{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "source": [
    "# Full run through of raw images to classification with Convolutional Neural Network #\n",
    "\n",
    "In this tutorial, we're going to be running through taking raw images that have been labeled for us already, and then feeding them through a convolutional neural network for classification. \n",
    "\n",
    "The images are either of dog(s) or cat(s). \n",
    "\n",
    "Once you have downloaded and extracted the data from https://www.kaggle.com/c/dogs-vs-cats-redux-kernels-edition/data, you're ready to begin."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true,
    "scrolled": true
   },
   "source": [
    "# Part 1 - Preprocessing\n",
    "\n",
    "We've got the data, but we can't exactly just stuff raw images right through our convolutional neural network. First, we need all of the images to be the same size, and then we also will probably want to just grayscale them. Also, the labels of \"cat\" and \"dog\" are not useful, we want them to be one-hot arrays. \n",
    "\n",
    "Interestingly, we may be approaching a time when our data might not need to be all the same size. Looking into TensorFlow's research blog: https://research.googleblog.com/2017/02/announcing-tensorflow-fold-deep.html\n",
    "\n",
    "\"TensorFlow Fold makes it easy to implement deep-learning models that operate over data of varying size and structure.\"\n",
    "\n",
    "Fascinating...but, for now, we'll do it the old fashioned way.\n",
    "\n",
    "<h4>Package Requirements</h4>\n",
    "numpy (pip install numpy)\n",
    "tqdm (pip install tqdm)\n",
    "\n",
    "I will be using the GPU version of TensorFlow along with tflearn. \n",
    "\n",
    "To install the CPU version of TensorFlow, just do pip install tensorflow\n",
    "To install the GPU version of TensorFlow, you need to get alllll the dependencies and such.\n",
    "\n",
    "<strong>TensorFlow Installation tutorials:</strong>\n",
    "\n",
    "<a href=\"https://pythonprogramming.net/how-to-cuda-gpu-tensorflow-deep-learning-tutorial/\" target=\"blank\">Installing the GPU version of TensorFlow in Ubuntu</a>\n",
    "\n",
    "<a href=\"https://www.youtube.com/watch?v=r7-WPbx8VuY\" target=\"blank\">Installing the GPU version of TensorFlow on a Windows machine</a>\n",
    "\n",
    "<strong>Using TensorFlow and concept tutorials:</strong>\n",
    "\n",
    "<a href=\"https://pythonprogramming.net/neural-networks-machine-learning-tutorial\" target=\"blank\">Introduction to deep learning with neural networks</a>\n",
    "\n",
    "<a href=\"https://pythonprogramming.net/tensorflow-introduction-machine-learning-tutorial/\" target=\"blank\">Introduction to TensorFlow</a>\n",
    "\n",
    "<a href=\"https://pythonprogramming.net/convolutional-neural-network-cnn-machine-learning-tutorial/\" target=\"blank\">Intro to Convolutional Neural Networks</a>\n",
    "\n",
    "<a href=\"https://pythonprogramming.net/cnn-tensorflow-convolutional-nerual-network-machine-learning-tutorial/\" target=\"blank\">Convolutional Neural Network in TensorFlow tutorial</a>\n",
    "\n",
    "Finally, I will be making use of <a href=\"https://pythonprogramming.net/tflearn-machine-learning-tutorial/\" target=\"blank\">TFLearn</a>. Once you have TensorFlow installed, do pip install tflearn.\n",
    "\n",
    "\n",
    "First, we'll get our imports and constants for preprocessing:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true,
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "import cv2                 # working with, mainly resizing, images\n",
    "import numpy as np         # dealing with arrays\n",
    "import os                  # dealing with directories\n",
    "from random import shuffle # mixing up or currently ordered data that might lead our network astray in training.\n",
    "from tqdm import tqdm      # a nice pretty percentage bar for tasks. Thanks to viewer Daniel Bühler for this suggestion\n",
    "\n",
    "TRAIN_DIR = 'X:/Kaggle_Data/dogs_vs_cats/train/train'\n",
    "TEST_DIR = 'X:/Kaggle_Data/dogs_vs_cats/test/test'\n",
    "IMG_SIZE = 50\n",
    "LR = 1e-3\n",
    "\n",
