{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "# Build an Image Dataset in TensorFlow.\n",
    "\n",
    "For this example, you need to make your own set of images (JPEG).\n",
    "We will show 2 different ways to build that dataset:\n",
    "\n",
    "- From a root folder, that will have a sub-folder containing images for each class\n",
    "\n",
    "```\n",
    "    ROOT_FOLDER\n",
    "       |-------- SUBFOLDER (CLASS 0)\n",
    "       |             |\n",
    "       |             | ----- image1.jpg\n",
    "       |             | ----- image2.jpg\n",
    "       |             | ----- etc...\n",
    "       |             \n",
    "       |-------- SUBFOLDER (CLASS 1)\n",
    "       |             |\n",
    "       |             | ----- image1.jpg\n",
    "       |             | ----- image2.jpg\n",
    "       |             | ----- etc...\n",
    "\n",
    "```\n",
    "\n",
    "- From a plain text file, that will list all images with their class ID:\n",
    "\n",
    "```\n",
    "    /path/to/image/1.jpg CLASS_ID\n",
    "    /path/to/image/2.jpg CLASS_ID\n",
    "    /path/to/image/3.jpg CLASS_ID\n",
    "    /path/to/image/4.jpg CLASS_ID\n",
    "    etc...\n",
    "```\n",
    "\n",
    "Below, there are some parameters that you need to change (Marked 'CHANGE HERE'), \n",
    "such as the dataset path.\n",
    "\n",
    "- Author: Aymeric Damien\n",
    "- Project: https://github.com/aymericdamien/TensorFlow-Examples/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from __future__ import print_function\n",
    "\n",
    "import tensorflow as tf\n",
    "import os\n",
    "\n",
    "# Dataset Parameters - CHANGE HERE\n",
    "MODE = 'folder' # or 'file', if you choose a plain text file (see above).\n",
    "DATASET_PATH = '/path/to/dataset/' # the dataset file or root folder path.\n",
    "\n",
    "# Image Parameters\n",
    "N_CLASSES = 2 # CHANGE HERE, total number of classes\n",
    "IMG_HEIGHT = 64 # CHANGE HERE, the image height to be resized to\n",
    "IMG_WIDTH = 64 # CHANGE HERE, the image width to be resized to\n",
    "CHANNELS = 3 # The 3 color channels, change to 1 if grayscale"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Reading the dataset\n",
    "# 2 modes: 'file' or 'folder'\n",
    "def read_images(dataset_path, mode, batch_size):\n",
    "    imagepaths, labels = list(), list()\n",
    "    if mode == 'file':\n",
    "        # Read dataset file\n",
    "        data = open(dataset_path, 'r').read().splitlines()\n",
    "        for d in data:\n",
    "            imagepaths.append(d.split(' ')[0])\n",
    "            labels.append(int(d.split(' ')[1]))\n",
    "    elif mode == 'folder':\n",
    "        # An ID will be affected to each sub-folders by alphabetical order\n",
    "        label = 0\n",
    "        # List the directory\n",
    "        try:  # Python 2\n",
    "            classes = sorted(os.walk(dataset_path).next()[1])\n",
    "        except Exception:  # Python 3\n",
    "            classes = sorted(os.walk(dataset_path).__next__()[1])\n",
    "        # List each sub-directory (the classes)\n",
    "        for c in classes:\n",
    "            c_dir = os.path.join(dataset_path, c)\n",
    "            try:  # Python 2\n",
    "                walk = os.walk(c_dir).next()\n",
    "            except Exception:  # Python 3\n",
    "                walk = os.walk(c_dir).__next__()\n",
    "            # Add each image to the training set\n",
    "            for sample in walk[2]:\n",
    "                # Only keeps jpeg images\n",
    "                if sample.endswith('.jpg') or sample.endswith('.jpeg'):\n",
    "                    imagepaths.append(os.path.join(c_dir, sample))\n",
    "                    labels.append(label)\n",
    "            label += 1\n",
    "    else:\n",
    "        raise Exception(\"Unknown mode.\")\n",
    "\n",
    "    # Convert to Tensor\n",
    "    imagepaths = tf.convert_to_tensor(imagepaths, dtype=tf.string)\n",
    "    labels = tf.convert_to_tensor(labels, dtype=tf.int32)\n",
    "    # Build a TF Queue, shuffle data\n",
    "    image, label = tf.train.slice_input_producer([imagepaths, labels],\n",
    "                                                 shuffle=True)\n",
    "\n",
    "    # Read images from disk\n",
    "    image = tf.read_file(image)\n",
    "    image = tf.image.decode_jpeg(image, channels=CHANNELS)\n",
    "\n",
    "    # Resize images to a common size\n",
    "    image = tf.image.resize_images(image, [IMG_HEIGHT, IMG_WIDTH])\n",
    "\n",
    "    # Normalize\n",
    "    image = image * 1.0/127.5 - 1.0\n",
    "\n",
    "    # Create batches\n",
    "    X, Y = tf.train.batch([image, label], batch_size=batch_size,\n",
    "                          capacity=batch_size * 8,\n",
