwelling', 501: 'cloak', 502: 'clog, geta, patten, sabot', 503: 'cocktail shaker', 504: 'coffee mug', 505: 'coffeepot', 506: 'coil, spiral, volute, whorl, helix', 507: 'combination lock', 508: 'computer keyboard, keypad', 509: 'confectionery, confectionary, candy store', 510: 'container ship, containership, container vessel', 511: 'convertible', 512: 'corkscrew, bottle screw', 513: 'cornet, horn, trumpet, trump', 514: 'cowboy boot', 515: 'cowboy hat, ten-gallon hat', 516: 'cradle', 517: 'crane', 518: 'crash helmet', 519: 'crate', 520: 'crib, cot', 521: 'Crock Pot', 522: 'croquet ball', 523: 'crutch', 524: 'cuirass', 525: 'dam, dike, dyke', 526: 'desk', 527: 'desktop computer', 528: 'dial telephone, dial phone', 529: 'diaper, nappy, napkin', 530: 'digital clock', 531: 'digital watch', 532: 'dining table, board', 533: 'dishrag, dishcloth', 534: 'dishwasher, dish washer, dishwashing machine', 535: 'disk brake, disc brake', 536: 'dock, dockage, docking facility', 537: 'dogsled, dog sled, dog sleigh', 538: 'dome', 539: 'doormat, welcome mat', 540: 'drilling platform, offshore rig', 541: 'drum, membranophone, tympan', 542: 'drumstick', 543: 'dumbbell', 544: 'Dutch oven', 545: 'electric fan, blower', 546: 'electric guitar', 547: 'electric locomotive', 548: 'entertainment center', 549: 'envelope', 550: 'espresso maker', 551: 'face powder', 552: 'feather boa, boa', 553: 'file, file cabinet, filing cabinet', 554: 'fireboat', 555: 'fire engine, fire truck', 556: 'fire screen, fireguard', 557: 'flagpole, flagstaff', 558: 'flute, transverse flute', 559: 'folding chair', 560: 'football helmet', 561: 'forklift', 562: 'fountain', 563: 'fountain pen', 564: 'four-poster', 565: 'freight car', 566: 'French horn, horn', 567: 'frying pan, frypan, skillet', 568: 'fur coat', 569: 'garbage truck, dustcart', 570: 'gasmask, respirator, gas helmet', 571: 'gas pump, gasoline pump, petrol pump, island dispenser', 572: 'goblet', 573: 'go-kart', 574: 'golf ball', 575: 'golfcart, golf cart', 576: 'gondola', 577: 'gong, tam-tam', 578: 'gown', 579: 'grand piano, grand', 580: 'greenhouse, nursery, glasshouse', 581: 'grille, radiator grille', 582: 'grocery store, grocery, food market, market', 583: 'guillotine', 584: 'hair slide', 585: 'hair spray', 586: 'half track', 587: 'hammer', 588: 'hamper', 589: 'hand blower, blow dryer, blow drier, hair dryer, hair drier', 590: 'hand-held computer, hand-held microcomputer', 591: 'handkerchief, hankie, hanky, hankey', 592: 'hard disc, hard disk, fixed disk', 593: 'harmonica, mouth organ, harp, mouth harp', 594: 'harp', 595: 'harvester, reaper', 596: 'hatchet', 597: 'holster', 598: 'home theater, home theatre', 599: 'honeycomb', 600: 'hook, claw', 601: 'hoopskirt, crinoline', 602: 'horizontal bar, high bar', 603: 'horse cart, horse-cart', 604: 'hourglass', 605: 'iPod', 606: 'iron, smoothing iron', 607: \"jack-o'-lantern\", 608: 'jean, blue jean, denim', 609: 'jeep, landrover', 610: 'jersey, T-shirt, tee shirt', 611: 'jigsaw puzzle', 612: 'jinrikisha, ricksha, rickshaw', 613: 'joystick', 614: 'kimono', 615: 'knee pad', 616: 'knot', 617: 'lab coat, laboratory coat', 618: 'ladle', 619: 'lampshade, lamp shade', 620: 'laptop, laptop computer', 621: 'lawn mower, mower', 622: 'lens cap, lens cover', 623: 'letter opener, paper knife, paperknife', 624: 'library', 625: 'lifeboat', 626: 'lighter, light, igniter, ignitor', 627: 'limousine, limo', 628: 'liner, ocean liner', 629: 'lipstick, lip rouge', 630: 'Loafer', 631: 'lotion', 632: 'loudspeaker, speaker, speaker unit, loudspeaker system, speaker system', 633: \"loupe, jeweler's loupe\", 634: 'lumbermill, sawmill', 635: 'magnetic compass', 636: 'mailbag, postbag', 637: 'mailbox, letter box', 638: 'maillot', 639: 'maillot, tank suit', 640: 'manhole cover', 641: 'maraca', 642: 'marimba, xylophone', 643: 'mask', 644: 'matchstick', 645: 'maypole', 646: 'maze, labyrinth', 647: 'measuring cup', 648: 'medicine chest, medicine cabinet', 649: 'megalith, megalithic structure', 650: 'microphone, mike', 651: 'microwave, microwave oven', 652: 'military uniform', 653: 'milk can', 654: 'minibus', 655: 'miniskirt, mini', 656: 'minivan', 657: 'missile', 658: 'mitten', 659: 'mixing bowl', 660: 'mobile home, manufactured home', 661: 'Model T', 662: 'modem', 663: 'monastery', 664: 'monitor', 665: 'moped', 666: 'mortar', 667: 'mortarboard', 668: 'mosque', 669: 'mosquito net', 670: 'motor scooter, scooter', 671: 'mountain bike, all-terrain bike, off-roader', 672: 'mountain tent', 673: 'mouse, computer mouse', 674: 'mousetrap', 675: 'moving van', 676: 'muzzle', 677: 'nail', 678: 'neck brace', 679: 'necklace', 680: 'nipple', 681: 'notebook, notebook computer', 682: 'obelisk', 683: 'oboe, hautboy, hautbois', 684: 'ocarina, sweet potato', 685: 'odometer, hodometer, mileometer, milometer', 686: 'oil filter', 687: 'organ, pipe organ', 688: 'oscilloscope, scope, cathode-ray oscilloscope, CRO', 689: 'overskirt', 690: 'oxcart', 691: 'oxygen mask', 692: 'packet', 693: 'paddle, boat paddle', 694: 'paddlewheel, paddle wheel', 695: 'padlock', 696: 'paintbrush', 697: \"pajama, pyjama, pj's, jammies\", 698: 'palace', 699: 'panpipe, pandean pipe, syrinx', 700: 'paper towel', 701: 'parachute, chute', 702: 'parallel bars, bars', 703: 'park bench', 704: 'parking meter', 705: 'passenger car, coach, carriage', 706: 'patio, terrace', 707: 'pay-phone, pay-station', 708: 'pedestal, plinth, footstall', 709: 'pencil box, pencil case', 710: 'pencil sharpener', 711: 'perfume, essence', 712: 'Petri dish', 713: 'photocopier', 714: 'pick, plectrum, plectron', 715: 'pickelhaube', 716: 'picket fence, paling', 717: 'pickup, pickup truck', 718: 'pier', 719: 'piggy bank, penny bank', 720: 'pill bottle', 721: 'pillow', 722: 'ping-pong ball', 723: 'pinwheel', 724: 'pirate, pirate ship', 725: 'pitcher, ewer', 726: \"plane, carpenter's plane, woodworking plane\", 727: 'planetarium', 728: 'plastic bag', 729: 'plate rack', 730: 'plow, plough', 731: \"plunger, plumber's helper\", 732: 'Polaroid camera, Polaroid Land camera', 733: 'pole', 734: 'police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria', 735: 'poncho', 736: 'pool table, billiard table, snooker table', 737: 'pop bottle, soda bottle', 738: 'pot, flowerpot', 739: \"potter's wheel\", 740: 'power drill', 741: 'prayer rug, prayer mat', 742: 'printer', 743: 'prison, prison house', 744: 'projectile, missile', 745: 'projector', 746: 'puck, hockey puck', 747: 'punching bag, punch bag, punching ball, punchball', 748: 'purse', 749: 'quill, quill pen', 750: 'quilt, comforter, comfort, puff', 751: 'racer, race car, racing car', 752: 'racket, racquet', 753: 'radiator', 754: 'radio, wireless', 755: 'radio telescope, radio reflector', 756: 'rain barrel', 757: 'recreational vehicle, RV, R.V.', 758: 'reel', 759: 'reflex camera', 760: 'refrigerator, icebox', 761: 'remote control, remote', 762: 'restaurant, eating house, eating place, eatery', 763: 'revolver, six-gun, six-shooter', 764: 'rifle', 765: 'rocking chair, rocker', 766: 'rotisserie', 767: 'rubber eraser, rubber, pencil eraser', 768: 'rugby ball', 769: 'rule, ruler', 770: 'running shoe', 771: 'safe', 772: 'safety pin', 773: 'saltshaker, salt shaker', 774: 'sandal', 775: 'sarong', 776: 'sax, saxophone', 777: 'scabbard', 778: 'scale, weighing machine', 779: 'school bus', 780: 'schooner', 781: 'scoreboard', 782: 'screen, CRT screen', 783: 'screw', 784: 'screwdriver', 785: 'seat belt, seatbelt', 786: 'sewing machine', 787: 'shield, buckler', 788: 'shoe shop, shoe-shop, shoe store', 789: 'shoji', 790: 'shopping basket', 791: 'shopping cart', 792: 'shovel', 793: 'shower cap', 794: 'shower curtain', 795: 'ski', 796: 'ski mask', 797: 'sleeping bag', 798: 'slide rule, slipstick', 799: 'sliding door', 800: 'slot, one-armed bandit', 801: 'snorkel', 802: 'snowmobile', 803: 'snowplow, snowplough', 804: 'soap dispenser', 805: 'soccer ball', 806: 'sock', 807: 'solar dish, solar collector, solar furnace', 808: 'sombrero', 809: 'soup bowl', 810: 'space bar', 811: 'space heater', 812: 'space shuttle', 813: 'spatula', 814: 'speedboat', 815: \"spider web, spider's web\", 816: 'spindle', 817: 'sports car, sport car', 818: 'spotlight, spot', 819: 'stage', 820: 'steam locomotive', 821: 'steel arch bridge', 822: 'steel drum', 823: 'stethoscope', 824: 'stole', 825: 'stone wall', 826: 'stopwatch, stop watch', 827: 'stove', 828: 'strainer', 829: 'streetcar, tram, tramcar, trolley, trolley car', 830: 'stretcher', 831: 'studio couch, day bed', 832: 'stupa, tope', 833: 'submarine, pigboat, sub, U-boat', 834: 'suit, suit of clothes', 835: 'sundial', 836: 'sunglass', 837: 'sunglasses, dark glasses, shades', 838: 'sunscreen, sunblock, sun blocker', 839: 'suspension bridge', 840: 'swab, swob, mop', 841: 'sweatshirt', 842: 'swimming trunks, bathing trunks', 843: 'swing', 844: 'switch, electric switch, electrical switch', 845: 'syringe', 846: 'table lamp', 847: 'tank, army tank, armored combat vehicle, armoured combat vehicle', 848: 'tape player', 849: 'teapot', 850: 'teddy, teddy bear', 851: 'television, television system', 852: 'tennis ball', 853: 'thatch, thatched roof', 854: 'theater curtain, theatre curtain', 855: 'thimble', 856: 'thresher, thrasher, threshing machine', 857: 'throne', 858: 'tile roof', 859: 'toaster', 860: 'tobacco shop, tobacconist shop, tobacconist', 861: 'toilet seat', 862: 'torch', 863: 'totem pole', 864: 'tow truck, tow car, wrecker', 865: 'toyshop', 866: 'tractor', 867: 'trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi', 868: 'tray', 869: 'trench coat', 870: 'tricycle, trike, velocipede', 871: 'trimaran', 872: 'tripod', 873: 'triumphal arch', 874: 'trolleybus, trolley coach, trackless trolley', 875: 'trombone', 876: 'tub, vat', 877: 'turnstile', 878: 'typewriter keyboard', 879: 'umbrella', 880: 'unicycle, monocycle', 881: 'upright, upright piano', 882: 'vacuum, vacuum cleaner', 883: 'vase', 884: 'vault', 885: 'velvet', 886: 'vending machine', 887: 'vestment', 888: 'viaduct', 889: 'violin, fiddle', 890: 'volleyball', 891: 'waffle iron', 892: 'wall clock', 893: 'wallet, billfold, notecase, pocketbook', 894: 'wardrobe, closet, press', 895: 'warplane, military plane', 896: 'washbasin, handbasin, washbowl, lavabo, wash-hand basin', 897: 'washer, automatic washer, washing machine', 898: 'water bottle', 899: 'water jug', 900: 'water tower', 901: 'whiskey jug', 902: 'whistle', 903: 'wig', 904: 'window screen', 905: 'window shade', 906: 'Windsor tie', 907: 'wine bottle', 908: 'wing', 909: 'wok', 910: 'wooden spoon', 911: 'wool, woolen, woollen', 912: 'worm fence, snake fence, snake-rail fence, Virginia fence', 913: 'wreck', 914: 'yawl', 915: 'yurt', 916: 'web site, website, internet site, site', 917: 'comic book', 918: 'crossword puzzle, crossword', 919: 'street sign', 920: 'traffic light, traffic signal, stoplight', 921: 'book jacket, dust cover, dust jacket, dust wrapper', 922: 'menu', 923: 'plate', 924: 'guacamole', 925: 'consomme', 926: 'hot pot, hotpot', 927: 'trifle', 928: 'ice cream, icecream', 929: 'ice lolly, lolly, lollipop, popsicle', 930: 'French loaf', 931: 'bagel, beigel', 932: 'pretzel', 933: 'cheeseburger', 934: 'hotdog, hot dog, red hot', 935: 'mashed potato', 936: 'head cabbage', 937: 'broccoli', 938: 'cauliflower', 939: 'zucchini, courgette', 940: 'spaghetti squash', 941: 'acorn squash', 942: 'butternut squash', 943: 'cucumber, cuke', 944: 'artichoke, globe artichoke', 945: 'bell pepper', 946: 'cardoon', 947: 'mushroom', 948: 'Granny Smith', 949: 'strawberry', 950: 'orange', 951: 'lemon', 952: 'fig', 953: 'pineapple, ananas', 954: 'banana', 955: 'jackfruit, jak, jack', 956: 'custard apple', 957: 'pomegranate', 958: 'hay', 959: 'carbonara', 960: 'chocolate sauce, chocolate syrup', 961: 'dough', 962: 'meat loaf, meatloaf', 963: 'pizza, pizza pie', 964: 'potpie', 965: 'burrito', 966: 'red wine', 967: 'espresso', 968: 'cup', 969: 'eggnog', 970: 'alp', 971: 'bubble', 972: 'cliff, drop, drop-off', 973: 'coral reef', 974: 'geyser', 975: 'lakeside, lakeshore', 976: 'promontory, headland, head, foreland', 977: 'sandbar, sand bar', 978: 'seashore, coast, seacoast, sea-coast', 979: 'valley, vale', 980: 'volcano', 981: 'ballplayer, baseball player', 982: 'groom, bridegroom', 983: 'scuba diver', 984: 'rapeseed', 985: 'daisy', 986: \"yellow lady's slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum\", 987: 'corn', 988: 'acorn', 989: 'hip, rose hip, rosehip', 990: 'buckeye, horse chestnut, conker', 991: 'coral fungus', 992: 'agaric', 993: 'gyromitra', 994: 'stinkhorn, carrion fungus', 995: 'earthstar', 996: 'hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa', 997: 'bolete', 998: 'ear, spike, capitulum', 999: 'toilet tissue, toilet paper, bathroom tissue'}"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fr6pOOh0hHaj"
      },
      "source": [
        "# Etapa 1: Importação das bibliotecas"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "QqPjanlXkVzi",
        "outputId": "2a0e8b63-1aff-4ee1-e9bb-da6134e9f656",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        }
      },
      "source": [
        "%tensorflow_version 2.x\n",
        "import tensorflow as tf\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "import random \n",
        "import zipfile\n",
        "tf.__version__"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'2.8.0'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 1
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "qqOSkGp9R55q"
      },
      "source": [
        "# Etapa 2: Importação do modelo com os pesos pré-trainados"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "wZuccYaR5YOr"
      },
      "source": [
        "model = tf.keras.applications.ResNet50(weights = 'imagenet')"
      ],
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "jWb45OshSDsr"
      },
      "source": [
