ML_5.2.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Untitled0.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyMRRd1oshM6GQlYWvzWbJf0",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/OneOneFour/TropicalCyclonesMSci/blob/master/ML_5.2.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "WaN4eKnbV0s1",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "from __future__ import print_function\n",
        "import tensorflow.keras\n",
        "from tensorflow.keras.datasets import cifar10\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "from tensorflow.keras.models import Sequential, load_model\n",
        "from tensorflow.keras.layers import Dense, Dropout, Activation, Flatten\n",
        "from tensorflow.keras.layers import Conv2D, MaxPooling2D\n",
        "from tensorflow.python.keras.optimizers import RMSprop\n",
        "from tensorflow.compat.v1 import disable_eager_execution\n",
        "\n",
        "import os\n",
        "\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ZkhBbrCMWFZq",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "batch_size = 32\n",
        "num_classes = 10\n",
        "epochs = 100\n",
        "data_augmentation = True\n",
        "num_predictions = 20\n",
        "save_dir = os.path.join(os.getcwd(), 'saved_models')\n",
        "model_name = 'keras_cifar10_trained_model.h5'"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "UGvN6A7mWQlC",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 101
        },
        "outputId": "e528ce79-2b90-45f4-d23c-855060168aaf"
      },
      "source": [
        "(x_train, y_train), (x_test, y_test) = cifar10.load_data()\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",
        "# Convert class vectors to binary class matrices.\n",
        "y_train = tensorflow.keras.utils.to_categorical(y_train, num_classes)\n",
        "y_test = tensorflow.keras.utils.to_categorical(y_test, num_classes)"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Downloading data from https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz\n",
            "170500096/170498071 [==============================] - 12s 0us/step\n",
            "x_train shape: (50000, 32, 32, 3)\n",
            "50000 train samples\n",
            "10000 test samples\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "fm3K8dbHWSaz",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 283
        },
        "outputId": "6b2c66e0-4e4d-4544-af97-b1c00aaa231f"
      },
      "source": [
        "plt.imshow(x_train[40],interpolation='nearest')\n",
        "y_train[40]"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([0., 0., 0., 0., 0., 1., 0., 0., 0., 0.], dtype=float32)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 4
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": [],
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pZ3O8cV-WYKw",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 87
        },
        "outputId": "0dc6805a-6c79-4729-cd34-3d0f08ad4973"
      },
      "source": [
        "disable_eager_execution() # this had to be added to avoid error message\n",
        "\n",
        "model = Sequential()\n",
        "model.add(Conv2D(32, (3, 3), padding='same',\n",
        "                 input_shape=x_train.shape[1:]))\n",
        "model.add(Activation('relu'))\n",
        "model.add(Conv2D(32, (3, 3)))\n",
        "model.add(Activation('relu'))\n",
        "model.add(MaxPooling2D(pool_size=(2, 2)))\n",
        "model.add(Dropout(0.25))\n",
        "\n",
        "model.add(Conv2D(64, (3, 3), padding='same'))\n",
        "model.add(Activation('relu'))\n",
        "model.add(Conv2D(64, (3, 3)))\n",
        "model.add(Activation('relu'))\n",
        "model.add(MaxPooling2D(pool_size=(2, 2)))\n",
        "model.add(Dropout(0.25))\n",
        "\n",
        "model.add(Flatten())\n",
        "model.add(Dense(512))\n",
        "model.add(Activation('relu'))\n",
        "model.add(Dropout(0.5))\n",
        "model.add(Dense(num_classes))\n",
        "model.add(Activation('softmax'))\n",
        "\n",
        "# initiate RMSprop optimizer\n",
        "opt = RMSprop(lr=0.0001, decay=1e-6)\n",
        "\n",
        "# Let's train the model using RMSprop\n",
        "model.compile(loss='categorical_crossentropy',\n",
        "              optimizer=opt,\n",
        "              metrics=['accuracy'])\n",
        "\n",
        "x_train = x_train.astype('float32')\n",
        "x_test = x_test.astype('float32')\n",
        "x_train /= 255\n",
        "x_test /= 255"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/resource_variable_ops.py:1666: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.\n",
            "Instructions for updating:\n",
            "If using Keras pass *_constraint arguments to layers.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "yaLNtlodWayM",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "filepath = 'keras_cifar_10_trained_model.h5'\n",
        "load_model(filepath, custom_objects=None, compile=True)"
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}