{ "cells": [ { "cell_type": "markdown", "metadata": { "_cell_guid": "2b259663-cbdb-69ed-70f3-2d0bee1bdefc" }, "source": [ "Deep Neural Networks with TensorFlow\n", "\n", "- based on https://www.kaggle.com/kakauandme/digit-recognizer/tensorflow-deep-nn \n", "- extended and achieved **0.99157** score\n", "- added documentations to tensorflow built-in functions" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "aee84856-1c55-ff2f-6c0e-74b14832124c" }, "outputs": [], "source": [ "# import packages\n", "\n", "import numpy as np\n", "import pandas as pd\n", "import tensorflow as tf\n", "import matplotlib.pyplot as plt\n", "import matplotlib.cm as cm\n", "from subprocess import check_output\n", "\n", "# Learning rate for learning algorithm\n", "LEARNING_RATE = 5e-4\n", "\n", "# number of training iterations\n", "TRAINING_ITERATIONS = 10000\n", "ITERATIONS_PER_RUN = 100\n", "\n", "# dropout. Dropout is an extremely effective and simple regularization technique\n", "# based on keeping a neuron active with some probability p (a hyperparameter, here is DROPOUT), \n", "# or setting it to zero otherwise.\n", "# More about dropout http://cs231n.github.io/neural-networks-2/ \n", "DROPOUT = 0.5\n", "# training is made by selecting batches of size 50\n", "BATCH_SIZE = 100\n", "\n", "# validation set size. Validation set is a set of examples used to tune the parameters .\n", "# set to 0 to train on all available data\n", "VALIDATION_SIZE = 2000\n", "\n", "# image number to output\n", "IMAGE_TO_DISPLAY = 25" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "6dd4e899-deb1-d869-78fe-e3b482e46eba" }, "outputs": [], "source": [ "# Strutified shuffle is used insted of simple shuffle in order to achieve sample balancing\n", " # or equal number of examples in each of 10 classes.\n", "# Since there are different number of examples for each 10 classes in the MNIST data you may\n", " # also use simple shuffle.\n", "\n", "def stratified_shuffle(labels, num_classes):\n", " ix = np.argsort(labels).reshape((num_classes,-1))\n", " for i in range(len(ix)):\n", " np.random.shuffle(ix[i])\n", " return ix.T.reshape((-1))" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "c5eb4fd4-26af-08b8-e090-be6958981258" }, "outputs": [], "source": [ "# preload train and test data\n", "dataset = pd.read_csv(\"../input/train.csv\")\n", "test = pd.read_csv(\"../input/test.csv\").values\n", "\n", "images = dataset.iloc[:,1:].values\n", "images = images.astype(np.float)\n", "\n", "# convert from [0:255] => [0.0:1.0]\n", "images = np.multiply(images, 1.0 / 255.0)\n", "print('data size: (%g, %g)' % images.shape)\n", "\n", "# size of one image - 784 values which can be transformed to 28 by 28 image\n", "image_size = images.shape[1]\n", "print ('image_size => {0}'.format(image_size))\n", "\n", "# in this case all images are square (28x28)\n", "image_width = image_height = np.ceil(np.sqrt(image_size)).astype(np.uint8)\n", "print ('image_width => {0}\\nimage_height => {1}'.format(image_width,image_height))" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "6083f494-c491-d98d-5239-bfe54f362705" }, "outputs": [], "source": [ "# display an image\n", "def display(img):\n", " \n", " # (784) => (28x28)\n", " one_image = img.reshape(image_width,image_height)\n", " \n", " plt.axis('off')\n", " plt.imshow(one_image, cmap=cm.binary)\n", "\n", "# display an image. IMAGE_TO_DISPLAY = 25\n", "display(images[IMAGE_TO_DISPLAY])" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "77ee1345-2b88-fb04-cea2-380a99f2455a" }, "outputs": [], "source": [ "# print information about image size, label of image-to-display and number of labels\n", "labels_flat = dataset[[0]].values.ravel()\n", "print('length of one image ({0})'.format(len(labels_flat)))\n", "print ('label of image [{0}] => {1}'.format(IMAGE_TO_DISPLAY,labels_flat[IMAGE_TO_DISPLAY]))\n", "\n", "labels_count = np.unique(labels_flat).shape[0]\n", "print('number of labes => {0}'.format(labels_count))" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "88c77ef9-2801-7b09-c152-9b5306ecde25" }, "outputs": [], "source": [ "# convert class labels from scalars to one-hot vectors\n", "# 0 => [1 0 0 0 0 0 0 0 0 0]\n", "# 1 => [0 1 0 0 0 0 0 0 0 0]\n", "# ...