        "# Etapa 3: Testes com o modelo pré-treinado"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-cfqEXakjdjd"
      },
      "source": [
        "- Visualização Imagenet: http://www.image-net.org/synset?wnid=n02835271\n",
        "- Pesquisa por bicicleta\n",
        "- https://lear.inrialpes.fr/people/gordo/ImageNetResults/sift1000_accuracy_withPrior/results_sift_0253.htm"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "IFhOG8Pjkue2",
        "outputId": "adce13e6-561c-47e1-993e-360eff6ea0bf",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive')"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "B8aq-TaNmJIb"
      },
      "source": [
        "path = \"/content/drive/My Drive/Datasets/Transfer-Learning-Data.zip\"\n",
        "zip_object = zipfile.ZipFile(file=path, mode=\"r\")\n",
        "zip_object.extractall(\"./\")\n",
        "zip_object.close()"
      ],
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "g5emeIG66i_h"
      },
      "source": [
        "sample_image = tf.keras.preprocessing.image.load_img(r'/content/Transfer Learning Data/bicycle.png', target_size=(224,224))"
      ],
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "p7Dz5EAq61zp",
        "outputId": "eb31323e-6fa0-4f6e-8fe6-f5b41625d1f8",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 286
        }
      },
      "source": [
        "plt.imshow(sample_image)"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.image.AxesImage at 0x7f1cc0170650>"
            ]
          },
          "metadata": {},
          "execution_count": 6
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "lBRcj8gD7IvN",
        "outputId": "aa9475e8-e6a1-499e-cec1-e8c72c5157c7",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "type(sample_image)"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "PIL.Image.Image"
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "DOMsZryl7MxC"
      },
      "source": [
        "sample_image = tf.keras.preprocessing.image.img_to_array(sample_image)"
      ],
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "39-_kKp37UGr",
        "outputId": "cf90cd27-46d7-47e3-b3fe-2bbf45289e4d",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "type(sample_image)"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "numpy.ndarray"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "zJFNWPkO7XI3",
        "outputId": "23c2ab7a-beac-4558-ad00-a5dcecce6186",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "np.shape(sample_image)"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(224, 224, 3)"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Jp9KDPCE7ez5"
      },
      "source": [
        "sample_image = np.expand_dims(sample_image, axis =0)"
      ],
      "execution_count": 11,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "HRVy8QiF7liD",
        "outputId": "35f05561-572a-4415-bc74-c9af228e1c2c",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "#torna a imagem como um elemento de 244x244 e 3 canais de cores\n",
        "sample_image.shape"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1, 224, 224, 3)"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_IUZmlD67pS9",
        "outputId": "2065e2f0-a7cd-41f2-feab-45188f89a973",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "sample_image.max()"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "255.0"
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "WjxLYS127s7T",
        "outputId": "b1f8654f-3ca8-4e50-8550-44a19be396a6",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "sample_image.min()"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.0"
            ]
          },
          "metadata": {},
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "rpjn6I1-7ziJ"
      },
      "source": [
        "#Preprocessa o input normalizando de acordo com o formato que a resnet espera\n",
        "sample_image = tf.keras.applications.resnet50.preprocess_input(sample_image)"
      ],
      "execution_count": 15,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "twAsWLAu8BEM",
        "outputId": "43f8e3e1-37ef-4709-b4b1-26f8cd7101a5",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "sample_image.max()"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "151.061"
            ]
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "eufOHRk48GOS",
        "outputId": "3d38ff06-b2ee-4686-fb7d-2a71e1148500",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "sample_image.min()"
      ],
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "-123.68"
            ]
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "wyK3e2Rc8Mde"
      },
      "source": [
        "predictions = model.predict(sample_image)"
      ],
      "execution_count": 18,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "DoHpjnYp8SFV",
        "outputId": "87cc06c0-f048-4da6-fc5b-933441a0cda5",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "#Mostra as 5 classes que a rede acha que aquela imagem é.\n",
        "\n",
        "print('predictions: ', tf.keras.applications.resnet50.decode_predictions(predictions, top = 5))"
      ],
      "execution_count": 19,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "predictions:  [[('n02835271', 'bicycle-built-for-two', 0.6329612), ('n03792782', 'mountain_bike', 0.053755645), ('n04482393', 'tricycle', 0.04975806), ('n03599486', 'jinrikisha', 0.01569029), ('n04507155', 'umbrella', 0.010513417)]]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "H38yzWMAn7hu"
      },
      "source": [
        "# Etapa 4: Transfer learning e reuso do modelo"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "QcUoh_nj-bit",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "9860938e-91c9-4c8b-845c-073ef052cd21"
      },
      "source": [
        "#Pega apenas a base do modelo.\n",
        "base_model = tf.keras.applications.ResNet50(weights = 'imagenet', include_top = False)"
      ],
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/resnet/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5\n",
            "94773248/94765736 [==============================] - 2s 0us/step\n",
            "94781440/94765736 [==============================] - 2s 0us/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "PuGsz2O3--oi",
        "outputId": "b48c631e-dc89-46b0-b973-2b36b9033139",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "base_model.summary()"
      ],
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model: \"resnet50\"\n",
            "__________________________________________________________________________________________________\n",
            " Layer (type)                   Output Shape         Param #     Connected to                     \n",
            "==================================================================================================\n",
            " input_2 (InputLayer)           [(None, None, None,  0           []                               \n",
            "                                 3)]                                                              \n",
            "                                                                                                  \n",
            " conv1_pad (ZeroPadding2D)      (None, None, None,   0           ['input_2[0][0]']                \n",
            "                                3)                                                                \n",
            "                                                                                                  \n",
            " conv1_conv (Conv2D)            (None, None, None,   9472        ['conv1_pad[0][0]']              \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv1_bn (BatchNormalization)  (None, None, None,   256         ['conv1_conv[0][0]']             \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv1_relu (Activation)        (None, None, None,   0           ['conv1_bn[0][0]']               \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " pool1_pad (ZeroPadding2D)      (None, None, None,   0           ['conv1_relu[0][0]']             \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " pool1_pool (MaxPooling2D)      (None, None, None,   0           ['pool1_pad[0][0]']              \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_1_conv (Conv2D)   (None, None, None,   4160        ['pool1_pool[0][0]']             \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_1_bn (BatchNormal  (None, None, None,   256        ['conv2_block1_1_conv[0][0]']    \n",
            " ization)                       64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_1_relu (Activatio  (None, None, None,   0          ['conv2_block1_1_bn[0][0]']      \n",
            " n)                             64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_2_conv (Conv2D)   (None, None, None,   36928       ['conv2_block1_1_relu[0][0]']    \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_2_bn (BatchNormal  (None, None, None,   256        ['conv2_block1_2_conv[0][0]']    \n",
            " ization)                       64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_2_relu (Activatio  (None, None, None,   0          ['conv2_block1_2_bn[0][0]']      \n",
            " n)                             64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_0_conv (Conv2D)   (None, None, None,   16640       ['pool1_pool[0][0]']             \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block1_3_conv (Conv2D)   (None, None, None,   16640       ['conv2_block1_2_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block1_0_bn (BatchNormal  (None, None, None,   1024       ['conv2_block1_0_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block1_3_bn (BatchNormal  (None, None, None,   1024       ['conv2_block1_3_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block1_add (Add)         (None, None, None,   0           ['conv2_block1_0_bn[0][0]',      \n",
            "                                256)                              'conv2_block1_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv2_block1_out (Activation)  (None, None, None,   0           ['conv2_block1_add[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block2_1_conv (Conv2D)   (None, None, None,   16448       ['conv2_block1_out[0][0]']       \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block2_1_bn (BatchNormal  (None, None, None,   256        ['conv2_block2_1_conv[0][0]']    \n",
            " ization)                       64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block2_1_relu (Activatio  (None, None, None,   0          ['conv2_block2_1_bn[0][0]']      \n",
            " n)                             64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block2_2_conv (Conv2D)   (None, None, None,   36928       ['conv2_block2_1_relu[0][0]']    \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block2_2_bn (BatchNormal  (None, None, None,   256        ['conv2_block2_2_conv[0][0]']    \n",
            " ization)                       64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block2_2_relu (Activatio  (None, None, None,   0          ['conv2_block2_2_bn[0][0]']      \n",
            " n)                             64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block2_3_conv (Conv2D)   (None, None, None,   16640       ['conv2_block2_2_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block2_3_bn (BatchNormal  (None, None, None,   1024       ['conv2_block2_3_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block2_add (Add)         (None, None, None,   0           ['conv2_block1_out[0][0]',       \n",
            "                                256)                              'conv2_block2_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv2_block2_out (Activation)  (None, None, None,   0           ['conv2_block2_add[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block3_1_conv (Conv2D)   (None, None, None,   16448       ['conv2_block2_out[0][0]']       \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block3_1_bn (BatchNormal  (None, None, None,   256        ['conv2_block3_1_conv[0][0]']    \n",
            " ization)                       64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block3_1_relu (Activatio  (None, None, None,   0          ['conv2_block3_1_bn[0][0]']      \n",
            " n)                             64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block3_2_conv (Conv2D)   (None, None, None,   36928       ['conv2_block3_1_relu[0][0]']    \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block3_2_bn (BatchNormal  (None, None, None,   256        ['conv2_block3_2_conv[0][0]']    \n",
            " ization)                       64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block3_2_relu (Activatio  (None, None, None,   0          ['conv2_block3_2_bn[0][0]']      \n",
            " n)                             64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block3_3_conv (Conv2D)   (None, None, None,   16640       ['conv2_block3_2_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block3_3_bn (BatchNormal  (None, None, None,   1024       ['conv2_block3_3_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block3_add (Add)         (None, None, None,   0           ['conv2_block2_out[0][0]',       \n",
            "                                256)                              'conv2_block3_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv2_block3_out (Activation)  (None, None, None,   0           ['conv2_block3_add[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_1_conv (Conv2D)   (None, None, None,   32896       ['conv2_block3_out[0][0]']       \n",
            "                                128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_1_bn (BatchNormal  (None, None, None,   512        ['conv3_block1_1_conv[0][0]']    \n",