    "                          num_threads=4)\n",
    "\n",
    "    return X, Y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# -----------------------------------------------\n",
    "# THIS IS A CLASSIC CNN (see examples, section 3)\n",
    "# -----------------------------------------------\n",
    "# Note that a few elements have changed (usage of queues).\n",
    "\n",
    "# Parameters\n",
    "learning_rate = 0.001\n",
    "num_steps = 10000\n",
    "batch_size = 128\n",
    "display_step = 100\n",
    "\n",
    "# Network Parameters\n",
    "dropout = 0.75 # Dropout, probability to keep units\n",
    "\n",
    "# Build the data input\n",
    "X, Y = read_images(DATASET_PATH, MODE, batch_size)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Create model\n",
    "def conv_net(x, n_classes, dropout, reuse, is_training):\n",
    "    # Define a scope for reusing the variables\n",
    "    with tf.variable_scope('ConvNet', reuse=reuse):\n",
    "\n",
    "        # Convolution Layer with 32 filters and a kernel size of 5\n",
    "        conv1 = tf.layers.conv2d(x, 32, 5, activation=tf.nn.relu)\n",
    "        # Max Pooling (down-sampling) with strides of 2 and kernel size of 2\n",
    "        conv1 = tf.layers.max_pooling2d(conv1, 2, 2)\n",
    "\n",
    "        # Convolution Layer with 32 filters and a kernel size of 5\n",
    "        conv2 = tf.layers.conv2d(conv1, 64, 3, activation=tf.nn.relu)\n",
    "        # Max Pooling (down-sampling) with strides of 2 and kernel size of 2\n",
    "        conv2 = tf.layers.max_pooling2d(conv2, 2, 2)\n",
    "\n",
    "        # Flatten the data to a 1-D vector for the fully connected layer\n",
    "        fc1 = tf.contrib.layers.flatten(conv2)\n",
    "\n",
    "        # Fully connected layer (in contrib folder for now)\n",
    "        fc1 = tf.layers.dense(fc1, 1024)\n",
    "        # Apply Dropout (if is_training is False, dropout is not applied)\n",
    "        fc1 = tf.layers.dropout(fc1, rate=dropout, training=is_training)\n",
    "\n",
    "        # Output layer, class prediction\n",
    "        out = tf.layers.dense(fc1, n_classes)\n",
    "        # Because 'softmax_cross_entropy_with_logits' already apply softmax,\n",
    "        # we only apply softmax to testing network\n",
    "        out = tf.nn.softmax(out) if not is_training else out\n",
    "\n",
    "    return out"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Because Dropout have different behavior at training and prediction time, we\n",
    "# need to create 2 distinct computation graphs that share the same weights.\n",
    "\n",
    "# Create a graph for training\n",
    "logits_train = conv_net(X, N_CLASSES, dropout, reuse=False, is_training=True)\n",
    "# Create another graph for testing that reuse the same weights\n",
    "logits_test = conv_net(X, N_CLASSES, dropout, reuse=True, is_training=False)\n",
    "\n",
    "# Define loss and optimizer (with train logits, for dropout to take effect)\n",
    "loss_op = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(\n",
    "    logits=logits_train, labels=Y))\n",
    "optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)\n",
    "train_op = optimizer.minimize(loss_op)\n",
    "\n",
    "# Evaluate model (with test logits, for dropout to be disabled)\n",
    "correct_pred = tf.equal(tf.argmax(logits_test, 1), tf.cast(Y, tf.int64))\n",
    "accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))\n",
    "\n",
    "# Initialize the variables (i.e. assign their default value)\n",
    "init = tf.global_variables_initializer()\n",
    "\n",
    "# Saver object\n",
    "saver = tf.train.Saver()\n",
    "\n",
    "# Start training\n",
    "with tf.Session() as sess:\n",
    "\n",
    "    # Run the initializer\n",
    "    sess.run(init)\n",
    "\n",
    "    # Start the data queue\n",
    "    tf.train.start_queue_runners()\n",
    "\n",
    "    # Training cycle\n",
    "    for step in range(1, num_steps+1):\n",
    "\n",
    "        if step % display_step == 0:\n",
    "            # Run optimization and calculate batch loss and accuracy\n",
    "            _, loss, acc = sess.run([train_op, loss_op, accuracy])\n",
    "            print(\"Step \" + str(step) + \", Minibatch Loss= \" + \\\n",
    "                  \"{:.4f}\".format(loss) + \", Training Accuracy= \" + \\\n",
    "                  \"{:.3f}\".format(acc))\n",
    "        else:\n",
    "            # Only run the optimization op (backprop)\n",
    "            sess.run(train_op)\n",
    "\n",
    "    print(\"Optimization Finished!\")\n",
    "\n",
    "    # Save your model\n",
    "    saver.save(sess, 'my_tf_model')"
   ]
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python [default]",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}