\n", "# 9 => [0 0 0 0 0 0 0 0 0 1]\n", "\n", "def dense_to_one_hot(labels_dense, num_classes):\n", " num_labels = labels_dense.shape[0]\n", " index_offset = np.arange(num_labels) * num_classes\n", " labels_one_hot = np.zeros((num_labels, num_classes))\n", " labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1\n", " return labels_one_hot\n", "\n", "labels = dense_to_one_hot(labels_flat, labels_count)\n", "labels = labels.astype(np.uint8)\n", "\n", "print('labels({0[0]},{0[1]})'.format(labels.shape))\n", "print ('labels vector for image [{0}] => {1}'.format(IMAGE_TO_DISPLAY,labels[IMAGE_TO_DISPLAY]))" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "886f637d-b9ae-ee72-bd34-91e23ea0af20" }, "outputs": [], "source": [ "# split data into training & validation sets\n", "validation_images = images[:VALIDATION_SIZE]\n", "validation_labels = labels[:VALIDATION_SIZE]\n", "\n", "train_images = images[VALIDATION_SIZE:]\n", "train_labels = labels[VALIDATION_SIZE:]\n", "train_labels_flat = labels_flat[VALIDATION_SIZE:]\n", "\n", "#train_images = images\n", "#train_labels = labels\n", "#train_labels_flat = labels_flat\n", "\n", "print('train data size({0[0]},{0[1]})'.format(train_images.shape))\n", "print('validation data size({0[0]},{0[1]})'.format(validation_images.shape))" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "f25c4279-a723-3b3f-47f2-b444f2b66cc7" }, "outputs": [], "source": [ "# weights initialization.\n", "# tf.truncated_normal: Outputs random values from a truncated normal distribution.\n", "# The generated values follow a normal distribution with specified standard deviation.\n", "\n", "def weight_variable(shape):\n", " initial = tf.truncated_normal(shape, stddev=0.1)\n", " return tf.Variable(initial)\n", "\n", "# tf.constant: Creates a constant tensor. \n", "# The resulting tensor is populated with values of type dtype, as specified by arguments value and shape\n", "def bias_variable(shape):\n", " initial = tf.constant(0.1, shape=shape)\n", " return tf.Variable(initial)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "14a7eec3-d624-c01d-a8ea-2b51d92bd003" }, "outputs": [], "source": [ "# convolution\n", "# Computes a 2-D convolution given 4-D input and filter tensors.\n", "# tf.nn.conv2d(input, filter, strides, padding, use_cudnn_on_gpu=None, data_format=None, name=None)\n", "# input: A Tensor. Must be one of the following types: half, float32, float64.\n", "# filter: A Tensor. Must have the same type as input.\n", "# strides: A list of ints. 1-D of length 4. The stride of the sliding window for each dimension \n", " # of input. Must be in the same order as the dimension specified with format.\n", "# padding: A string from: \"SAME\", \"VALID\". The type of padding algorithm to use.\n", "\n", "def conv2d(x, W):\n", " return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "ac4b0c8f-3f94-5bbd-20d3-cb91c374596f" }, "outputs": [], "source": [ "# Performs the max pooling on the input.\n", "# tf.nn.max_pool(value, ksize, strides, padding, data_format='NHWC', name=None)\n", "# value: A 4-D Tensor with shape [batch, height, width, channels] and type tf.float32.\n", "# ksize: A list of ints that has length >= 4. The size of the window for each dimension \n", " # of the input tensor.\n", "# strides: A list of ints that has length >= 4. The stride of the sliding window for \n", " # each dimension of the input tensor.