            " ization)                       128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_1_relu (Activatio  (None, None, None,   0          ['conv3_block1_1_bn[0][0]']      \n",
            " n)                             128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_2_conv (Conv2D)   (None, None, None,   147584      ['conv3_block1_1_relu[0][0]']    \n",
            "                                128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_2_bn (BatchNormal  (None, None, None,   512        ['conv3_block1_2_conv[0][0]']    \n",
            " ization)                       128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_2_relu (Activatio  (None, None, None,   0          ['conv3_block1_2_bn[0][0]']      \n",
            " n)                             128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_0_conv (Conv2D)   (None, None, None,   131584      ['conv2_block3_out[0][0]']       \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_3_conv (Conv2D)   (None, None, None,   66048       ['conv3_block1_2_relu[0][0]']    \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_0_bn (BatchNormal  (None, None, None,   2048       ['conv3_block1_0_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_3_bn (BatchNormal  (None, None, None,   2048       ['conv3_block1_3_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_add (Add)         (None, None, None,   0           ['conv3_block1_0_bn[0][0]',      \n",
            "                                512)                              'conv3_block1_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv3_block1_out (Activation)  (None, None, None,   0           ['conv3_block1_add[0][0]']       \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_1_conv (Conv2D)   (None, None, None,   65664       ['conv3_block1_out[0][0]']       \n",
            "                                128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_1_bn (BatchNormal  (None, None, None,   512        ['conv3_block2_1_conv[0][0]']    \n",
            " ization)                       128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_1_relu (Activatio  (None, None, None,   0          ['conv3_block2_1_bn[0][0]']      \n",
            " n)                             128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_2_conv (Conv2D)   (None, None, None,   147584      ['conv3_block2_1_relu[0][0]']    \n",
            "                                128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_2_bn (BatchNormal  (None, None, None,   512        ['conv3_block2_2_conv[0][0]']    \n",
            " ization)                       128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_2_relu (Activatio  (None, None, None,   0          ['conv3_block2_2_bn[0][0]']      \n",
            " n)                             128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_3_conv (Conv2D)   (None, None, None,   66048       ['conv3_block2_2_relu[0][0]']    \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_3_bn (BatchNormal  (None, None, None,   2048       ['conv3_block2_3_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_add (Add)         (None, None, None,   0           ['conv3_block1_out[0][0]',       \n",
            "                                512)                              'conv3_block2_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv3_block2_out (Activation)  (None, None, None,   0           ['conv3_block2_add[0][0]']       \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_1_conv (Conv2D)   (None, None, None,   65664       ['conv3_block2_out[0][0]']       \n",
            "                                128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_1_bn (BatchNormal  (None, None, None,   512        ['conv3_block3_1_conv[0][0]']    \n",
            " ization)                       128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_1_relu (Activatio  (None, None, None,   0          ['conv3_block3_1_bn[0][0]']      \n",
            " n)                             128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_2_conv (Conv2D)   (None, None, None,   147584      ['conv3_block3_1_relu[0][0]']    \n",
            "                                128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_2_bn (BatchNormal  (None, None, None,   512        ['conv3_block3_2_conv[0][0]']    \n",
            " ization)                       128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_2_relu (Activatio  (None, None, None,   0          ['conv3_block3_2_bn[0][0]']      \n",
            " n)                             128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_3_conv (Conv2D)   (None, None, None,   66048       ['conv3_block3_2_relu[0][0]']    \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_3_bn (BatchNormal  (None, None, None,   2048       ['conv3_block3_3_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_add (Add)         (None, None, None,   0           ['conv3_block2_out[0][0]',       \n",
            "                                512)                              'conv3_block3_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv3_block3_out (Activation)  (None, None, None,   0           ['conv3_block3_add[0][0]']       \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_1_conv (Conv2D)   (None, None, None,   65664       ['conv3_block3_out[0][0]']       \n",
            "                                128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_1_bn (BatchNormal  (None, None, None,   512        ['conv3_block4_1_conv[0][0]']    \n",
            " ization)                       128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_1_relu (Activatio  (None, None, None,   0          ['conv3_block4_1_bn[0][0]']      \n",
            " n)                             128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_2_conv (Conv2D)   (None, None, None,   147584      ['conv3_block4_1_relu[0][0]']    \n",
            "                                128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_2_bn (BatchNormal  (None, None, None,   512        ['conv3_block4_2_conv[0][0]']    \n",
            " ization)                       128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_2_relu (Activatio  (None, None, None,   0          ['conv3_block4_2_bn[0][0]']      \n",
            " n)                             128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_3_conv (Conv2D)   (None, None, None,   66048       ['conv3_block4_2_relu[0][0]']    \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_3_bn (BatchNormal  (None, None, None,   2048       ['conv3_block4_3_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_add (Add)         (None, None, None,   0           ['conv3_block3_out[0][0]',       \n",
            "                                512)                              'conv3_block4_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv3_block4_out (Activation)  (None, None, None,   0           ['conv3_block4_add[0][0]']       \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv4_block1_1_conv (Conv2D)   (None, None, None,   131328      ['conv3_block4_out[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block1_1_bn (BatchNormal  (None, None, None,   1024       ['conv4_block1_1_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block1_1_relu (Activatio  (None, None, None,   0          ['conv4_block1_1_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block1_2_conv (Conv2D)   (None, None, None,   590080      ['conv4_block1_1_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block1_2_bn (BatchNormal  (None, None, None,   1024       ['conv4_block1_2_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block1_2_relu (Activatio  (None, None, None,   0          ['conv4_block1_2_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block1_0_conv (Conv2D)   (None, None, None,   525312      ['conv3_block4_out[0][0]']       \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block1_3_conv (Conv2D)   (None, None, None,   263168      ['conv4_block1_2_relu[0][0]']    \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block1_0_bn (BatchNormal  (None, None, None,   4096       ['conv4_block1_0_conv[0][0]']    \n",
            " ization)                       1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block1_3_bn (BatchNormal  (None, None, None,   4096       ['conv4_block1_3_conv[0][0]']    \n",
            " ization)                       1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block1_add (Add)         (None, None, None,   0           ['conv4_block1_0_bn[0][0]',      \n",
            "                                1024)                             'conv4_block1_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv4_block1_out (Activation)  (None, None, None,   0           ['conv4_block1_add[0][0]']       \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block2_1_conv (Conv2D)   (None, None, None,   262400      ['conv4_block1_out[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block2_1_bn (BatchNormal  (None, None, None,   1024       ['conv4_block2_1_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block2_1_relu (Activatio  (None, None, None,   0          ['conv4_block2_1_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block2_2_conv (Conv2D)   (None, None, None,   590080      ['conv4_block2_1_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block2_2_bn (BatchNormal  (None, None, None,   1024       ['conv4_block2_2_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block2_2_relu (Activatio  (None, None, None,   0          ['conv4_block2_2_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block2_3_conv (Conv2D)   (None, None, None,   263168      ['conv4_block2_2_relu[0][0]']    \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block2_3_bn (BatchNormal  (None, None, None,   4096       ['conv4_block2_3_conv[0][0]']    \n",
            " ization)                       1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block2_add (Add)         (None, None, None,   0           ['conv4_block1_out[0][0]',       \n",
            "                                1024)                             'conv4_block2_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv4_block2_out (Activation)  (None, None, None,   0           ['conv4_block2_add[0][0]']       \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block3_1_conv (Conv2D)   (None, None, None,   262400      ['conv4_block2_out[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block3_1_bn (BatchNormal  (None, None, None,   1024       ['conv4_block3_1_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block3_1_relu (Activatio  (None, None, None,   0          ['conv4_block3_1_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block3_2_conv (Conv2D)   (None, None, None,   590080      ['conv4_block3_1_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block3_2_bn (BatchNormal  (None, None, None,   1024       ['conv4_block3_2_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block3_2_relu (Activatio  (None, None, None,   0          ['conv4_block3_2_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block3_3_conv (Conv2D)   (None, None, None,   263168      ['conv4_block3_2_relu[0][0]']    \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block3_3_bn (BatchNormal  (None, None, None,   4096       ['conv4_block3_3_conv[0][0]']    \n",
            " ization)                       1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block3_add (Add)         (None, None, None,   0           ['conv4_block2_out[0][0]',       \n",
            "                                1024)                             'conv4_block3_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv4_block3_out (Activation)  (None, None, None,   0           ['conv4_block3_add[0][0]']       \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block4_1_conv (Conv2D)   (None, None, None,   262400      ['conv4_block3_out[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block4_1_bn (BatchNormal  (None, None, None,   1024       ['conv4_block4_1_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block4_1_relu (Activatio  (None, None, None,   0          ['conv4_block4_1_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block4_2_conv (Conv2D)   (None, None, None,   590080      ['conv4_block4_1_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block4_2_bn (BatchNormal  (None, None, None,   1024       ['conv4_block4_2_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block4_2_relu (Activatio  (None, None, None,   0          ['conv4_block4_2_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block4_3_conv (Conv2D)   (None, None, None,   263168      ['conv4_block4_2_relu[0][0]']    \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block4_3_bn (BatchNormal  (None, None, None,   4096       ['conv4_block4_3_conv[0][0]']    \n",
            " ization)                       1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block4_add (Add)         (None, None, None,   0           ['conv4_block3_out[0][0]',       \n",
