rpsTutorial.ipynb

rpstutorial.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "rpsTutorial.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/gist/Bill-Park/bf4d086db213e1fae12005ccf6d77f74/rpstutorial.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pr6oPG81fP-v",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "%tensorflow_version 2.x\n",
        "import tensorflow as tf\n",
        "device_name = tf.test.gpu_device_name()\n",
        "if device_name != '/device:GPU:0':\n",
        "  raise SystemError('GPU device not found')\n",
        "print('Found GPU at: {}'.format(device_name))"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Ett5cpuARsIL",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "from tensorflow.keras.models import Sequential\n",
        "from tensorflow.keras.layers import Dense, Conv2D, Flatten, Dropout, MaxPooling2D\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "\n",
        "import os\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ZFvs98_ASBXt",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "!wget https://storage.googleapis.com/laurencemoroney-blog.appspot.com/rps.zip -O /tmp/rps.zip\n",
        "!unzip /tmp/rps.zip -d /tmp"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "PWSIEDYKSo8J",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "!wget https://storage.googleapis.com/laurencemoroney-blog.appspot.com/rps-test-set.zip -O /tmp/rps-test-set.zip\n",
        "!unzip /tmp/rps-test-set.zip -d /tmp"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3nx3lkVOSyDT",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "train_dir = os.path.join(\"/\", \"tmp\", \"rps\")\n",
        "\n",
        "train_rock_dir = os.path.join(train_dir, \"rock\")\n",
        "train_paper_dir = os.path.join(train_dir, \"paper\")\n",
        "train_scissors_dir = os.path.join(train_dir, \"scissors\")"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "e1ZM7CMbS3bq",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "validation_dir = os.path.join(\"/\", \"tmp\", \"rps-test-set\")\n",
        "\n",
        "validation_rock_dir = os.path.join(validation_dir, \"rock\")\n",
        "validation_paper_dir = os.path.join(validation_dir, \"paper\")\n",
        "validation_scissors_dir = os.path.join(validation_dir, \"scissors\")"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pi8yZj6nS8XD",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "total_train = len(os.listdir(train_rock_dir)) + len(os.listdir(train_paper_dir)) + len(os.listdir(train_scissors_dir))\n",
        "total_val = len(os.listdir(validation_rock_dir)) + len(os.listdir(validation_paper_dir)) + len(os.listdir(validation_scissors_dir))\n",
        "\n",
        "print(\"Total training images:\", total_train)\n",
        "print(\"Total validation images:\", total_val)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "yS-TnPFGYidl",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "rock_dir = train_rock_dir\n",
        "paper_dir = train_paper_dir\n",
        "scissors_dir = train_scissors_dir\n",
        "\n",
        "rock_files = os.listdir(rock_dir)\n",
        "paper_files = os.listdir(paper_dir)\n",
        "scissors_files = os.listdir(scissors_dir)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ahRZipZoXTiy",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "%matplotlib inline\n",
        "\n",
        "import matplotlib.pyplot as plt\n",
        "import matplotlib.image as mpimg\n",
        "\n",
        "pic_index = 2\n",
        "\n",
        "next_rock = [os.path.join(rock_dir, fname) \n",
        "                for fname in rock_files[pic_index-2:pic_index]]\n",
        "next_paper = [os.path.join(paper_dir, fname) \n",
        "                for fname in paper_files[pic_index-2:pic_index]]\n",
        "next_scissors = [os.path.join(scissors_dir, fname) \n",
        "                for fname in scissors_files[pic_index-2:pic_index]]\n",
        "\n",
        "for i, img_path in enumerate(next_rock+next_paper+next_scissors):\n",
        "  #print(img_path)\n",
        "  img = mpimg.imread(img_path)\n",
        "  plt.imshow(img)\n",
        "  plt.axis('Off')\n",
        "  plt.show()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "JVOG8hw3YypA",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import keras_preprocessing\n",
        "from keras_preprocessing import image\n",
        "from keras_preprocessing.image import ImageDataGenerator\n",
        "\n",
        "TRAINING_DIR = \"/tmp/rps/\""
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "B61KjJv-ZF16",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "training_datagen = ImageDataGenerator(\n",
        "      rescale = 1./255,\n",
        "\t    rotation_range=40,\n",
        "      width_shift_range=0.2,\n",
        "      height_shift_range=0.2,\n",
        "      shear_range=0.2,\n",
        "      zoom_range=0.2,\n",
        "      horizontal_flip=True,\n",
        "      fill_mode='nearest')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "qHnBzZ5kZJHW",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "VALIDATION_DIR = \"/tmp/rps-test-set/\"\n",
        "validation_datagen = ImageDataGenerator(rescale = 1./255)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "a0PLwOLzZLpa",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "train_generator = training_datagen.flow_from_directory(\n",
        "\tTRAINING_DIR,\n",
        "\ttarget_size=(150,150),\n",
        "\tclass_mode='categorical'\n",
        ")"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_OPIzHuoZOXC",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "validation_generator = validation_datagen.flow_from_directory(\n",
        "\tVALIDATION_DIR,\n",
        "\ttarget_size=(150,150),\n",
        "\tclass_mode='categorical'\n",
        ")"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "nOHswUa3Z9z6",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "model = tf.keras.models.Sequential([\n",
        "    # Note the input shape is the desired size of the image 150x150 with 3 bytes color\n",
        "    # This is the first convolution\n",
        "    tf.keras.layers.Conv2D(64, (3,3), activation='relu', input_shape=(150, 150, 3)),\n",
        "    tf.keras.layers.MaxPooling2D(2, 2),\n",
        "    # The second convolution\n",
        "    tf.keras.layers.Conv2D(64, (3,3), activation='relu'),\n",
        "    tf.keras.layers.MaxPooling2D(2,2),\n",
        "    # The third convolution\n",
        "    tf.keras.layers.Conv2D(128, (3,3), activation='relu'),\n",
        "    tf.keras.layers.MaxPooling2D(2,2),\n",
        "    # The fourth convolution\n",
        "    tf.keras.layers.Conv2D(128, (3,3), activation='relu'),\n",
        "    tf.keras.layers.MaxPooling2D(2,2),\n",
        "    # Flatten the results to feed into a DNN\n",
        "    tf.keras.layers.Flatten(),\n",
        "    tf.keras.layers.Dropout(0.5),\n",
        "    # 512 neuron hidden layer\n",
        "    tf.keras.layers.Dense(512, activation='relu'),\n",
        "    tf.keras.layers.Dense(3, activation='softmax')\n",
        "])\n",
        "\n",
        "model.summary()\n",
        "\n",
        "model.compile(loss = 'categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3ZaLMUMbaCKU",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "history = model.fit(\n",
        "    train_generator, \n",
        "    epochs=10, \n",
        "    validation_data=validation_generator,\n",
        "    verbose=True\n",
        ")"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5suZ71hChRKA",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import numpy as np\n",
        "from google.colab import files\n",
        "from keras.preprocessing import image\n",
        "\n",
        "uploaded = files.upload()\n",
        "\n",
        "for fn in uploaded.keys():\n",
        " \n",
        "  # predicting images\n",
        "  path = fn\n",
        "  img = image.load_img(path, target_size=(150, 150))\n",
        "  x = image.img_to_array(img)\n",
        "  x = np.expand_dims(x, axis=0)\n",
        "\n",
        "  images = np.vstack([x])\n",
        "  classes = model.predict(images, batch_size=10)\n",
        "  print(fn)\n",
        "  print(classes)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "b8AnbtWXWFRy",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "model.save(\"rps.h5\")\n",
        "\n",
        "files.download(\"rps.h5\")"
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}