    "MODEL_NAME = 'dogsvscats-{}-{}.model'.format(LR, '2conv-basic') # just so we remember which saved model is which, sizes must match"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "Now, our first order of business is to convert the images and labels to array information that we can pass through our network. To do this, we'll need a helper function to convert the image name to an array. \n",
    "\n",
    "Our images are labeled like \"cat.1\" or \"dog.3\" and so on, so we can just split out the dog/cat, and then convert to an array like so:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "def label_img(img):\n",
    "    word_label = img.split('.')[-3]\n",
    "    # conversion to one-hot array [cat,dog]\n",
    "    #                            [much cat, no dog]\n",
    "    if word_label == 'cat': return [1,0]\n",
    "    #                             [no cat, very doggo]\n",
    "    elif word_label == 'dog': return [0,1]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "Now, we can build another function to fully process the training images and their labels into arrays:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "def create_train_data():\n",
    "    training_data = []\n",
    "    for img in tqdm(os.listdir(TRAIN_DIR)):\n",
    "        label = label_img(img)\n",
    "        path = os.path.join(TRAIN_DIR,img)\n",
    "        img = cv2.imread(path,cv2.IMREAD_GRAYSCALE)\n",
    "        img = cv2.resize(img, (IMG_SIZE,IMG_SIZE))\n",
    "        training_data.append([np.array(img),np.array(label)])\n",
    "    shuffle(training_data)\n",
    "    np.save('train_data.npy', training_data)\n",
    "    return training_data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "The tqdm module was introduced to me by one of my viewers, it's a really nice, pretty, way to measure where you are in a process, rather than printing things out at intervals...etc, it gives a progress bar. Super neat. \n",
    "\n",
    "Anyway, the above function converts the data for us into array data of the image and its label. \n",
    "\n",
    "When we've gone through all of the images, we shuffle them, then save. Shuffle modifies a variable in place, so there's no need to re-define it here. \n",
    "\n",
    "With this function, we will both save, and return the array data. This way, if we just change the neural network's structure, and not something with the images, like image size..etc..then we can just load the array file and save some processing time. While we're here, we might as well also make a function to process the testing data. This is the *actual* competition test data, NOT the data that we'll use to check the accuracy of our algorithm as we test. This data has no label. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "def process_test_data():\n",
    "    testing_data = []\n",
    "    for img in tqdm(os.listdir(TEST_DIR)):\n",
    "        path = os.path.join(TEST_DIR,img)\n",
    "        img_num = img.split('.')[0]\n",
    "        img = cv2.imread(path,cv2.IMREAD_GRAYSCALE)\n",
    "        img = cv2.resize(img, (IMG_SIZE,IMG_SIZE))\n",
    "        testing_data.append([np.array(img), img_num])\n",
    "        \n",
    "    shuffle(testing_data)\n",
    "    np.save('test_data.npy', testing_data)\n",
    "    return testing_data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "Now, we can run the training:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████████████████████| 25000/25000 [00:23<00:00, 1048.08it/s]\n"
     ]
    }
   ],
   "source": [
    "train_data = create_train_data()\n",
    "# If you have already created the dataset:\n",
    "#train_data = np.load('train_data.npy')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "# Convolutional Neural Network\n",
    "\n",
    "Next, we're ready to define our neural network:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "import tflearn\n",
    "from tflearn.layers.conv import conv_2d, max_pool_2d\n",
    "from tflearn.layers.core import input_data, dropout, fully_connected\n",
    "from tflearn.layers.estimator import regression\n",
    "\n",
    "convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name='input')\n",
    "\n",
    "convnet = conv_2d(convnet, 32, 5, activation='relu')\n",
    "convnet = max_pool_2d(convnet, 5)\n",
    "\n",