            "                                1024)                             'conv4_block4_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv4_block4_out (Activation)  (None, None, None,   0           ['conv4_block4_add[0][0]']       \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block5_1_conv (Conv2D)   (None, None, None,   262400      ['conv4_block4_out[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block5_1_bn (BatchNormal  (None, None, None,   1024       ['conv4_block5_1_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block5_1_relu (Activatio  (None, None, None,   0          ['conv4_block5_1_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block5_2_conv (Conv2D)   (None, None, None,   590080      ['conv4_block5_1_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block5_2_bn (BatchNormal  (None, None, None,   1024       ['conv4_block5_2_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block5_2_relu (Activatio  (None, None, None,   0          ['conv4_block5_2_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block5_3_conv (Conv2D)   (None, None, None,   263168      ['conv4_block5_2_relu[0][0]']    \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block5_3_bn (BatchNormal  (None, None, None,   4096       ['conv4_block5_3_conv[0][0]']    \n",
            " ization)                       1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block5_add (Add)         (None, None, None,   0           ['conv4_block4_out[0][0]',       \n",
            "                                1024)                             'conv4_block5_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv4_block5_out (Activation)  (None, None, None,   0           ['conv4_block5_add[0][0]']       \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block6_1_conv (Conv2D)   (None, None, None,   262400      ['conv4_block5_out[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block6_1_bn (BatchNormal  (None, None, None,   1024       ['conv4_block6_1_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block6_1_relu (Activatio  (None, None, None,   0          ['conv4_block6_1_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block6_2_conv (Conv2D)   (None, None, None,   590080      ['conv4_block6_1_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block6_2_bn (BatchNormal  (None, None, None,   1024       ['conv4_block6_2_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block6_2_relu (Activatio  (None, None, None,   0          ['conv4_block6_2_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block6_3_conv (Conv2D)   (None, None, None,   263168      ['conv4_block6_2_relu[0][0]']    \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block6_3_bn (BatchNormal  (None, None, None,   4096       ['conv4_block6_3_conv[0][0]']    \n",
            " ization)                       1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block6_add (Add)         (None, None, None,   0           ['conv4_block5_out[0][0]',       \n",
            "                                1024)                             'conv4_block6_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv4_block6_out (Activation)  (None, None, None,   0           ['conv4_block6_add[0][0]']       \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv5_block1_1_conv (Conv2D)   (None, None, None,   524800      ['conv4_block6_out[0][0]']       \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block1_1_bn (BatchNormal  (None, None, None,   2048       ['conv5_block1_1_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block1_1_relu (Activatio  (None, None, None,   0          ['conv5_block1_1_bn[0][0]']      \n",
            " n)                             512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block1_2_conv (Conv2D)   (None, None, None,   2359808     ['conv5_block1_1_relu[0][0]']    \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block1_2_bn (BatchNormal  (None, None, None,   2048       ['conv5_block1_2_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block1_2_relu (Activatio  (None, None, None,   0          ['conv5_block1_2_bn[0][0]']      \n",
            " n)                             512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block1_0_conv (Conv2D)   (None, None, None,   2099200     ['conv4_block6_out[0][0]']       \n",
            "                                2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block1_3_conv (Conv2D)   (None, None, None,   1050624     ['conv5_block1_2_relu[0][0]']    \n",
            "                                2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block1_0_bn (BatchNormal  (None, None, None,   8192       ['conv5_block1_0_conv[0][0]']    \n",
            " ization)                       2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block1_3_bn (BatchNormal  (None, None, None,   8192       ['conv5_block1_3_conv[0][0]']    \n",
            " ization)                       2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block1_add (Add)         (None, None, None,   0           ['conv5_block1_0_bn[0][0]',      \n",
            "                                2048)                             'conv5_block1_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv5_block1_out (Activation)  (None, None, None,   0           ['conv5_block1_add[0][0]']       \n",
            "                                2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block2_1_conv (Conv2D)   (None, None, None,   1049088     ['conv5_block1_out[0][0]']       \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block2_1_bn (BatchNormal  (None, None, None,   2048       ['conv5_block2_1_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block2_1_relu (Activatio  (None, None, None,   0          ['conv5_block2_1_bn[0][0]']      \n",
            " n)                             512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block2_2_conv (Conv2D)   (None, None, None,   2359808     ['conv5_block2_1_relu[0][0]']    \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block2_2_bn (BatchNormal  (None, None, None,   2048       ['conv5_block2_2_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block2_2_relu (Activatio  (None, None, None,   0          ['conv5_block2_2_bn[0][0]']      \n",
            " n)                             512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block2_3_conv (Conv2D)   (None, None, None,   1050624     ['conv5_block2_2_relu[0][0]']    \n",
            "                                2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block2_3_bn (BatchNormal  (None, None, None,   8192       ['conv5_block2_3_conv[0][0]']    \n",
            " ization)                       2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block2_add (Add)         (None, None, None,   0           ['conv5_block1_out[0][0]',       \n",
            "                                2048)                             'conv5_block2_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv5_block2_out (Activation)  (None, None, None,   0           ['conv5_block2_add[0][0]']       \n",
            "                                2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block3_1_conv (Conv2D)   (None, None, None,   1049088     ['conv5_block2_out[0][0]']       \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block3_1_bn (BatchNormal  (None, None, None,   2048       ['conv5_block3_1_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block3_1_relu (Activatio  (None, None, None,   0          ['conv5_block3_1_bn[0][0]']      \n",
            " n)                             512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block3_2_conv (Conv2D)   (None, None, None,   2359808     ['conv5_block3_1_relu[0][0]']    \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block3_2_bn (BatchNormal  (None, None, None,   2048       ['conv5_block3_2_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block3_2_relu (Activatio  (None, None, None,   0          ['conv5_block3_2_bn[0][0]']      \n",
            " n)                             512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block3_3_conv (Conv2D)   (None, None, None,   1050624     ['conv5_block3_2_relu[0][0]']    \n",
            "                                2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block3_3_bn (BatchNormal  (None, None, None,   8192       ['conv5_block3_3_conv[0][0]']    \n",
            " ization)                       2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block3_add (Add)         (None, None, None,   0           ['conv5_block2_out[0][0]',       \n",
            "                                2048)                             'conv5_block3_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv5_block3_out (Activation)  (None, None, None,   0           ['conv5_block3_add[0][0]']       \n",
            "                                2048)                                                             \n",
            "                                                                                                  \n",
            "==================================================================================================\n",
            "Total params: 23,587,712\n",
            "Trainable params: 23,534,592\n",
            "Non-trainable params: 53,120\n",
            "__________________________________________________________________________________________________\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "755AOb7p_sHw"
      },
      "source": [
        "x = base_model.output"
      ],
      "execution_count": 22,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "W_yiEoYyAAG2"
      },
      "source": [
        "x = tf.keras.layers.GlobalAveragePooling2D()(x)"
      ],
      "execution_count": 23,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "xYgaxSP9AQzs"
      },
      "source": [
        "x = tf.keras.layers.Dense(1024, activation='relu')(x)\n",
        "x = tf.keras.layers.Dense(1024, activation='relu')(x)\n",
        "x = tf.keras.layers.Dense(1024, activation='relu')(x)\n",
        "x = tf.keras.layers.Dense(512, activation='relu')(x)\n",
        "preds = tf.keras.layers.Dense(2, activation='softmax')(x)"
      ],
      "execution_count": 24,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "iE_g-SjKA49Z"
      },
      "source": [
        "model = tf.keras.models.Model(inputs = base_model.input, outputs = preds)"
      ],
      "execution_count": 25,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "SDaUV1XvBQx8",
        "outputId": "69a1c024-ac98-4c26-d60a-7b1f471aac53",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "model.summary()"
      ],
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model: \"model\"\n",
            "__________________________________________________________________________________________________\n",
            " Layer (type)                   Output Shape         Param #     Connected to                     \n",
            "==================================================================================================\n",
            " input_2 (InputLayer)           [(None, None, None,  0           []                               \n",
            "                                 3)]                                                              \n",
            "                                                                                                  \n",
            " conv1_pad (ZeroPadding2D)      (None, None, None,   0           ['input_2[0][0]']                \n",
            "                                3)                                                                \n",
            "                                                                                                  \n",
            " conv1_conv (Conv2D)            (None, None, None,   9472        ['conv1_pad[0][0]']              \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv1_bn (BatchNormalization)  (None, None, None,   256         ['conv1_conv[0][0]']             \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv1_relu (Activation)        (None, None, None,   0           ['conv1_bn[0][0]']               \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " pool1_pad (ZeroPadding2D)      (None, None, None,   0           ['conv1_relu[0][0]']             \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " pool1_pool (MaxPooling2D)      (None, None, None,   0           ['pool1_pad[0][0]']              \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_1_conv (Conv2D)   (None, None, None,   4160        ['pool1_pool[0][0]']             \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_1_bn (BatchNormal  (None, None, None,   256        ['conv2_block1_1_conv[0][0]']    \n",
            " ization)                       64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_1_relu (Activatio  (None, None, None,   0          ['conv2_block1_1_bn[0][0]']      \n",
            " n)                             64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_2_conv (Conv2D)   (None, None, None,   36928       ['conv2_block1_1_relu[0][0]']    \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_2_bn (BatchNormal  (None, None, None,   256        ['conv2_block1_2_conv[0][0]']    \n",
            " ization)                       64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_2_relu (Activatio  (None, None, None,   0          ['conv2_block1_2_bn[0][0]']      \n",
            " n)                             64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block1_0_conv (Conv2D)   (None, None, None,   16640       ['pool1_pool[0][0]']             \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block1_3_conv (Conv2D)   (None, None, None,   16640       ['conv2_block1_2_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block1_0_bn (BatchNormal  (None, None, None,   1024       ['conv2_block1_0_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block1_3_bn (BatchNormal  (None, None, None,   1024       ['conv2_block1_3_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block1_add (Add)         (None, None, None,   0           ['conv2_block1_0_bn[0][0]',      \n",