\n", "# padding: A string, either 'VALID' or 'SAME'. \n", "\n", "def max_pool_2x2(x):\n", " return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "7896ced3-b214-0ba8-a1c2-27bbeb4f9e60" }, "outputs": [], "source": [ "# input & output of NN\n", "\n", "# images\n", "x = tf.placeholder('float', shape=[None, image_size])\n", "# labels\n", "y_ = tf.placeholder('float', shape=[None, labels_count])" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "8f284c89-f890-75ed-9281-5299fefd8389" }, "outputs": [], "source": [ "# first convolutional layer\n", "W_conv1 = weight_variable([5, 5, 1, 32])\n", "b_conv1 = bias_variable([32])\n", "\n", "# (40000,784) => (40000,28,28,1)]\n", "# tf.reshape(tensor, shape, name=None)\n", "# Given tensor, this operation returns a tensor that has the same values as tensor with shape shape.\n", "image = tf.reshape(x, [-1,image_width , image_height,1])\n", "#print (image.get_shape()) # =>(40000,28,28,1)\n", "\n", "h_conv1 = tf.nn.relu(conv2d(image, W_conv1) + b_conv1)\n", "#print (h_conv1.get_shape()) # => (40000, 28, 28, 32)\n", "h_pool1 = max_pool_2x2(h_conv1)\n", "#print (h_pool1.get_shape()) # => (40000, 14, 14, 32)\n", "\n", "# Prepare for visualization\n", "# display 32 fetures in 4 by 8 grid\n", "layer1 = tf.reshape(h_conv1, (-1, image_height, image_width, 4 ,8)) \n", "# reorder so the channels are in the first dimension, x and y follow.\n", "layer1 = tf.transpose(layer1, (0, 3, 1, 4,2))\n", "layer1 = tf.reshape(layer1, (-1, image_height*4, image_width*8)) " ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "81baa5d3-84d9-1e87-5210-170dcf1da26a" }, "outputs": [], "source": [ "# second convolutional layer\n", "W_conv2 = weight_variable([5, 5, 32, 64])\n", "b_conv2 = bias_variable([64])\n", "\n", "h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)\n", "#print (h_conv2.get_shape()) # => (40000, 14,14, 64)\n", "h_pool2 = max_pool_2x2(h_conv2)\n", "#print (h_pool2.get_shape()) # => (40000, 7, 7, 64)\n", "\n", "# Prepare for visualization\n", "# display 64 fetures in 4 by 16 grid\n", "layer2 = tf.reshape(h_conv2, (-1, 14, 14, 4 ,16)) \n", "# reorder so the channels are in the first dimension, x and y follow.\n", "layer2 = tf.transpose(layer2, (0, 3, 1, 4,2))\n", "layer2 = tf.reshape(layer2, (-1, 14*4, 14*16)) " ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "288b4d3c-e82e-daf5-eb4a-af45c99f6679" }, "outputs": [], "source": [ "# fully-connected layer\n", "W_fc1 = weight_variable([7 * 7 * 64, 1024])\n", "b_fc1 = bias_variable([1024])\n", "\n", "# (40000, 7, 7, 64) => (40000, 3136)\n", "h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])\n", "\n", "#tf.matmul(a, b, transpose_a=False, transpose_b=False, a_is_sparse=False, b_is_sparse=False, name=None)\n", "# Multiplies matrix a by matrix b, producing a * b.\n", "h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)\n", "#print (h_fc1.get_shape()) # => (40000, 1024)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "d096f94d-021a-6b6a-3766-148057344ba2" }, "outputs": [], "source": [ "# dropout\n", "# tf.nn.dropout(x, keep_prob, noise_shape=None, seed=None, name=None)\n", "# Computes dropout.\n", "# With probability keep_prob, outputs the input element scaled up by 1 / keep_prob, otherwise outputs 0. \n", " # The scaling is so that the expected sum is unchanged.\n", "keep_prob = tf.placeholder('float')\n", "h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "247dd8de-d8e7-70ef-29e9-906f8baa9963" }, "outputs": [], "source": [ "# readout layer for deep net\n", "W_fc2 = weight_variable([1024, labels_count])\n", "b_fc2 = bias_variable([labels_count])\n", "\n", "y = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)\n", "\n", "#print (y.get_shape()) # => (40000, 10)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "13992fbb-9696-e881-6ecb-bc0f648e75b0" }, "outputs": [], "source": [ "# cost function\n", "cross_entropy = -tf.reduce_sum(y_*tf.log(y))\n", "\n", "# optimisation function\n", "global_step = tf.Variable(0, name='global_step', trainable=False)\n", "train_step = tf.train.AdamOptimizer(LEARNING_RATE).minimize(cross_entropy, global_step=global_step)\n", "\n", "# evaluation\n", "correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))\n", "\n", "accuracy = tf.reduce_mean(tf.cast(correct_prediction, 'float'))" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "3dbbbf92-ec8c-8a6e-9db2-eefc66f17fc7" }, "outputs": [], "source": [ "# prediction function\n", "#[0.1, 0.9, 0.2, 0.1, 0.1 0.3, 0.5, 0.1, 0.2, 0.3] => 1\n", "predict = tf.argmax(y,1)\n", "print(predict)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "c101e1cb-961a-0419-4a2f-dca346b024af" }, "outputs": [], "source": [ "# Training\n", "epochs_completed = 0\n", "index_in_epoch = 0\n", "num_examples = train_images.shape[0]\n", "\n", "# visualisation variables\n", "train_accuracies = []\n", "validation_accuracies = []\n", "x_range = []\n", "\n", "display_step=100\n", "\n", "# serve data by batches\n", "def next_batch(batch_size):\n", " \n", " global train_images\n", " global train_labels\n", " global train_labels_flat\n", " global index_in_epoch\n", " global epochs_completed\n", " \n", " start = index_in_epoch\n", " index_in_epoch += batch_size\n", " \n", " # when all trainig data have been already used, it is reorder randomly \n", " if index_in_epoch > num_examples:\n", " # finished epoch\n", " epochs_completed += 1\n", " # shuffle the data\n", " #perm = np.arange(num_examples)\n", " #np.random.shuffle(perm)\n", " perm = stratified_shuffle(train_labels_flat, 10)\n", " train_images = train_images[perm]\n", " train_labels = train_labels[perm]\n", " train_labels_flat = train_labels_flat[perm]\n", " # start next epoch\n", " start = 0\n", " index_in_epoch = batch_size\n", " assert batch_size <= num_examples\n", " end = index_in_epoch\n", " return train_images[start:end], train_labels[start:end]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "b0995616-17b0-5410-9881-4b66c14273be" }, "outputs": [], "source": [ "# displays the progress of the training\n", "# Training accuracy, validation accuracy and iterations\n", "\n", "def check_progress(sess, accuracy, batch_xs, batch_ys, i):\n", " import datetime\n", " train_accuracy = accuracy.eval(session=sess, feed_dict={x: batch_xs, y_: batch_ys, keep_prob: 1.0}) \n", " if(VALIDATION_SIZE):\n", " validation_accuracy = accuracy.eval(session=sess, feed_dict={x: validation_images,\n", " y_: validation_labels,\n", " keep_prob: 1.0}) \n", " print('%s: trn / val => %.4f / %.4f for step %d'\n", " % (str(datetime.datetime.now()), train_accuracy, validation_accuracy, i+1))\n", " else:\n", " print('training_accuracy => %.4f for step %d' % (train_accuracy, i+1))\n", " validation_accuracy = []\n", " return (train_accuracy, validation_accuracy)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "e9f4489c-70d2-4c35-cff2-83df5d9ab8d4" }, "outputs": [], "source": [ "# In this part we save model after a certain number of iterations and use the saved model\n", "# for the next round\n", "# By this we achieve 10 epochs on the entire training data (validation data included)\n", "\n", "saver = tf.train.Saver(max_to_keep=5)\n", "sess = tf.Session()\n", "sess.run(tf.initialize_all_variables())\n", "\n", "ckpt = tf.train.get_checkpoint_state('.')\n", "if ckpt and ckpt.model_checkpoint_path:\n", " saver.restore(sess, ckpt.model_checkpoint_path)\n", " print(\"Restored session from: %s\" % ckpt.model_checkpoint_path)\n", "else:\n", " print(\"No checkpoint found.