    "convnet = conv_2d(convnet, 64, 5, activation='relu')\n",
    "convnet = max_pool_2d(convnet, 5)\n",
    "\n",
    "convnet = fully_connected(convnet, 1024, activation='relu')\n",
    "convnet = dropout(convnet, 0.8)\n",
    "\n",
    "convnet = fully_connected(convnet, 2, activation='softmax')\n",
    "convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')\n",
    "\n",
    "model = tflearn.DNN(convnet, tensorboard_dir='log')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "What we have here is a nice, 2 layered convolutional neural network, with a fully connected layer, and then the output layer. It's been debated whether or not a fully connected layer is of any use. I'll leave it in anyway. \n",
    "\n",
    "This exact convnet was good enough for recognizing hand 28x28 written digits. Let's see how it does with cats and dogs at 50x50 resolution. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "Now, it wont always be the case that you're training the network fresh every time. Maybe first you just want to see how 3 epochs trains, but then, after 3, maybe you're done, or maybe you want to see about 5 epochs. We want to be saving our model after every session, and reloading it if we have a saved version, so I will add this:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "if os.path.exists('{}.meta'.format(MODEL_NAME)):\n",
    "    model.load(MODEL_NAME)\n",
    "    print('model loaded!')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "Now, let's split out training and testing data:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "train = train_data[:-500]\n",
    "test = train_data[-500:]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "Now, the training data and testing data are both labeled datasets. The training data is what we'll fit the neural network with, and the test data is what we're going to use to validate the results. The test data will be \"out of sample,\" meaning the testing data will only be used to test the accuracy of the network, not to train it. \n",
    "\n",
    "We also have \"test\" images that we downloaded. THOSE images are not labeled at all, and those are what we'll submit to Kaggle for the competition.\n",
    "\n",
    "Next, we're going to create our data arrays. For some reason, typical numpy logic like:\n",
    "\n",
    "array[:,0] and array[:,1] did NOT work for me here. Not sure what I'm doing wrong, so I do this instead to separate my features and labels:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "X = np.array([i[0] for i in train]).reshape(-1,IMG_SIZE,IMG_SIZE,1)\n",
    "Y = [i[1] for i in train]\n",
    "\n",
    "test_x = np.array([i[0] for i in test]).reshape(-1,IMG_SIZE,IMG_SIZE,1)\n",
    "test_y = [i[1] for i in test]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "Now we fit for 3 epochs:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training Step: 1148  | total loss: \u001b[1m\u001b[32m11.71334\u001b[0m\u001b[0m | time: 4.061s\n",
      "| Adam | epoch: 003 | loss: 11.71334 - acc: 0.4913 -- iter: 24448/24500\n",
      "Training Step: 1149  | total loss: \u001b[1m\u001b[32m11.72928\u001b[0m\u001b[0m | time: 5.074s\n",
      "| Adam | epoch: 003 | loss: 11.72928 - acc: 0.4906 | val_loss: 11.88134 - val_acc: 0.4840 -- iter: 24500/24500\n",
      "--\n"
     ]
    }
   ],
   "source": [
    "model.fit({'input': X}, {'targets': Y}, n_epoch=3, validation_set=({'input': test_x}, {'targets': test_y}), \n",
    "    snapshot_step=500, show_metric=True, run_id=MODEL_NAME)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "Hmm... it doesn't look like we've gotten anywhere at all. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "We could keep trying, but, if you haven't made accuracy progress in the first 3 epochs, you're probably not going to at all, unless it's due to overfitment...at least in my experience. \n",
    "\n",
    "So... now what?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "# Size Matters #\n",
    "We're gonna need a bigger network\n",
    "\n",
    "First, we need to reset the graph instance, since we're doing this in a continuous environment:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "tf.reset_default_graph()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training Step: 1148  | total loss: \u001b[1m\u001b[32m0.47510\u001b[0m\u001b[0m | time: 4.969s\n",
