Merge pull request pranjay-poddar#3562 from karthikbhandary2/food

Added the food detector script

Author: TusharKesarwani

ML Projects/Food-Vision/09_pretrained_effnetb2_feature_extractor_food101_20_percent.pth

@@ -0,0 +1,6 @@
+# Food-Vision
+This is project that is done as a part of PyTorch for deep learning by ZTM. This is a more advanced version of the Food-Vision-Mini. In this I used all of the data that is all types of food available on the dataset is used. I used `EfficientNetV2` as my model which was taken from the pytorch models through `transfer learning`.
+
+I deployed the project on to `Hugging Face🤗` using `Gradio`.
+
+Here is the link: https://huggingface.co/spaces/karthik2/foodvision_big

ML Projects/Food-Vision/README.md

@@ -0,0 +1,70 @@
+### 1. Imports and class names setup ###
+import gradio as gr
+import os
+import torch
+
+from model import create_effnetb2_model
+from timeit import default_timer as timer
+from typing import Tuple, Dict
+
+# Setup class names
+with open("class_names.txt", "r") as f:
+  class_names = [food_name.strip() for food_name in f.readlines()]
+
+### 2. Model and transforms preparation ### 
+# Create model and transforms
+effnetb2, effnetb2_transforms = create_effnetb2_model(num_classes=101)
+
+# Load saved weights
+effnetb2.load_state_dict(
+    torch.load(f="09_pretrained_effnetb2_feature_extractor_food101_20_percent.pth",
+               map_location=torch.device("cpu")) # load to CPU
+)
+
+### 3. Predict function ###
+
+def predict(img) -> Tuple[Dict, float]:
+  # Start a timer
+  start_time = timer()
+
+  # Transform the input image for use with EffNetB2
+  img = effnetb2_transforms(img).unsqueeze(0) # unsqueeze = add batch dimension on 0th index
+
+  # Put model into eval mode, make prediction
+  effnetb2.eval()
+  with torch.inference_mode():
+    # Pass transformed image through the model and turn the prediction logits into probaiblities
+    pred_probs = torch.softmax(effnetb2(img), dim=1)
+
+  # Create a prediction label and prediction probability dictionary
+  pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}
+
+  # Calculate pred time
+  end_time = timer()
+  pred_time = round(end_time - start_time, 4)
+
+  # Return pred dict and pred time
+  return pred_labels_and_probs, pred_time
+
+### 4. Gradio app ###
+
+# Create title, description and article
+title = "FoodVision BIG 🍔👁💪"
+description = "An [EfficientNetB2 feature extractor](https://pytorch.org/vision/stable/models/generated/torchvision.models.efficientnet_b2.html#torchvision.models.efficientnet_b2) computer vision model to classify images [101 classes of food from the Food101 dataset](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/extras/food101_class_names.txt)."
+article = "Created at [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/#11-turning-our-foodvision-big-model-into-a-deployable-app)."
+
+# Create example list
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+# Create the Gradio demo
+demo = gr.Interface(fn=predict, # maps inputs to outputs
+                    inputs=gr.Image(type="pil"),
+                    outputs=[gr.Label(num_top_classes=5, label="Predictions"),
+                             gr.Number(label="Prediction time (s)")],
+                    examples=example_list,
+                    title=title,
+                    description=description,
+                    article=article)
+
+# Launch the demo!
+demo.launch() 

ML Projects/Food-Vision/app.py

@@ -0,0 +1,101 @@
+apple_pie
+baby_back_ribs
+baklava
+beef_carpaccio
+beef_tartare
+beet_salad
+beignets
+bibimbap
+bread_pudding
+breakfast_burrito
+bruschetta
+caesar_salad
+cannoli
+caprese_salad
+carrot_cake
+ceviche
+cheese_plate
+cheesecake
+chicken_curry
+chicken_quesadilla
+chicken_wings
+chocolate_cake
+chocolate_mousse
+churros
+clam_chowder
+club_sandwich
+crab_cakes
+creme_brulee
+croque_madame
+cup_cakes
+deviled_eggs
+donuts
+dumplings
+edamame
+eggs_benedict
+escargots
+falafel
+filet_mignon
+fish_and_chips
+foie_gras
+french_fries
+french_onion_soup
+french_toast
+fried_calamari
+fried_rice
+frozen_yogurt
+garlic_bread
+gnocchi
+greek_salad
+grilled_cheese_sandwich
+grilled_salmon
+guacamole
+gyoza
+hamburger
+hot_and_sour_soup
+hot_dog
+huevos_rancheros
+hummus
+ice_cream
+lasagna
+lobster_bisque
+lobster_roll_sandwich
+macaroni_and_cheese
+macarons
+miso_soup
+mussels
+nachos
+omelette
+onion_rings
+oysters
+pad_thai
+paella
+pancakes
+panna_cotta
+peking_duck
+pho
+pizza
+pork_chop
+poutine
+prime_rib
+pulled_pork_sandwich
+ramen
+ravioli
+red_velvet_cake
+risotto
+samosa
+sashimi
+scallops
+seaweed_salad
+shrimp_and_grits
+spaghetti_bolognese
+spaghetti_carbonara
+spring_rolls
+steak
+strawberry_shortcake
+sushi
+tacos
+takoyaki
+tiramisu
+tuna_tartare
+waffles

ML Projects/Food-Vision/class_names.txt

@@ -0,0 +1,24 @@
+import torch
+import torchvision
+
+from torch import nn
+
+def create_effnetb2_model(num_classes:int=3, # default output classes = 3 (pizza, steak, sushi)
+                          seed:int=42):
+  # 1, 2, 3 Create EffNetB2 pretrained weights, transforms and model
+  weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+  transforms = weights.transforms()
+  model = torchvision.models.efficientnet_b2(weights=weights)
+
+  # 4. Freeze all layers in the base model
+  for param in model.parameters():
+    param.requires_grad = False
+
+  # 5. Change classifier head with random seed for reproducibility
+  torch.manual_seed(seed)
+  model.classifier = nn.Sequential(
+      nn.Dropout(p=0.3, inplace=True),
+      nn.Linear(in_features=1408, out_features=num_classes)
+  )
+
+  return model, transforms

ML Projects/Food-Vision/examples/04-pizza-dad.jpeg

@@ -0,0 +1,3 @@
+torch==1.12.0
+torchvision==0.13.0
+gradio==3.1.4