            "                                256)                              'conv2_block1_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv2_block1_out (Activation)  (None, None, None,   0           ['conv2_block1_add[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block2_1_conv (Conv2D)   (None, None, None,   16448       ['conv2_block1_out[0][0]']       \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block2_1_bn (BatchNormal  (None, None, None,   256        ['conv2_block2_1_conv[0][0]']    \n",
            " ization)                       64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block2_1_relu (Activatio  (None, None, None,   0          ['conv2_block2_1_bn[0][0]']      \n",
            " n)                             64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block2_2_conv (Conv2D)   (None, None, None,   36928       ['conv2_block2_1_relu[0][0]']    \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block2_2_bn (BatchNormal  (None, None, None,   256        ['conv2_block2_2_conv[0][0]']    \n",
            " ization)                       64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block2_2_relu (Activatio  (None, None, None,   0          ['conv2_block2_2_bn[0][0]']      \n",
            " n)                             64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block2_3_conv (Conv2D)   (None, None, None,   16640       ['conv2_block2_2_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block2_3_bn (BatchNormal  (None, None, None,   1024       ['conv2_block2_3_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block2_add (Add)         (None, None, None,   0           ['conv2_block1_out[0][0]',       \n",
            "                                256)                              'conv2_block2_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv2_block2_out (Activation)  (None, None, None,   0           ['conv2_block2_add[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block3_1_conv (Conv2D)   (None, None, None,   16448       ['conv2_block2_out[0][0]']       \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block3_1_bn (BatchNormal  (None, None, None,   256        ['conv2_block3_1_conv[0][0]']    \n",
            " ization)                       64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block3_1_relu (Activatio  (None, None, None,   0          ['conv2_block3_1_bn[0][0]']      \n",
            " n)                             64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block3_2_conv (Conv2D)   (None, None, None,   36928       ['conv2_block3_1_relu[0][0]']    \n",
            "                                64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block3_2_bn (BatchNormal  (None, None, None,   256        ['conv2_block3_2_conv[0][0]']    \n",
            " ization)                       64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block3_2_relu (Activatio  (None, None, None,   0          ['conv2_block3_2_bn[0][0]']      \n",
            " n)                             64)                                                               \n",
            "                                                                                                  \n",
            " conv2_block3_3_conv (Conv2D)   (None, None, None,   16640       ['conv2_block3_2_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block3_3_bn (BatchNormal  (None, None, None,   1024       ['conv2_block3_3_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv2_block3_add (Add)         (None, None, None,   0           ['conv2_block2_out[0][0]',       \n",
            "                                256)                              'conv2_block3_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv2_block3_out (Activation)  (None, None, None,   0           ['conv2_block3_add[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_1_conv (Conv2D)   (None, None, None,   32896       ['conv2_block3_out[0][0]']       \n",
            "                                128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_1_bn (BatchNormal  (None, None, None,   512        ['conv3_block1_1_conv[0][0]']    \n",
            " ization)                       128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_1_relu (Activatio  (None, None, None,   0          ['conv3_block1_1_bn[0][0]']      \n",
            " n)                             128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_2_conv (Conv2D)   (None, None, None,   147584      ['conv3_block1_1_relu[0][0]']    \n",
            "                                128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_2_bn (BatchNormal  (None, None, None,   512        ['conv3_block1_2_conv[0][0]']    \n",
            " ization)                       128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_2_relu (Activatio  (None, None, None,   0          ['conv3_block1_2_bn[0][0]']      \n",
            " n)                             128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_0_conv (Conv2D)   (None, None, None,   131584      ['conv2_block3_out[0][0]']       \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_3_conv (Conv2D)   (None, None, None,   66048       ['conv3_block1_2_relu[0][0]']    \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_0_bn (BatchNormal  (None, None, None,   2048       ['conv3_block1_0_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_3_bn (BatchNormal  (None, None, None,   2048       ['conv3_block1_3_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block1_add (Add)         (None, None, None,   0           ['conv3_block1_0_bn[0][0]',      \n",
            "                                512)                              'conv3_block1_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv3_block1_out (Activation)  (None, None, None,   0           ['conv3_block1_add[0][0]']       \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_1_conv (Conv2D)   (None, None, None,   65664       ['conv3_block1_out[0][0]']       \n",
            "                                128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_1_bn (BatchNormal  (None, None, None,   512        ['conv3_block2_1_conv[0][0]']    \n",
            " ization)                       128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_1_relu (Activatio  (None, None, None,   0          ['conv3_block2_1_bn[0][0]']      \n",
            " n)                             128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_2_conv (Conv2D)   (None, None, None,   147584      ['conv3_block2_1_relu[0][0]']    \n",
            "                                128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_2_bn (BatchNormal  (None, None, None,   512        ['conv3_block2_2_conv[0][0]']    \n",
            " ization)                       128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_2_relu (Activatio  (None, None, None,   0          ['conv3_block2_2_bn[0][0]']      \n",
            " n)                             128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_3_conv (Conv2D)   (None, None, None,   66048       ['conv3_block2_2_relu[0][0]']    \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_3_bn (BatchNormal  (None, None, None,   2048       ['conv3_block2_3_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block2_add (Add)         (None, None, None,   0           ['conv3_block1_out[0][0]',       \n",
            "                                512)                              'conv3_block2_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv3_block2_out (Activation)  (None, None, None,   0           ['conv3_block2_add[0][0]']       \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_1_conv (Conv2D)   (None, None, None,   65664       ['conv3_block2_out[0][0]']       \n",
            "                                128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_1_bn (BatchNormal  (None, None, None,   512        ['conv3_block3_1_conv[0][0]']    \n",
            " ization)                       128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_1_relu (Activatio  (None, None, None,   0          ['conv3_block3_1_bn[0][0]']      \n",
            " n)                             128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_2_conv (Conv2D)   (None, None, None,   147584      ['conv3_block3_1_relu[0][0]']    \n",
            "                                128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_2_bn (BatchNormal  (None, None, None,   512        ['conv3_block3_2_conv[0][0]']    \n",
            " ization)                       128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_2_relu (Activatio  (None, None, None,   0          ['conv3_block3_2_bn[0][0]']      \n",
            " n)                             128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_3_conv (Conv2D)   (None, None, None,   66048       ['conv3_block3_2_relu[0][0]']    \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_3_bn (BatchNormal  (None, None, None,   2048       ['conv3_block3_3_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block3_add (Add)         (None, None, None,   0           ['conv3_block2_out[0][0]',       \n",
            "                                512)                              'conv3_block3_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv3_block3_out (Activation)  (None, None, None,   0           ['conv3_block3_add[0][0]']       \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_1_conv (Conv2D)   (None, None, None,   65664       ['conv3_block3_out[0][0]']       \n",
            "                                128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_1_bn (BatchNormal  (None, None, None,   512        ['conv3_block4_1_conv[0][0]']    \n",
            " ization)                       128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_1_relu (Activatio  (None, None, None,   0          ['conv3_block4_1_bn[0][0]']      \n",
            " n)                             128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_2_conv (Conv2D)   (None, None, None,   147584      ['conv3_block4_1_relu[0][0]']    \n",
            "                                128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_2_bn (BatchNormal  (None, None, None,   512        ['conv3_block4_2_conv[0][0]']    \n",
            " ization)                       128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_2_relu (Activatio  (None, None, None,   0          ['conv3_block4_2_bn[0][0]']      \n",
            " n)                             128)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_3_conv (Conv2D)   (None, None, None,   66048       ['conv3_block4_2_relu[0][0]']    \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_3_bn (BatchNormal  (None, None, None,   2048       ['conv3_block4_3_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv3_block4_add (Add)         (None, None, None,   0           ['conv3_block3_out[0][0]',       \n",
            "                                512)                              'conv3_block4_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv3_block4_out (Activation)  (None, None, None,   0           ['conv3_block4_add[0][0]']       \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv4_block1_1_conv (Conv2D)   (None, None, None,   131328      ['conv3_block4_out[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block1_1_bn (BatchNormal  (None, None, None,   1024       ['conv4_block1_1_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block1_1_relu (Activatio  (None, None, None,   0          ['conv4_block1_1_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block1_2_conv (Conv2D)   (None, None, None,   590080      ['conv4_block1_1_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block1_2_bn (BatchNormal  (None, None, None,   1024       ['conv4_block1_2_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block1_2_relu (Activatio  (None, None, None,   0          ['conv4_block1_2_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block1_0_conv (Conv2D)   (None, None, None,   525312      ['conv3_block4_out[0][0]']       \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block1_3_conv (Conv2D)   (None, None, None,   263168      ['conv4_block1_2_relu[0][0]']    \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block1_0_bn (BatchNormal  (None, None, None,   4096       ['conv4_block1_0_conv[0][0]']    \n",
            " ization)                       1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block1_3_bn (BatchNormal  (None, None, None,   4096       ['conv4_block1_3_conv[0][0]']    \n",
            " ization)                       1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block1_add (Add)         (None, None, None,   0           ['conv4_block1_0_bn[0][0]',      \n",
            "                                1024)                             'conv4_block1_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv4_block1_out (Activation)  (None, None, None,   0           ['conv4_block1_add[0][0]']       \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block2_1_conv (Conv2D)   (None, None, None,   262400      ['conv4_block1_out[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block2_1_bn (BatchNormal  (None, None, None,   1024       ['conv4_block2_1_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block2_1_relu (Activatio  (None, None, None,   0          ['conv4_block2_1_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block2_2_conv (Conv2D)   (None, None, None,   590080      ['conv4_block2_1_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block2_2_bn (BatchNormal  (None, None, None,   1024       ['conv4_block2_2_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block2_2_relu (Activatio  (None, None, None,   0          ['conv4_block2_2_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block2_3_conv (Conv2D)   (None, None, None,   263168      ['conv4_block2_2_relu[0][0]']    \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block2_3_bn (BatchNormal  (None, None, None,   4096       ['conv4_block2_3_conv[0][0]']    \n",
