MNIST_Android.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.8.2"
    },
    "colab": {
      "name": "MNIST-Android.ipynb",
      "provenance": [],
      "include_colab_link": true
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/FelosRG/MNIST-Android/blob/main/MNIST_Android.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "2JH6DeldnsAp"
      },
      "source": [
        "# MNIST KERAS"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Cqzir-FDnsAv",
        "outputId": "3708ce26-8c61-43a0-d250-5d0e272f1596"
      },
      "source": [
        "# REVISAMOS EL DISPOSITIVO EN EL QUE ESTAMOS TRABAJANDO\n",
        "\n",
        "from tensorflow.python.client import device_lib\n",
        "print(device_lib.list_local_devices())\n"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[name: \"/device:CPU:0\"\n",
            "device_type: \"CPU\"\n",
            "memory_limit: 268435456\n",
            "locality {\n",
            "}\n",
            "incarnation: 2726610591092874326\n",
            ", name: \"/device:XLA_CPU:0\"\n",
            "device_type: \"XLA_CPU\"\n",
            "memory_limit: 17179869184\n",
            "locality {\n",
            "}\n",
            "incarnation: 10041975974662050738\n",
            "physical_device_desc: \"device: XLA_CPU device\"\n",
            ", name: \"/device:XLA_GPU:0\"\n",
            "device_type: \"XLA_GPU\"\n",
            "memory_limit: 17179869184\n",
            "locality {\n",
            "}\n",
            "incarnation: 3570962965847598056\n",
            "physical_device_desc: \"device: XLA_GPU device\"\n",
            ", name: \"/device:GPU:0\"\n",
            "device_type: \"GPU\"\n",
            "memory_limit: 14640891840\n",
            "locality {\n",
            "  bus_id: 1\n",
            "  links {\n",
            "  }\n",
            "}\n",
            "incarnation: 12700630950342469278\n",
            "physical_device_desc: \"device: 0, name: Tesla T4, pci bus id: 0000:00:04.0, compute capability: 7.5\"\n",
            "]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Gk-TG594nsAx"
      },
      "source": [
        "# SETUP\n",
        "\n",
        "import numpy as np\n",
        "from tensorflow import keras\n",
        "from tensorflow.keras import layers\n",
        "import tensorflow as tf\n"
      ],
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jJQuP-f7nsAx",
        "outputId": "ed7c34a3-f1e7-4308-b10b-2287f815b579"
      },
      "source": [
        "# PREPARACIÓN DE DATOS\n",
        "\n",
        "num_classes = 10\n",
        "input_shape = (28, 28, 1)\n",
        "\n",
        "# Separamos entre los conjuntos de train y test\n",
        "(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()\n",
        "\n",
        "# Normalización\n",
        "x_train = x_train.astype(\"float32\") / 255\n",
        "x_test = x_test.astype(\"float32\") / 255\n",
        "\n",
        "# Convertimos los tesores a la forma adecuada.\n",
        "x_train = np.expand_dims(x_train, -1)\n",
        "x_test = np.expand_dims(x_test, -1)\n",
        "\n",
        "print(\"x_train shape:\", x_train.shape)\n",
        "print(x_train.shape[0], \"train samples\")\n",
        "print(x_test.shape[0], \"test samples\")\n",
        "\n",
        "\n",
        "# Pasamos los labels a one-hot econding \n",
        "y_train = keras.utils.to_categorical(y_train, num_classes)\n",
        "y_test = keras.utils.to_categorical(y_test, num_classes)"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz\n",
            "11493376/11490434 [==============================] - 0s 0us/step\n",
            "x_train shape: (60000, 28, 28, 1)\n",
            "60000 train samples\n",
            "10000 test samples\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-tddkKRInsAy",
        "outputId": "b6ac3c58-1fcd-409c-8486-5d414eec62e2"
      },
      "source": [
        "# MODELO\n",
        "\n",
        "model = keras.Sequential(\n",
        "    [\n",
        "        keras.Input(shape=input_shape),\n",
        "        layers.Conv2D(32, kernel_size=(3, 3), activation=\"relu\"),\n",
        "        layers.MaxPooling2D(pool_size=(2, 2)),\n",
        "        layers.Conv2D(64, kernel_size=(3, 3), activation=\"relu\"),\n",
        "        layers.MaxPooling2D(pool_size=(2, 2)),\n",
        "        layers.Flatten(),\n",
        "        layers.Dropout(0.5),\n",
        "        layers.Dense(num_classes, activation=\"softmax\"),\n",
        "    ]\n",
        ")\n",
        "\n",
        "model.summary()\n"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Model: \"sequential\"\n",
            "_________________________________________________________________\n",
            "Layer (type)                 Output Shape              Param #   \n",
            "=================================================================\n",
            "conv2d (Conv2D)              (None, 26, 26, 32)        320       \n",
            "_________________________________________________________________\n",
            "max_pooling2d (MaxPooling2D) (None, 13, 13, 32)        0         \n",
            "_________________________________________________________________\n",
            "conv2d_1 (Conv2D)            (None, 11, 11, 64)        18496     \n",