      "| Adam | epoch: 003 | loss: 0.47510 - acc: 0.7791 -- iter: 24448/24500\n",
      "Training Step: 1149  | total loss: \u001b[1m\u001b[32m0.46175\u001b[0m\u001b[0m | time: 5.983s\n",
      "| Adam | epoch: 003 | loss: 0.46175 - acc: 0.7856 | val_loss: 0.56595 - val_acc: 0.7040 -- iter: 24500/24500\n",
      "--\n"
     ]
    }
   ],
   "source": [
    "convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name='input')\n",
    "\n",
    "convnet = conv_2d(convnet, 32, 5, activation='relu')\n",
    "convnet = max_pool_2d(convnet, 5)\n",
    "\n",
    "convnet = conv_2d(convnet, 64, 5, activation='relu')\n",
    "convnet = max_pool_2d(convnet, 5)\n",
    "\n",
    "convnet = conv_2d(convnet, 128, 5, activation='relu')\n",
    "convnet = max_pool_2d(convnet, 5)\n",
    "\n",
    "convnet = conv_2d(convnet, 64, 5, activation='relu')\n",
    "convnet = max_pool_2d(convnet, 5)\n",
    "\n",
    "convnet = conv_2d(convnet, 32, 5, activation='relu')\n",
    "convnet = max_pool_2d(convnet, 5)\n",
    "\n",
    "convnet = fully_connected(convnet, 1024, activation='relu')\n",
    "convnet = dropout(convnet, 0.8)\n",
    "\n",
    "convnet = fully_connected(convnet, 2, activation='softmax')\n",
    "convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')\n",
    "\n",
    "model = tflearn.DNN(convnet, tensorboard_dir='log')\n",
    "\n",
    "\n",
    "\n",
    "if os.path.exists('{}.meta'.format(MODEL_NAME)):\n",
    "    model.load(MODEL_NAME)\n",
    "    print('model loaded!')\n",
    "\n",
    "train = train_data[:-500]\n",
    "test = train_data[-500:]\n",
    "\n",
    "X = np.array([i[0] for i in train]).reshape(-1,IMG_SIZE,IMG_SIZE,1)\n",
    "Y = [i[1] for i in train]\n",
    "\n",
    "test_x = np.array([i[0] for i in test]).reshape(-1,IMG_SIZE,IMG_SIZE,1)\n",
    "test_y = [i[1] for i in test]\n",
    "\n",
    "model.fit({'input': X}, {'targets': Y}, n_epoch=3, validation_set=({'input': test_x}, {'targets': test_y}), \n",
    "    snapshot_step=500, show_metric=True, run_id=MODEL_NAME)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "WELL WELL WELL... Looks like we've got a winner. With neural networks, size matters a ton. We went from having apparently un-trainable data to having obviously trainable data, and this was only 3 epochs. \n",
    "\n",
    "If you are happy with the model, go ahead and save it:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INFO:tensorflow:C:\\Users\\H\\Desktop\\KaggleDogsvsCats\\dogsvscats-0.001-2conv-basic.model is not in all_model_checkpoint_paths. Manually adding it.\n"
     ]
    }
   ],
   "source": [
    "model.save(MODEL_NAME)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "Now we can reload the model, and continue training (we don't NEED to reload the model here since this is continuous and the model is still in memory, but if you were running this as a program you would)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "tf.reset_default_graph()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training Step: 4978  | total loss: \u001b[1m\u001b[32m0.31290\u001b[0m\u001b[0m | time: 4.031s\n",
      "| Adam | epoch: 010 | loss: 0.31290 - acc: 0.8641 -- iter: 24448/24500\n",
      "Training Step: 4979  | total loss: \u001b[1m\u001b[32m0.30547\u001b[0m\u001b[0m | time: 5.044s\n",
      "| Adam | epoch: 010 | loss: 0.30547 - acc: 0.8683 | val_loss: 0.57259 - val_acc: 0.7980 -- iter: 24500/24500\n",
      "--\n",
      "INFO:tensorflow:C:\\Users\\H\\Desktop\\KaggleDogsvsCats\\dogsvscats-0.001-2conv-basic.model is not in all_model_checkpoint_paths. Manually adding it.\n"
     ]
    }
   ],
   "source": [
    "convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name='input')\n",
    "\n",
    "convnet = conv_2d(convnet, 32, 5, activation='relu')\n",
    "convnet = max_pool_2d(convnet, 5)\n",
    "\n",
    "convnet = conv_2d(convnet, 64, 5, activation='relu')\n",
    "convnet = max_pool_2d(convnet, 5)\n",
    "\n",
    "convnet = conv_2d(convnet, 128, 5, activation='relu')\n",
    "convnet = max_pool_2d(convnet, 5)\n",
    "\n",
    "convnet = conv_2d(convnet, 64, 5, activation='relu')\n",