\")\n", "\n", "start_step = global_step.eval(sess)\n", "for i in range(start_step, min(start_step + ITERATIONS_PER_RUN, TRAINING_ITERATIONS)):\n", " #get new batch\n", " batch_xs, batch_ys = next_batch(BATCH_SIZE)\n", "\n", " # train on batch\n", " sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys, keep_prob: DROPOUT})\n", "\n", " # check progress and create a checkpoint\n", " if (i+1) % display_step == 0 or (i+1) == TRAINING_ITERATIONS:\n", " train_accuracy, validation_accuracy = check_progress(sess, accuracy, batch_xs, batch_ys, i)\n", " train_accuracies.append(train_accuracy)\n", " validation_accuracies.append(validation_accuracy)\n", " x_range.append(i)\n", "\n", " saver.save(sess, 'model', global_step=i+1)\n", "\n", " # increase display_step\n", " #if i % (display_step*10) == 0 and i:\n", " # display_step *= 2" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "c7be9290-71d1-f2ea-61e0-745067e7ea08" }, "outputs": [], "source": [ "#ckpt = tf.train.get_checkpoint_state('.')\n", "#ckpt.model_checkpoint_path\n", "#saver.restore(sess, './model-3800')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "d59a83f2-3be1-55da-b0b9-0b8ad83172a1" }, "outputs": [], "source": [ "# check final accuracy on validation set.\n", "# Since we may use validation data set in training data set the accuracy is around 0.99\n", "\n", "if(VALIDATION_SIZE):\n", " validation_accuracy = accuracy.eval(session=sess, feed_dict={x: validation_images,\n", " y_: validation_labels,\n", " keep_prob: 1.0})\n", " print('validation_accuracy => %.4f' % validation_accuracy)\n", " plt.plot(x_range, train_accuracies,'-b', label='Training')\n", " plt.plot(x_range, validation_accuracies,'-g', label='Validation')\n", " plt.legend(loc='lower right', frameon=False)\n", " plt.ylim(ymax = 1.1, ymin = 0.9)\n", " plt.ylabel('accuracy')\n", " plt.xlabel('step')\n", " plt.grid()\n", " plt.show()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "1d6a5b15-6099-65f3-e2a1-8c1e3a74a161" }, "outputs": [], "source": [ "# read test data from CSV file \n", "test_images = pd.read_csv('../input/test.csv').values\n", "test_images = test_images.astype(np.float)\n", "\n", "# convert from [0:255] => [0.0:1.0]\n", "test_images = np.multiply(test_images, 1.0 / 255.0)\n", "print('test_images({0[0]},{0[1]})'.format(test_images.shape))\n", "\n", "# predict test set\n", "#predicted_lables = predict.eval(feed_dict={x: test_images, keep_prob: 1.0})\n", "\n", "# using batches is more resource efficient\n", "predicted_lables = np.zeros(test_images.shape[0])\n", "for i in range(0,test_images.shape[0]//BATCH_SIZE):\n", " predicted_lables[i*BATCH_SIZE : (i+1)*BATCH_SIZE] = predict.eval(\n", " session=sess, feed_dict={x: test_images[i*BATCH_SIZE : (i+1)*BATCH_SIZE],\n", " keep_prob: 1.0})\n", "\n", "print('predicted_lables({0})'.format(len(predicted_lables)))\n", "\n", "# output test image and prediction\n", "display(test_images[IMAGE_TO_DISPLAY])\n", "print ('predicted_lables[{0}] => {1}'.format(IMAGE_TO_DISPLAY,predicted_lables[IMAGE_TO_DISPLAY]))\n", "\n", "# save results\n", "file_name = 'submission_softmax_%s.csv' % global_step.eval(sess)\n", "np.savetxt(file_name, \n", " np.c_[range(1,len(test_images)+1),predicted_lables], \n", " delimiter=',', \n", " header = 'ImageId,Label', \n", " comments = '', \n", " fmt='%d')\n", "print('saved: %s' % file_name)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "76c36fc9-4d4a-e7f7-39e8-87812472841a" }, "outputs": [], "source": [ "layer1_grid = layer1.eval(session=sess, feed_dict={x: test_images[IMAGE_TO_DISPLAY:IMAGE_TO_DISPLAY+1], \n", " keep_prob: 1.0})\n", "plt.axis('off')\n", "plt.imshow(layer1_grid[0], cmap=cm.seismic )" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "2f4dcca5-5153-e7b8-fcd9-8b9fb1f42c18" }, "outputs": [], "source": [ "sess.close()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "8c251f6a-512a-21f6-2b65-0c90f80b964b" }, "outputs": [], "source": [ "#!rm model-6*\n", "!ls -ahl" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "8a6f9f5d-8b96-aa02-6e25-927a130d43e1" }, "outputs": [], "source": [ "#!cp model-8200 model-submission-8200\n", "#!cp model-8200.meta model-submission-8200.meta\n", "#!cat submission_softmax_8200.csv" ] } ], "metadata": { "_change_revision": 0, "_is_fork": false, "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": "3.5.2" } }, "nbformat": 4, "nbformat_minor": 0 }