            "_________________________________________________________________\n",
            "max_pooling2d_1 (MaxPooling2 (None, 5, 5, 64)          0         \n",
            "_________________________________________________________________\n",
            "flatten (Flatten)            (None, 1600)              0         \n",
            "_________________________________________________________________\n",
            "dropout (Dropout)            (None, 1600)              0         \n",
            "_________________________________________________________________\n",
            "dense (Dense)                (None, 10)                16010     \n",
            "=================================================================\n",
            "Total params: 34,826\n",
            "Trainable params: 34,826\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "T_xqtaOPnsAy",
        "outputId": "80bcd381-5333-4b9b-dfde-715e9ee481ca"
      },
      "source": [
        "# ENTRENAMIENTO\n",
        "\n",
        "batch_size = 128\n",
        "epochs = 15\n",
        "\n",
        "model.compile(loss=\"categorical_crossentropy\", optimizer=\"adam\", metrics=[\"accuracy\"])\n",
        "\n",
        "model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.1)"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/15\n",
            "422/422 [==============================] - 2s 5ms/step - loss: 0.3643 - accuracy: 0.8892 - val_loss: 0.0829 - val_accuracy: 0.9785\n",
            "Epoch 2/15\n",
            "422/422 [==============================] - 2s 5ms/step - loss: 0.1144 - accuracy: 0.9656 - val_loss: 0.0626 - val_accuracy: 0.9828\n",
            "Epoch 3/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0865 - accuracy: 0.9737 - val_loss: 0.0466 - val_accuracy: 0.9858\n",
            "Epoch 4/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0725 - accuracy: 0.9775 - val_loss: 0.0422 - val_accuracy: 0.9878\n",
            "Epoch 5/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0632 - accuracy: 0.9804 - val_loss: 0.0376 - val_accuracy: 0.9902\n",
            "Epoch 6/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0556 - accuracy: 0.9827 - val_loss: 0.0363 - val_accuracy: 0.9898\n",
            "Epoch 7/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0520 - accuracy: 0.9840 - val_loss: 0.0365 - val_accuracy: 0.9905\n",
            "Epoch 8/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0475 - accuracy: 0.9854 - val_loss: 0.0327 - val_accuracy: 0.9903\n",
            "Epoch 9/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0451 - accuracy: 0.9860 - val_loss: 0.0325 - val_accuracy: 0.9910\n",
            "Epoch 10/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0408 - accuracy: 0.9872 - val_loss: 0.0339 - val_accuracy: 0.9912\n",
            "Epoch 11/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0393 - accuracy: 0.9873 - val_loss: 0.0299 - val_accuracy: 0.9922\n",
            "Epoch 12/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0389 - accuracy: 0.9878 - val_loss: 0.0290 - val_accuracy: 0.9922\n",
            "Epoch 13/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0344 - accuracy: 0.9888 - val_loss: 0.0299 - val_accuracy: 0.9908\n",
            "Epoch 14/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0356 - accuracy: 0.9885 - val_loss: 0.0302 - val_accuracy: 0.9917\n",
            "Epoch 15/15\n",
            "422/422 [==============================] - 2s 4ms/step - loss: 0.0327 - accuracy: 0.9896 - val_loss: 0.0299 - val_accuracy: 0.9927\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<tensorflow.python.keras.callbacks.History at 0x7fa19c577f98>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "scrolled": true,
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "m51eeUlFnsAz",
        "outputId": "86ad0573-be6d-4706-c3ca-581a2537633a"
      },
      "source": [
        "# EVALUACIÓN DEL MODELO\n",
        "\n",
        "score = model.evaluate(x_test, y_test, verbose=0)\n",
        "print(\"Test loss:\", score[0])\n",
        "print(\"Test accuracy:\", score[1])"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Test loss: 0.027707671746611595\n",
            "Test accuracy: 0.9901999831199646\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "O-lnWhFnnsAz",
        "outputId": "d8d0e89f-bdfe-4e0d-d143-662453839234"
      },
      "source": [
        "# Guardanos el modelo de tensorlfow\n",
        "name = \"/home/MNIST_andoid_model.HDF5\"\n",
        "model.save(name)"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:Assets written to: /home/MNIST_andoid_model.HDF5/assets\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:Assets written to: /home/MNIST_andoid_model.HDF5/assets\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-HYQ9LM2nsAz"
      },
      "source": [
        "# Convert the model\n",
        "\n",
        "converter = tf.lite.TFLiteConverter.from_saved_model(name) # path to the SavedModel directory\n",
        "tflite_model = converter.convert()\n",
        "\n",
        "# Save the model.\n",
        "with open('model.tflite', 'wb') as f:\n",
        "  f.write(tflite_model)"
      ],
      "execution_count": 11,
      "outputs": []
    }
  ]
}