    "convnet = max_pool_2d(convnet, 5)\n",
    "\n",
    "convnet = conv_2d(convnet, 32, 5, activation='relu')\n",
    "convnet = max_pool_2d(convnet, 5)\n",
    "\n",
    "convnet = fully_connected(convnet, 1024, activation='relu')\n",
    "convnet = dropout(convnet, 0.8)\n",
    "\n",
    "convnet = fully_connected(convnet, 2, activation='softmax')\n",
    "convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')\n",
    "\n",
    "model = tflearn.DNN(convnet, tensorboard_dir='log')\n",
    "\n",
    "\n",
    "\n",
    "if os.path.exists('C:/Users/H/Desktop/KaggleDogsvsCats/{}.meta'.format(MODEL_NAME)):\n",
    "    model.load(MODEL_NAME)\n",
    "    print('model loaded!')\n",
    "\n",
    "train = train_data[:-500]\n",
    "test = train_data[-500:]\n",
    "\n",
    "X = np.array([i[0] for i in train]).reshape(-1,IMG_SIZE,IMG_SIZE,1)\n",
    "Y = [i[1] for i in train]\n",
    "\n",
    "test_x = np.array([i[0] for i in test]).reshape(-1,IMG_SIZE,IMG_SIZE,1)\n",
    "test_y = [i[1] for i in test]\n",
    "\n",
    "model.fit({'input': X}, {'targets': Y}, n_epoch=10, validation_set=({'input': test_x}, {'targets': test_y}), \n",
    "    snapshot_step=500, show_metric=True, run_id=MODEL_NAME)\n",
    "\n",
    "model.save(MODEL_NAME)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "# You can be too big #\n",
    "\n",
    "Bigger is not always better, there does get to be a limit, at least from my experience. A bigger network figures things out better, and quicker, but tends to also overfit the training data. You can use dropout (sets randomly a certain % of nodes to not take part in the network for more robusts networks) to rectify this slightly, but there does seem to be a limit. \n",
    "\n",
    "Okay, now what? Let's see how we've done!"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "# Visually inspecting our network against unlabeled data #"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAdsAAAFeCAYAAADNB7VfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nQEBAQMAF4z8I7EzMCxVsNgAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x1834fc3cf60>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# if you need to create the data:\n",
    "#test_data = process_test_data()\n",
    "# if you already have some saved:\n",
    "test_data = np.load('test_data.npy')\n",
    "\n",
    "fig=plt.figure()\n",
    "\n",
    "for num,data in enumerate(test_data[:12]):\n",
    "    # cat: [1,0]\n",
    "    # dog: [0,1]\n",
    "    \n",
    "    img_num = data[1]\n",
    "    img_data = data[0]\n",
    "    \n",
    "    y = fig.add_subplot(3,4,num+1)\n",
    "    orig = img_data\n",
    "    data = img_data.reshape(IMG_SIZE,IMG_SIZE,1)\n",
    "    #model_out = model.predict([data])[0]\n",
    "    model_out = model.predict([data])[0]\n",
    "    \n",
    "    if np.argmax(model_out) == 1: str_label='Dog'\n",
    "    else: str_label='Cat'\n",
    "        \n",
    "    y.imshow(orig,cmap='gray')\n",
    "    plt.title(str_label)\n",
    "    y.axes.get_xaxis().set_visible(False)\n",
    "    y.axes.get_yaxis().set_visible(False)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "Alright, so we made a couple mistakes, but not too bad actually! \n",
    "\n",
    "If you're happy with it, let's compete!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|███████████████████████████| 12500/12500 [00:22<00:00, 566.76it/s]\n"
     ]
    }
   ],
   "source": [
    "with open('submission_file.csv','w') as f:\n",
    "    f.write('id,label\\n')\n",
    "            \n",
    "with open('submission_file.csv','a') as f:\n",
    "    for data in tqdm(test_data):\n",
    "        img_num = data[1]\n",
    "        img_data = data[0]\n",
    "        orig = img_data\n",
    "        data = img_data.reshape(IMG_SIZE,IMG_SIZE,1)\n",
    "        model_out = model.predict([data])[0]\n",
    "        f.write('{},{}\\n'.format(img_num,model_out[1]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "Heading to Kaggle > Competitions > Dogs vs. Cats Redux: Kernels Edition... Let's submit!\n",
    "\n",
    "This got me ~700th place with a logloss of 0.55508"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.5.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}