            " ization)                       1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block2_add (Add)         (None, None, None,   0           ['conv4_block1_out[0][0]',       \n",
            "                                1024)                             'conv4_block2_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv4_block2_out (Activation)  (None, None, None,   0           ['conv4_block2_add[0][0]']       \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block3_1_conv (Conv2D)   (None, None, None,   262400      ['conv4_block2_out[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block3_1_bn (BatchNormal  (None, None, None,   1024       ['conv4_block3_1_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block3_1_relu (Activatio  (None, None, None,   0          ['conv4_block3_1_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block3_2_conv (Conv2D)   (None, None, None,   590080      ['conv4_block3_1_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block3_2_bn (BatchNormal  (None, None, None,   1024       ['conv4_block3_2_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block3_2_relu (Activatio  (None, None, None,   0          ['conv4_block3_2_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block3_3_conv (Conv2D)   (None, None, None,   263168      ['conv4_block3_2_relu[0][0]']    \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block3_3_bn (BatchNormal  (None, None, None,   4096       ['conv4_block3_3_conv[0][0]']    \n",
            " ization)                       1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block3_add (Add)         (None, None, None,   0           ['conv4_block2_out[0][0]',       \n",
            "                                1024)                             'conv4_block3_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv4_block3_out (Activation)  (None, None, None,   0           ['conv4_block3_add[0][0]']       \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block4_1_conv (Conv2D)   (None, None, None,   262400      ['conv4_block3_out[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block4_1_bn (BatchNormal  (None, None, None,   1024       ['conv4_block4_1_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block4_1_relu (Activatio  (None, None, None,   0          ['conv4_block4_1_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block4_2_conv (Conv2D)   (None, None, None,   590080      ['conv4_block4_1_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block4_2_bn (BatchNormal  (None, None, None,   1024       ['conv4_block4_2_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block4_2_relu (Activatio  (None, None, None,   0          ['conv4_block4_2_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block4_3_conv (Conv2D)   (None, None, None,   263168      ['conv4_block4_2_relu[0][0]']    \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block4_3_bn (BatchNormal  (None, None, None,   4096       ['conv4_block4_3_conv[0][0]']    \n",
            " ization)                       1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block4_add (Add)         (None, None, None,   0           ['conv4_block3_out[0][0]',       \n",
            "                                1024)                             'conv4_block4_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv4_block4_out (Activation)  (None, None, None,   0           ['conv4_block4_add[0][0]']       \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block5_1_conv (Conv2D)   (None, None, None,   262400      ['conv4_block4_out[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block5_1_bn (BatchNormal  (None, None, None,   1024       ['conv4_block5_1_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block5_1_relu (Activatio  (None, None, None,   0          ['conv4_block5_1_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block5_2_conv (Conv2D)   (None, None, None,   590080      ['conv4_block5_1_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block5_2_bn (BatchNormal  (None, None, None,   1024       ['conv4_block5_2_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block5_2_relu (Activatio  (None, None, None,   0          ['conv4_block5_2_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block5_3_conv (Conv2D)   (None, None, None,   263168      ['conv4_block5_2_relu[0][0]']    \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block5_3_bn (BatchNormal  (None, None, None,   4096       ['conv4_block5_3_conv[0][0]']    \n",
            " ization)                       1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block5_add (Add)         (None, None, None,   0           ['conv4_block4_out[0][0]',       \n",
            "                                1024)                             'conv4_block5_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv4_block5_out (Activation)  (None, None, None,   0           ['conv4_block5_add[0][0]']       \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block6_1_conv (Conv2D)   (None, None, None,   262400      ['conv4_block5_out[0][0]']       \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block6_1_bn (BatchNormal  (None, None, None,   1024       ['conv4_block6_1_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block6_1_relu (Activatio  (None, None, None,   0          ['conv4_block6_1_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block6_2_conv (Conv2D)   (None, None, None,   590080      ['conv4_block6_1_relu[0][0]']    \n",
            "                                256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block6_2_bn (BatchNormal  (None, None, None,   1024       ['conv4_block6_2_conv[0][0]']    \n",
            " ization)                       256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block6_2_relu (Activatio  (None, None, None,   0          ['conv4_block6_2_bn[0][0]']      \n",
            " n)                             256)                                                              \n",
            "                                                                                                  \n",
            " conv4_block6_3_conv (Conv2D)   (None, None, None,   263168      ['conv4_block6_2_relu[0][0]']    \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block6_3_bn (BatchNormal  (None, None, None,   4096       ['conv4_block6_3_conv[0][0]']    \n",
            " ization)                       1024)                                                             \n",
            "                                                                                                  \n",
            " conv4_block6_add (Add)         (None, None, None,   0           ['conv4_block5_out[0][0]',       \n",
            "                                1024)                             'conv4_block6_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv4_block6_out (Activation)  (None, None, None,   0           ['conv4_block6_add[0][0]']       \n",
            "                                1024)                                                             \n",
            "                                                                                                  \n",
            " conv5_block1_1_conv (Conv2D)   (None, None, None,   524800      ['conv4_block6_out[0][0]']       \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block1_1_bn (BatchNormal  (None, None, None,   2048       ['conv5_block1_1_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block1_1_relu (Activatio  (None, None, None,   0          ['conv5_block1_1_bn[0][0]']      \n",
            " n)                             512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block1_2_conv (Conv2D)   (None, None, None,   2359808     ['conv5_block1_1_relu[0][0]']    \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block1_2_bn (BatchNormal  (None, None, None,   2048       ['conv5_block1_2_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block1_2_relu (Activatio  (None, None, None,   0          ['conv5_block1_2_bn[0][0]']      \n",
            " n)                             512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block1_0_conv (Conv2D)   (None, None, None,   2099200     ['conv4_block6_out[0][0]']       \n",
            "                                2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block1_3_conv (Conv2D)   (None, None, None,   1050624     ['conv5_block1_2_relu[0][0]']    \n",
            "                                2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block1_0_bn (BatchNormal  (None, None, None,   8192       ['conv5_block1_0_conv[0][0]']    \n",
            " ization)                       2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block1_3_bn (BatchNormal  (None, None, None,   8192       ['conv5_block1_3_conv[0][0]']    \n",
            " ization)                       2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block1_add (Add)         (None, None, None,   0           ['conv5_block1_0_bn[0][0]',      \n",
            "                                2048)                             'conv5_block1_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv5_block1_out (Activation)  (None, None, None,   0           ['conv5_block1_add[0][0]']       \n",
            "                                2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block2_1_conv (Conv2D)   (None, None, None,   1049088     ['conv5_block1_out[0][0]']       \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block2_1_bn (BatchNormal  (None, None, None,   2048       ['conv5_block2_1_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block2_1_relu (Activatio  (None, None, None,   0          ['conv5_block2_1_bn[0][0]']      \n",
            " n)                             512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block2_2_conv (Conv2D)   (None, None, None,   2359808     ['conv5_block2_1_relu[0][0]']    \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block2_2_bn (BatchNormal  (None, None, None,   2048       ['conv5_block2_2_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block2_2_relu (Activatio  (None, None, None,   0          ['conv5_block2_2_bn[0][0]']      \n",
            " n)                             512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block2_3_conv (Conv2D)   (None, None, None,   1050624     ['conv5_block2_2_relu[0][0]']    \n",
            "                                2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block2_3_bn (BatchNormal  (None, None, None,   8192       ['conv5_block2_3_conv[0][0]']    \n",
            " ization)                       2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block2_add (Add)         (None, None, None,   0           ['conv5_block1_out[0][0]',       \n",
            "                                2048)                             'conv5_block2_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv5_block2_out (Activation)  (None, None, None,   0           ['conv5_block2_add[0][0]']       \n",
            "                                2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block3_1_conv (Conv2D)   (None, None, None,   1049088     ['conv5_block2_out[0][0]']       \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block3_1_bn (BatchNormal  (None, None, None,   2048       ['conv5_block3_1_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block3_1_relu (Activatio  (None, None, None,   0          ['conv5_block3_1_bn[0][0]']      \n",
            " n)                             512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block3_2_conv (Conv2D)   (None, None, None,   2359808     ['conv5_block3_1_relu[0][0]']    \n",
            "                                512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block3_2_bn (BatchNormal  (None, None, None,   2048       ['conv5_block3_2_conv[0][0]']    \n",
            " ization)                       512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block3_2_relu (Activatio  (None, None, None,   0          ['conv5_block3_2_bn[0][0]']      \n",
            " n)                             512)                                                              \n",
            "                                                                                                  \n",
            " conv5_block3_3_conv (Conv2D)   (None, None, None,   1050624     ['conv5_block3_2_relu[0][0]']    \n",
            "                                2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block3_3_bn (BatchNormal  (None, None, None,   8192       ['conv5_block3_3_conv[0][0]']    \n",
            " ization)                       2048)                                                             \n",
            "                                                                                                  \n",
            " conv5_block3_add (Add)         (None, None, None,   0           ['conv5_block2_out[0][0]',       \n",
            "                                2048)                             'conv5_block3_3_bn[0][0]']      \n",
            "                                                                                                  \n",
            " conv5_block3_out (Activation)  (None, None, None,   0           ['conv5_block3_add[0][0]']       \n",
            "                                2048)                                                             \n",
            "                                                                                                  \n",
            " global_average_pooling2d (Glob  (None, 2048)        0           ['conv5_block3_out[0][0]']       \n",
            " alAveragePooling2D)                                                                              \n",
            "                                                                                                  \n",
            " dense (Dense)                  (None, 1024)         2098176     ['global_average_pooling2d[0][0]'\n",
            "                                                                 ]                                \n",
            "                                                                                                  \n",
            " dense_1 (Dense)                (None, 1024)         1049600     ['dense[0][0]']                  \n",
            "                                                                                                  \n",
            " dense_2 (Dense)                (None, 1024)         1049600     ['dense_1[0][0]']                \n",
            "                                                                                                  \n",
            " dense_3 (Dense)                (None, 512)          524800      ['dense_2[0][0]']                \n",
            "                                                                                                  \n",
            " dense_4 (Dense)                (None, 2)            1026        ['dense_3[0][0]']                \n",
            "                                                                                                  \n",
            "==================================================================================================\n",
            "Total params: 28,310,914\n",
            "Trainable params: 28,257,794\n",
            "Non-trainable params: 53,120\n",
            "__________________________________________________________________________________________________\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "l_Hf89qpBhBU",
        "outputId": "fe6ea8a2-081a-454c-f589-9a7201950959",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "for i, layer in enumerate(model.layers):\n",
        "  print(i, layer.name)"
      ],
      "execution_count": 27,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0 input_2\n",
            "1 conv1_pad\n",
            "2 conv1_conv\n",
            "3 conv1_bn\n",
            "4 conv1_relu\n",
            "5 pool1_pad\n",
            "6 pool1_pool\n",
            "7 conv2_block1_1_conv\n",
            "8 conv2_block1_1_bn\n",
            "9 conv2_block1_1_relu\n",
            "10 conv2_block1_2_conv\n",
            "11 conv2_block1_2_bn\n",
            "12 conv2_block1_2_relu\n",
            "13 conv2_block1_0_conv\n",
            "14 conv2_block1_3_conv\n",
            "15 conv2_block1_0_bn\n",
            "16 conv2_block1_3_bn\n",
            "17 conv2_block1_add\n",
            "18 conv2_block1_out\n",
            "19 conv2_block2_1_conv\n",
            "20 conv2_block2_1_bn\n",
            "21 conv2_block2_1_relu\n",
            "22 conv2_block2_2_conv\n",
            "23 conv2_block2_2_bn\n",
            "24 conv2_block2_2_relu\n",
            "25 conv2_block2_3_conv\n",
            "26 conv2_block2_3_bn\n",
            "27 conv2_block2_add\n",
            "28 conv2_block2_out\n",
            "29 conv2_block3_1_conv\n",
            "30 conv2_block3_1_bn\n",
            "31 conv2_block3_1_relu\n",
            "32 conv2_block3_2_conv\n",
            "33 conv2_block3_2_bn\n",
            "34 conv2_block3_2_relu\n",
            "35 conv2_block3_3_conv\n",
            "36 conv2_block3_3_bn\n",
            "37 conv2_block3_add\n",
            "38 conv2_block3_out\n",
            "39 conv3_block1_1_conv\n",
            "40 conv3_block1_1_bn\n",
            "41 conv3_block1_1_relu\n",
            "42 conv3_block1_2_conv\n",
            "43 conv3_block1_2_bn\n",
            "44 conv3_block1_2_relu\n",
            "45 conv3_block1_0_conv\n",
            "46 conv3_block1_3_conv\n",
            "47 conv3_block1_0_bn\n",
            "48 conv3_block1_3_bn\n",
            "49 conv3_block1_add\n",
            "50 conv3_block1_out\n",
            "51 conv3_block2_1_conv\n",
            "52 conv3_block2_1_bn\n",
            "53 conv3_block2_1_relu\n",
            "54 conv3_block2_2_conv\n",
            "55 conv3_block2_2_bn\n",
            "56 conv3_block2_2_relu\n",
            "57 conv3_block2_3_conv\n",
            "58 conv3_block2_3_bn\n",
            "59 conv3_block2_add\n",
            "60 conv3_block2_out\n",
            "61 conv3_block3_1_conv\n",
            "62 conv3_block3_1_bn\n",
            "63 conv3_block3_1_relu\n",
            "64 conv3_block3_2_conv\n",
            "65 conv3_block3_2_bn\n",
            "66 conv3_block3_2_relu\n",
            "67 conv3_block3_3_conv\n",
            "68 conv3_block3_3_bn\n",
            "69 conv3_block3_add\n",
            "70 conv3_block3_out\n",
            "71 conv3_block4_1_conv\n",
            "72 conv3_block4_1_bn\n",
            "73 conv3_block4_1_relu\n",
            "74 conv3_block4_2_conv\n",
            "75 conv3_block4_2_bn\n",
            "76 conv3_block4_2_relu\n",
            "77 conv3_block4_3_conv\n",
            "78 conv3_block4_3_bn\n",
            "79 conv3_block4_add\n",
            "80 conv3_block4_out\n",
            "81 conv4_block1_1_conv\n",
            "82 conv4_block1_1_bn\n",
            "83 conv4_block1_1_relu\n",
            "84 conv4_block1_2_conv\n",
            "85 conv4_block1_2_bn\n",
            "86 conv4_block1_2_relu\n",
            "87 conv4_block1_0_conv\n",
            "88 conv4_block1_3_conv\n",
            "89 conv4_block1_0_bn\n",
            "90 conv4_block1_3_bn\n",
            "91 conv4_block1_add\n",
            "92 conv4_block1_out\n",
            "93 conv4_block2_1_conv\n",
            "94 conv4_block2_1_bn\n",
            "95 conv4_block2_1_relu\n",
            "96 conv4_block2_2_conv\n",
            "97 conv4_block2_2_bn\n",
            "98 conv4_block2_2_relu\n",
            "99 conv4_block2_3_conv\n",
            "100 conv4_block2_3_bn\n",
            "101 conv4_block2_add\n",
            "102 conv4_block2_out\n",
            "103 conv4_block3_1_conv\n",
            "104 conv4_block3_1_bn\n",
            "105 conv4_block3_1_relu\n",
            "106 conv4_block3_2_conv\n",
            "107 conv4_block3_2_bn\n",
            "108 conv4_block3_2_relu\n",
            "109 conv4_block3_3_conv\n",
            "110 conv4_block3_3_bn\n",
            "111 conv4_block3_add\n",
            "112 conv4_block3_out\n",
            "113 conv4_block4_1_conv\n",
            "114 conv4_block4_1_bn\n",
            "115 conv4_block4_1_relu\n",
            "116 conv4_block4_2_conv\n",
            "117 conv4_block4_2_bn\n",
            "118 conv4_block4_2_relu\n",
            "119 conv4_block4_3_conv\n",
            "120 conv4_block4_3_bn\n",
            "121 conv4_block4_add\n",
            "122 conv4_block4_out\n",
            "123 conv4_block5_1_conv\n",
            "124 conv4_block5_1_bn\n",
            "125 conv4_block5_1_relu\n",
            "126 conv4_block5_2_conv\n",
            "127 conv4_block5_2_bn\n",
            "128 conv4_block5_2_relu\n",
            "129 conv4_block5_3_conv\n",
            "130 conv4_block5_3_bn\n",
            "131 conv4_block5_add\n",
            "132 conv4_block5_out\n",
            "133 conv4_block6_1_conv\n",
            "134 conv4_block6_1_bn\n",
            "135 conv4_block6_1_relu\n",
            "136 conv4_block6_2_conv\n",
            "137 conv4_block6_2_bn\n",
            "138 conv4_block6_2_relu\n",
            "139 conv4_block6_3_conv\n",
            "140 conv4_block6_3_bn\n",
            "141 conv4_block6_add\n",
            "142 conv4_block6_out\n",
            "143 conv5_block1_1_conv\n",
            "144 conv5_block1_1_bn\n",
            "145 conv5_block1_1_relu\n",
            "146 conv5_block1_2_conv\n",
            "147 conv5_block1_2_bn\n",
            "148 conv5_block1_2_relu\n",
            "149 conv5_block1_0_conv\n",
            "150 conv5_block1_3_conv\n",
            "151 conv5_block1_0_bn\n",
            "152 conv5_block1_3_bn\n",
            "153 conv5_block1_add\n",
            "154 conv5_block1_out\n",
            "155 conv5_block2_1_conv\n",
            "156 conv5_block2_1_bn\n",
            "157 conv5_block2_1_relu\n",
            "158 conv5_block2_2_conv\n",
            "159 conv5_block2_2_bn\n",
            "160 conv5_block2_2_relu\n",
            "161 conv5_block2_3_conv\n",
            "162 conv5_block2_3_bn\n",
            "163 conv5_block2_add\n",
            "164 conv5_block2_out\n",
            "165 conv5_block3_1_conv\n",
            "166 conv5_block3_1_bn\n",
            "167 conv5_block3_1_relu\n",
            "168 conv5_block3_2_conv\n",
            "169 conv5_block3_2_bn\n",
            "170 conv5_block3_2_relu\n",
            "171 conv5_block3_3_conv\n",
            "172 conv5_block3_3_bn\n",
            "173 conv5_block3_add\n",
            "174 conv5_block3_out\n",
            "175 global_average_pooling2d\n",
            "176 dense\n",
            "177 dense_1\n",
            "178 dense_2\n",
            "179 dense_3\n",
            "180 dense_4\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "aLqKaw5vBvcB"
      },
      "source": [
        "for layer in model.layers[:175]:\n",
        "  layer.trainable = False"
      ],
      "execution_count": 28,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "WbLni6RPB7qD"
      },
      "source": [
        "for layer in model.layers[175:]:\n",
        "  layer.trainable = True"
      ],
      "execution_count": 29,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "DdwM_MJFCcQm"
      },
      "source": [
        "train_datagen = tf.keras.preprocessing.image.ImageDataGenerator(preprocessing_function=tf.keras.applications.resnet50.preprocess_input)"
      ],
      "execution_count": 30,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jLCxpu9gC8tl",
        "outputId": "87402aef-2fcd-4ffe-fe9c-0671704d5f7e",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "train_generator = train_datagen.flow_from_directory('/content/Transfer Learning Data/train',\n",
        "                                                    target_size = (224,224),\n",
        "                                                    color_mode = 'rgb',\n",
        "                                                    batch_size = 32,\n",
        "                                                    class_mode = 'categorical',\n",
        "                                                    shuffle = True)"
      ],
      "execution_count": 31,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 202 images belonging to 2 classes.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ThtFjs9GDf2t"
      },
      "source": [
        "model.compile(optimizer='Adam', loss='categorical_crossentropy', metrics=['accuracy'])"
      ],
      "execution_count": 32,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "owvshmnqDplE",
        "outputId": "7df2d2c7-2a79-4d33-c4dd-c1dd0a2c6f47",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "source": [
        "history = model.fit_generator(generator=train_generator,\n",
        "                              epochs = 10)"
      ],
      "execution_count": 33,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:2: UserWarning: `Model.fit_generator` is deprecated and will be removed in a future version. Please use `Model.fit`, which supports generators.\n",
            "  \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/10\n",
            "7/7 [==============================] - 9s 315ms/step - loss: 1.1911 - accuracy: 0.6683\n",
            "Epoch 2/10\n",
            "7/7 [==============================] - 2s 214ms/step - loss: 0.0793 - accuracy: 0.9802\n",
            "Epoch 3/10\n",
            "7/7 [==============================] - 2s 236ms/step - loss: 0.0537 - accuracy: 0.9901\n",
            "Epoch 4/10\n",
            "7/7 [==============================] - 2s 214ms/step - loss: 0.0037 - accuracy: 1.0000\n",
            "Epoch 5/10\n",
            "7/7 [==============================] - 2s 234ms/step - loss: 0.0434 - accuracy: 0.9851\n",
            "Epoch 6/10\n",
            "7/7 [==============================] - 2s 214ms/step - loss: 0.0508 - accuracy: 0.9901\n",
            "Epoch 7/10\n",
            "7/7 [==============================] - 2s 207ms/step - loss: 0.0173 - accuracy: 0.9950\n",
            "Epoch 8/10\n",
            "7/7 [==============================] - 2s 213ms/step - loss: 1.2730e-04 - accuracy: 1.0000\n",
            "Epoch 9/10\n",
            "7/7 [==============================] - 2s 214ms/step - loss: 0.0031 - accuracy: 1.0000\n",
            "Epoch 10/10\n",
            "7/7 [==============================] - 2s 234ms/step - loss: 1.5261e-06 - accuracy: 1.0000\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "0wR3uKW8g5po"
      },
      "source": [
        "# Etapa 5: Avaliação do modelo"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "hW_BIEqpHXPk",
        "outputId": "4f2dde75-511b-43f3-fa3a-6e0623605a0f",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 559
        }
      },
      "source": [
        "acc = history.history['accuracy']\n",
        "loss = history.history['loss']\n",
        "\n",
        "plt.figure()\n",
        "plt.plot(acc, label='Training Accuracy')\n",
        "plt.ylabel('Accuracy')\n",
        "plt.title('Training Accuracy')\n",
        "\n",
        "plt.figure()\n",
        "\n",
        "plt.plot(loss, label='Training Loss')\n",
        "plt.ylabel('Loss')\n",
        "plt.title('Training Loss')\n",
        "plt.xlabel('epoch')\n",
        "plt.show()"
      ],
      "execution_count": 34,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEWCAYAAABrDZDcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nO3de5Qc513m8e/Tc9XMdEsaaSS1bpZky1aPTUKCsJ0NLIbAWdsLNrvc4k1M4CR42SWBbLJAwrJONiwHFlgWOOtATMiNhBgTAkeAg3NCgk2W2LEcJ451cSwk2xpZssa6z4zm/ts/uiS3xjPSSJqamu56PufMma6qt7t/3dL00/W+VW8pIjAzs/wqZF2AmZlly0FgZpZzDgIzs5xzEJiZ5ZyDwMws5xwEZmY55yCwXJP0OUlvmeu2ZvVEPo/A6o2kgZrFDmAEmEiW/2NEfGr+q7p0km4CPhkRa7OuxfKpOesCzC5WRHSduS3pWeBtEfGFqe0kNUfE+HzWZlaP3DVkDUPSTZL6JP2ypEPARyUtlfS3kvolHUtur625zz9Kelty+6ckfVnS7yRt90m65RLbbpT0sKRTkr4g6R5Jn7yE11RJnve4pB2SbqvZdquknclzHJD0X5P1y5PXeVzSUUn/JMl/6zYj/+ewRrMK6AauAO6i+n/8o8nyeuA08H/Pc/8bgKeB5cBvAX8iSZfQ9s+ArwLLgPcDd17sC5HUAvwN8HlgBfAO4FOSrkma/AnVrrAicB3wxWT9u4E+oAdYCfwK4D5gm5GDwBrNJPC+iBiJiNMRcSQi/jIihiLiFPDrwPec5/7PRcQfR8QE8HGgTPXDdNZtJa0HvhO4OyJGI+LLwLZLeC03Al3AbyaP80Xgb4E7ku1jQK+kUkQci4iv1awvA1dExFhE/FN4MNDOw0FgjaY/IobPLEjqkPQhSc9JOgk8DCyR1DTD/Q+duRERQ8nNrotsuxo4WrMOYP9Fvg6Sx9kfEZM1654D1iS3fwS4FXhO0kOSXpes/21gD/B5SXslvecSnttyxEFgjWbqN993A9cAN0RECfjXyfqZunvmwkGgW1JHzbp1l/A4LwDrpvTvrwcOAETEYxFxO9Vuo78G7k/Wn4qId0fEJuA24F2S3nAJz2854SCwRlekOi5wXFI38L60nzAingO2A++X1Jp8U/+hC91PUnvtD9UxhiHglyS1JIeZ/hBwX/K4b5K0OCLGgJNUu8WQ9IOSrkrGK05QPbR2ctonNcNBYI3v94BFwEvAI8Dfz9Pzvgl4HXAE+J/An1M932Ema6gGVu3POqof/LdQrf+DwE9GxO7kPncCzyZdXj+bPCfAZuALwADwFeCDEfGlOXtl1nB8QpnZPJD058DuiEh9j8TsYnmPwCwFkr5T0pWSCpJuBm6n2o9vtuD4zGKzdKwCPkv1PII+4D9FxBPZlmQ2PXcNmZnlnLuGzMxyru66hpYvXx4bNmzIugwzs7ry+OOPvxQRPdNtq7sg2LBhA9u3b8+6DDOzuiLpuZm2uWvIzCznHARmZjnnIDAzyzkHgZlZzqUWBJI+IumwpKdm2P4mSU9K+qakf5b06rRqMTOzmaW5R/Ax4ObzbN8HfE9EfBvwa8C9KdZiZmYzSO3w0Yh4WNKG82z/55rFR4C1M7U1M7P0LJQxgrcCn5tpo6S7JG2XtL2/v/+SnuDpQ6f4jQd2MTAyfqk1mpk1pMyDQNL3Ug2CX56pTUTcGxFbI2JrT8+0J8Zd0P6jQ3zo4b08fejkJVZqZtaYMg0CSa8CPgzcHhFH0nyuyuoSADsPnkrzaczM6k5mQSBpPdVpeu+MiG+l/XyrF7dTam9m10HvEZiZ1UptsFjSp4GbgOWS+qheK7YFICL+CLib6lztH6xeWpXxiNiaYj1UyiUHgZnZFGkeNXTHBba/DXhbWs8/nUq5xP3b9zM5GRQKms+nNjNbsDIfLJ5PveUSQ6MTPHd0KOtSzMwWjFwFQaVcHTDe7e4hM7OzchUEm1d20VSQxwnMzGrkKgjaW5rYtLzTh5CamdXIVRAAPnLIzGyKXAbBgeOnOXF6LOtSzMwWhNwFwZZyEfCAsZnZGbkLgt7kyCF3D5mZVeUuCFYU2+jubGWXB4zNzIAcBkF1qokiuzwLqZkZkMMgAKisKvH0oVOMT0xmXYqZWebyGQTlEiPjkzx7ZDDrUszMMpfbIABfm8DMDHIaBFet6KKlyVNNmJlBToOgtbnAlT1dPpfAzIycBgFUzyfwIaRmZjkOgkq5xKGTwxwbHM26FDOzTOU6CMBnGJuZ5TgIqnMO7XQQmFnO5TYIlnW10VNs8ziBmeVeboMAfG0CMzPIfRAU2XN4gDFPNWFmOZbrIOgtlxidmORf+geyLsXMLDO5DgIfOWRmlmIQSPqIpMOSnpphuyT9gaQ9kp6U9Nq0apnJpuWdtDYXPGBsZrmW5h7Bx4Cbz7P9FmBz8nMX8Icp1jKt5qYCV6/s8h6BmeVaakEQEQ8DR8/T5HbgE1H1CLBEUjmtemZSWeUjh8ws37IcI1gD7K9Z7kvWvYKkuyRtl7S9v79/TouolEu8NDDK4VPDc/q4Zmb1oi4GiyPi3ojYGhFbe3p65vSxzwwY7/Y4gZnlVJZBcABYV7O8Nlk3r3p95JCZ5VyWQbAN+Mnk6KEbgRMRcXC+i1jc0cLqxe0OAjPLrea0HljSp4GbgOWS+oD3AS0AEfFHwAPArcAeYAj46bRquZCKr01gZjmWWhBExB0X2B7Az6X1/BdjS7nIQ9/qZ2R8grbmpqzLMTObV3UxWJy2SrnE+GTwzIueasLM8sdBgKeaMLN8cxAAG5Z10t7iqSbMLJ8cBEBTQVzjM4zNLKccBInecpFdh05SHcM2M8sPB0GiUi5xfGiMQyc91YSZ5YuDIOEBYzPLKwdBYsuqIoAHjM0sdxwEiWJ7C+u6F3mPwMxyx0FQw9cmMLM8chDUqJRL7HtpkOGxiaxLMTObNw6CGpVyicmApw95nMDM8sNBUKNSPjNg7O4hM8sPB0GNdUs76GxtchCYWa44CGoUCmKLr01gZjnjIJii4qkmzCxnHARTVMolTg2P03fsdNalmJnNCwfBFJ5qwszyxkEwxZZVRSRPNWFm+eEgmKKjtZkNyzq9R2BmueEgmMaZAWMzszxwEEyjsqrEc0eGGBwZz7oUM7PUOQimcWbAeLenmjCzHHAQTKOy2kcOmVl+pBoEkm6W9LSkPZLeM8329ZK+JOkJSU9KujXNemZr9eJ2Su3NDgIzy4XUgkBSE3APcAvQC9whqXdKs18F7o+I1wBvBD6YVj0XQzoz1YSDwMwaX5p7BNcDeyJib0SMAvcBt09pE0Apub0YeCHFei5Kb7nE7kOnmJz0VBNm1tjSDII1wP6a5b5kXa33A2+W1Ac8ALxjugeSdJek7ZK29/f3p1HrK1TKRYZGJ3j+6NC8PJ+ZWVayHiy+A/hYRKwFbgX+VNIraoqIeyNia0Rs7enpmZfCPNWEmeVFmkFwAFhXs7w2WVfrrcD9ABHxFaAdWJ5iTbN29coiBTkIzKzxpRkEjwGbJW2U1Ep1MHjblDbPA28AkFShGgTz0/dzAe0tTWzq6WKn5xwyswaXWhBExDjwduBBYBfVo4N2SPqApNuSZu8GfkbSN4BPAz8VC+hCABUfOWRmOdCc5oNHxANUB4Fr191dc3sn8Po0a7gclXKRv/nGC5w4PcbiRS1Zl2NmloqsB4sXtLNTTXivwMwamIPgPHo955CZ5YCD4DxWFNvo7mz1OIGZNTQHwXlIql6bwEFgZg3MQXABW1aVePrFU0x4qgkza1AOgguolEsMj02y76XBrEsxM0uFg+ACKuUi4DOMzaxxOQgu4KoVXTQX5CAws4blILiAtuYmrlrR5SAws4blIJiF6lQTPpfAzBqTg2AWKuUih04Oc2xwNOtSzMzmnINgFnxtAjNrZA6CWTgTBDsdBGbWgBwEs7C8q42eYpvHCcysITkIZqlSLrH7kPcIzKzxOAhmqVIu8syLA4xNTGZdipnZnHIQzFJvucToxCR7+z3VhJk1FgfBLG1Z5SOHzKwxOQhmaVNPJ61NBQeBmTUcB8EstTQV2Lyyy4eQmlnDmVUQSOqUVEhuXy3pNkm5u5q7p5ows0Y02z2Ch4F2SWuAzwN3Ah9Lq6iFqlIu8dLACP2nRrIuxcxszsw2CBQRQ8C/Bz4YET8GXJteWQuTr01gZo1o1kEg6XXAm4C/S9Y1pVPSwtXrOYfMrAHNNgjeCbwX+KuI2CFpE/ClC91J0s2Snpa0R9J7Zmjz45J2Stoh6c9mX/r8W9LRSnlxu4PAzBpK82waRcRDwEMAyaDxSxHx8+e7j6Qm4B7gB4A+4DFJ2yJiZ02bzVQD5vURcUzSikt7GfPHA8Zm1mhme9TQn0kqSeoEngJ2SvrFC9ztemBPROyNiFHgPuD2KW1+BrgnIo4BRMThiyt//lXKRf6lf4CR8YmsSzEzmxOz7RrqjYiTwA8DnwM2Uj1y6HzWAPtrlvuSdbWuBq6W9P8kPSLp5ukeSNJdkrZL2t7f3z/LktNRKZcYnwz2HB7ItA4zs7ky2yBoSc4b+GFgW0SMATEHz98MbAZuAu4A/ljSkqmNIuLeiNgaEVt7enrm4Gkv3csXqXH3kJk1htkGwYeAZ4FO4GFJVwAXGjE9AKyrWV6brKvVRxIsEbEP+BbVYFiwNizrpL3FU02YWeOYVRBExB9ExJqIuDWqngO+9wJ3ewzYLGmjpFbgjcC2KW3+mureAJKWU+0q2nsxL2C+NRXENSuLDgIzaxizHSxeLOl3z/TTS/rfVPcOZhQR48DbgQeBXcD9yaGnH5B0W9LsQeCIpJ1UD0f9xYg4csmvZp5Ujxw6ScRc9I6ZmWVrtl1DHwFOAT+e/JwEPnqhO0XEAxFxdURcGRG/nqy7OyK2JbcjIt4VEb0R8W0Rcd+lvYz5VSmXODY0xosnPdWEmdW/WZ1HAFwZET9Ss/w/JH09jYLqQaXmDONVi9szrsbM7PLMdo/gtKTvOrMg6fXA6XRKWvi2JHMOeUpqM2sEs90j+FngE5IWJ8vHgLekU9LCV2pvYe3SRR4wNrOGMNspJr4BvFpSKVk+KemdwJNpFreQnRkwNjOrdxd1hbKIOJmcYQzwrhTqqRuVcol9Lw0yPOapJsysvl3OpSo1Z1XUod5ykcmApw/5DGMzq2+XEwS5Poi+4msTmFmDOO8YgaRTTP+BL2BRKhXViXVLO+hsbWK39wjMrM6dNwgiojhfhdSbQkFsKZd8CKmZ1b3L6RrKvS2rip5qwszqnoPgMlTKJU4Nj3PgeG7PrTOzBuAguAy+NoGZNQIHwWXYsqqI5COHzKy+OQguQ2dbM1d0dzgIzKyuOQguk6eaMLN65yC4TJVyieeODjE4Mp51KWZml8RBcJkq5RIR+MQyM6tbDoLLVEmuTeDuITOrVw6Cy7RmySJK7c0OAjOrWw6CyyRVp5pwEJhZvXIQzIHecondh04xOempJsys/jgI5kClXGRodIL9x4ayLsXM7KI5CObAllW+NoGZ1S8HwRy4ZlWRgmCn5xwyszqUahBIulnS05L2SHrPedr9iKSQtDXNetLS3tLExuWd3iMws7qUWhBIagLuAW4BeoE7JPVO064I/ALwaFq1zAdPNWFm9SrNPYLrgT0RsTciRoH7gNunafdrwP8ChlOsJXWVcom+Y6c5OTyWdSlmZhclzSBYA+yvWe5L1p0l6bXAuoj4uxTrmBe9ybUJdnucwMzqTGaDxZIKwO8C755F27skbZe0vb+/P/3iLsHLF6lx95CZ1Zc0g+AAsK5meW2y7owicB3wj5KeBW4Etk03YBwR90bE1ojY2tPTk2LJl25lqY2lHS0OAjOrO2kGwWPAZkkbJbUCbwS2ndkYESciYnlEbIiIDcAjwG0RsT3FmlIjyQPGZlaXUguCiBgH3g48COwC7o+IHZI+IOm2tJ43S5VyiadfPMWEp5owszrSnOaDR8QDwANT1t09Q9ub0qxlPlTKJYbHJtn30iBXrejKuhwzs1nxmcVzyNcmMLN65CCYQ1et6KK5IHYfchCYWf1wEMyhtuYmruzpYpfPJTCzOuIgmGOVctFdQ2ZWVxwEc6xSLnHwxDDHh0azLsXMbFYcBHPszBnGO71XYGZ1wkEwx16easLjBGZWHxwEc6yn2MbyrjaPE5hZ3XAQpMADxmZWTxwEKegtl3jmxQHGJiazLsXM7IIcBCmolEuMTkyyt38w61LMzC7IQZACX5vAzOqJgyAFm3o6aW0qOAjMrC44CFLQ0lRg88oun0tgZnXBQZCSLatK7D7kcwnMbOFzEKSkUi7Sf2qElwZGsi7FzOy8HAQp6fWAsZnVCQdBSnzkkJnVCwdBSpZ2trKq1O45h8xswXMQpMhTTZhZPXAQpKhSLrHn8AAj4xNZl2JmNiMHQYoq5RLjk8GewwNZl2JmNiMHQYp8bQIzqwcOghRtXN5Je4unmjCzhc1BkKKmgrhmpQeMzWxhSzUIJN0s6WlJeyS9Z5rt75K0U9KTkv5B0hVp1pOFSrnEroMniYisSzEzm1ZqQSCpCbgHuAXoBe6Q1Dul2RPA1oh4FfAZ4LfSqicrlXKJY0NjvHjSU02Y2cKU5h7B9cCeiNgbEaPAfcDttQ0i4ksRMZQsPgKsTbGeTGxZVQRg1yF3D5nZwpRmEKwB9tcs9yXrZvJW4HPTbZB0l6Ttkrb39/fPYYnp2+KpJsxsgVsQg8WS3gxsBX57uu0RcW9EbI2IrT09PfNb3GVavKiFNUsW+RBSM1uwmlN87APAuprltcm6c0j6fuC/Ad8TEQ3ZkX5mwNjMbCFKc4/gMWCzpI2SWoE3AttqG0h6DfAh4LaIOJxiLZnqLRfZ2z/A8JinmjCzhSe1IIiIceDtwIPALuD+iNgh6QOSbkua/TbQBfyFpK9L2jbDw9W1SrnEZMC3XnT3kJktPGl2DRERDwAPTFl3d83t70/z+ReK2msTvGrtkoyrMTM714IYLG5067s76Gxt8oCxmS1IDoJ5UCiIa1YV2ekBYzNbgBwE88RTTZjZQuUgmCeVcolTw+McOH4661LMzM7hIJgnvjaBmS1UDoJ5cnbOIY8TmNkC4yCYJ51tzVyxrIPdnnzOzBYYB8E8qqwquWvIzBYcB8E8qpRLPHtkkKHR8axLMTM7y0EwjyrlIhGw+5D3Csxs4XAQzKOKr01gZguQg2AerV26iGJ7s4PAzBYUB8E8kuQBYzNbcFKdfdReqXd1iY9/5Vm+73f+kTVLF7F2aQdrly5KfjpY172Inq42JGVdqpnlhINgnr31uzbS1lyg79hp+o4N8fkXDnFkcPScNm3NhelDIvm9vKvVQWFmc8ZBMM/WdXfw3lsr56wbHKnOQdR3bCgJiOrt/UdP882+4xwbGjunfVtz4Ww4rF26iHXdHecsL+t0UJjZ7DkIFoDOtmauXlnk6pXFabcPjIxz4NjLQbH/aBIYx4f4Rt9xjk8JivaWwjl7EGun7F10OyjMrIaDoA50tTVzzaoi16yaPihODY9V9yiOnmb/2b2K6u+vPX+cE6fPDYqO1ibWLl3E5hVFrt/YzfUbu7lmZZFCweEwH8YnJjk9NsHw2CTDYxPJT3XdxGSwflkHqxe3O6xt3jgIGkCxvYUtq1rYsqo07faTw2P0HT2362n/sSGeeP4Yf/fNgwAs6WjhOzd0c8PGbm7ctIxKuURTjoJhfGKSwdEJRmo+lIfHJs7+rv3QPl3TZmSadcNjE4y84jEmGUluj09e+JoUna1NXLWii80ri2xe0cXmlV1sXlFkzZJFDmybc6q3C6Vs3bo1tm/fnnUZDWP/0SEe3XeUR/ce4dF9R3n+6BAAxbZmtm5Yyg2blnHDxm6uW7OYlqbGONp4cGScXQdP8tSBEzz1QvX3nsMDs/qAnqqtuUB7SxOLWppob6nebk9uLzp7e7p11dttyfKZ+xcknj0yyDMvDvDM4VM88+IAh0+NnH2+9pZCNSBWFM+Gw+YVXazr7shVcNvFk/R4RGyddpuDwGodPHGar+47yiN7j/LoviPs7R8Eqt1J33HFUm7Y2M0Nm5bxqrWLaWtuyrjaCzs+NMqOF06y44UTPHXgJE+9cIJ9Lw1y5r/9ss5WrluzmN7VJZZ1ttZ8KDexqLVAe3P1w7r2g/7M9rbmwrx8Oz8xNMae/lNJOCQ/L57i4Inhs21amwtc2dNV3Xs4syexsosrujtobpAAt8vjILBLdvjUMI/tO8aj+47w6N6jPP1i9WS4tuYCr12/lBs2dXPDxmW8Zv0S2luyDYbDp4bZceDcD/2+Yy9fEW714nauXbOY61Yv5ro1Ja5dvZiVpfo9Z+PU8Bh7kmDYk4TDM4cHznnNLU1i0/Iurlp5JiSKXL2yiyuWddLa7IDIEweBzZmjg6N8dV91b+Gr+46y8+BJIqC1qcCr1y3mho3LuGFTN69dv5TOtnSGoCKCA8dP81Tyob8j6d6p7ULZuLyT3tWlcz70uztbU6lnoRkcGedf+gfO7kHsOVwNiOePDp3dE2ouiA3LO8/uQVyVjEVs6umsiz09u3gOAkvNidNjbH/2aHWcYd9RnjpwgonJoLkgrluzmBs2dXPjxmVs3bCUYnvLRT/+5GTw7JFBnnrhJDsOJB/6L5w4e8hsQbB5RZFrV5eSb/sleleXLum5Gt3w2ERNQFS7mvYcHuDZI4OcGR4pCDYs62Tj8k56im10d7ayrKuNZZ2tLOtqpbuzleVdbSztaPUeRZ3JLAgk3Qz8PtAEfDgifnPK9jbgE8B3AEeAn4iIZ8/3mA6ChW1gZJzHnzt2dvD5yb7jjE0EBcG1qxdz/cbqkUnXb+xmSce539DHJybZ0z9Q7dY5cIIdL5xg5wsnGRydAKp7HdesKnLdmhK9q6sf+ltWlVjU6m+wl2N4bOLlAeqke+nZI0McGRjh6ODojIPopfbmKSHRxvIkLKaGR3dHq8cqMpZJEEhqAr4F/ADQBzwG3BERO2va/GfgVRHxs5LeCPy7iPiJ8z2ug6C+nB6d4Innj/FIcmTSE/uPMzo+iQTXrCxyw8ZuxiaDHQdOsOvQKUbHJwFY1NKUdO1Uv+lfu7rE5hVFfwudZxHBydPjvDRYDYUjAyMcGRzlyMC5t48OjnIkaTPTwVdLOlqq4dDZxrKuacLjzPrOVpZ0tF7UUVCTk8H4ZDAxGYxPTjI5CeOTk8lydf3EBdqc+xi195lEEs0FUUh+NzUlvwuiuVBIfifLZ7cVatqIQmH6+8zX4cBZBcHrgPdHxL9Jlt8LEBG/UdPmwaTNVyQ1A4eAnjhPUQ6C+jY8NsGTfSfO7jE8/twxWprEtUlf/nVrFnPt6sVsXN7pwyHr0ORkcPz02JSQGOGlmrA4e3tghOOnx5jur70gWNrRSmdb85QP8clpP7TrmcTMoZKETpOqy3dcv563ffemS3yemYMgzRPK1gD7a5b7gBtmahMR45JOAMuAl2obSboLuAtg/fr1adVr86C9pens2czvACYmq91G9Xrkjp2rUFC1K6izlc2zaD8+McmxobEpexvJ78FRhkbGX/5m3TTDt3Il376bar59SzMsF87zGC+3qV0uJP83J6bsJUy8Yg9ikvGJl5cnI85ZPhNi59xvIpiImm0T0zxmzXJPsS2Vf7e6OLM4Iu4F7oXqHkHG5dgc8rf+fGtuKtBTbEs+4KafQsXSl2aH6wFgXc3y2mTdtG2SrqHFVAeNzcxsnqQZBI8BmyVtlNQKvBHYNqXNNuAtye0fBb54vvEBMzObe6l1DSV9/m8HHqR6+OhHImKHpA8A2yNiG/AnwJ9K2gMcpRoWZmY2j1IdI4iIB4AHpqy7u+b2MPBjadZgZmbn54OyzcxyzkFgZpZzDgIzs5xzEJiZ5VzdzT4qqR947hLvvpwpZy3nnN+Pc/n9eJnfi3M1wvtxRUT0TLeh7oLgckjaPtNcG3nk9+Ncfj9e5vfiXI3+frhryMws5xwEZmY5l7cguDfrAhYYvx/n8vvxMr8X52ro9yNXYwRmZvZKedsjMDOzKRwEZmY5l5sgkHSzpKcl7ZH0nqzryZKkdZK+JGmnpB2SfiHrmrImqUnSE5L+NutasiZpiaTPSNotaVdy2dlckvRfkr+RpyR9WlJ71jWlIRdBIKkJuAe4BegF7pDUm21VmRoH3h0RvcCNwM/l/P0A+AVgV9ZFLBC/D/x9RGwBXk1O3xdJa4CfB7ZGxHVUp9NvyKnycxEEwPXAnojYGxGjwH3A7RnXlJmIOBgRX0tun6L6h74m26qyI2kt8G+BD2ddS9YkLQb+NdVrhRARoxFxPNuqMtUMLEquoNgBvJBxPanISxCsAfbXLPeR4w++WpI2AK8BHs22kkz9HvBLwGTWhSwAG4F+4KNJV9mHJXVmXVQWIuIA8DvA88BB4EREfD7bqtKRlyCwaUjqAv4SeGdEnMy6nixI+kHgcEQ8nnUtC0Qz8FrgDyPiNcAgkMsxNUlLqfYcbARWA52S3pxtVenISxAcANbVLK9N1uWWpBaqIfCpiPhs1vVk6PXAbZKepdpl+H2SPpltSZnqA/oi4swe4meoBkMefT+wLyL6I2IM+CzwrzKuKRV5CYLHgM2SNkpqpTrgsy3jmjIjSVT7gHdFxO9mXU+WIuK9EbE2IjZQ/X/xxYhoyG99sxERh4D9kq5JVr0B2JlhSVl6HrhRUkfyN/MGGnTgPNVrFi8UETEu6e3Ag1RH/j8SETsyLitLrwfuBL4p6evJul9JrjFt9g7gU8mXpr3AT2dcTyYi4lFJnwG+RvVIuydo0KkmPMWEmVnO5aVryMzMZuAgMDPLOQeBmVnOOQjMzHLOQWBmlnMOArN5JOkmz3BqC42DwMws5xwEZtOQ9GZJX5X0dUkfSq5XMCDp/yTz0/+DpJ6k7bdLekTSk5L+KpmjBklXSfqCpG9I+pqkK5OH76qZ7/9TyVmrZplxEJhNIakC/ATw+oj4dmACeBPQCWyPiGuBh4D3JXf5BPDLEfEq4Js16z8F3BMRr6Y6R83BZP1rgHdSvTbGJqpneptlJhdTTJhdpDcA3wE8lnxZXwQcpjpN9Z8nbT4JfDaZv39JRDyUrNpkRdEAAADrSURBVP848BeSisCaiPgrgIgYBkge76sR0Zcsfx3YAHw5/ZdlNj0HgdkrCfh4RLz3nJXSf5/S7lLnZxmpuT2B/w4tY+4aMnulfwB+VNIKAEndkq6g+vfyo0mb/wB8OSJOAMckfXey/k7goeTKb32Sfjh5jDZJHfP6Ksxmyd9EzKaIiJ2SfhX4vKQCMAb8HNWLtFyfbDtMdRwB4C3AHyUf9LWzdd4JfEjSB5LH+LF5fBlms+bZR81mSdJARHRlXYfZXHPXkJlZznmPwMws57xHYGaWcw4CM7OccxCYmeWcg8DMLOccBGZmOff/AW30PysGTiv2AAAAAElFTkSuQmCC\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "GLuEtef-E3Y_"
      },
      "source": [
        "sample_image = tf.keras.preprocessing.image.load_img(r'/content/Transfer Learning Data/dog.309.jpg', target_size=(224,224))"
      ],
      "execution_count": 35,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5Ix965CtFTWT",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 286
        },
        "outputId": "e60ed8ee-502e-4a3c-e57b-2d7f5ea7be9e"
      },
      "source": [
        "plt.imshow(sample_image)"
      ],
      "execution_count": 36,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.image.AxesImage at 0x7f1c49e99f10>"
            ]
          },
          "metadata": {},
          "execution_count": 36
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4OWysMKCFXWt",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "308ac809-0005-4570-edb0-496130fe61a1"
      },
      "source": [
        "sample_image = tf.keras.preprocessing.image.img_to_array(sample_image)\n",
        "np.shape(sample_image)"
      ],
      "execution_count": 37,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(224, 224, 3)"
            ]
          },
          "metadata": {},
          "execution_count": 37
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "SkWlYMYBFhLT",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "d3ccfa70-9b8b-4b22-d4be-dc685fd7ea4f"
      },
      "source": [
        "sample_image = np.expand_dims(sample_image, axis = 0)\n",
        "np.shape(sample_image)"
      ],
      "execution_count": 38,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1, 224, 224, 3)"
            ]
          },
          "metadata": {},
          "execution_count": 38
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "kOokcU3pFpEo"
      },
      "source": [
        "sample_image = tf.keras.applications.resnet50.preprocess_input(sample_image)"
      ],
      "execution_count": 39,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-i-9cHmcFv2q",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "c2285232-4dd3-46c9-cd6a-6a2241d80c54"
      },
      "source": [
        "predictions = model.predict(sample_image)\n",
        "print(predictions)"
      ],
      "execution_count": 40,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[[3.452586e-09 1.000000e+00]]\n"
          ]
        }
      ]
    }
  ]
}