{ "cells": [ { "cell_type": "markdown", "metadata": { "colab_type": "text", "id": "4embtkV0pNxM" }, "source": [ "Deep Learning\n", "=============\n", "\n", "Assignment 4\n", "------------\n", "\n", "Previously in `2_fullyconnected.ipynb` and `3_regularization.ipynb`, we trained fully connected networks to classify [notMNIST](http://yaroslavvb.blogspot.com/2011/09/notmnist-dataset.html) characters.\n", "\n", "The goal of this assignment is make the neural network convolutional." ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "cellView": "both", "colab": { "autoexec": { "startup": false, "wait_interval": 0 } }, "colab_type": "code", "collapsed": true, "id": "tm2CQN_Cpwj0" }, "outputs": [], "source": [ "# These are all the modules we'll be using later. Make sure you can import them\n", "# before proceeding further.\n", "from __future__ import print_function\n", "import numpy as np\n", "import tensorflow as tf\n", "from six.moves import cPickle as pickle\n", "from six.moves import range" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "cellView": "both", "colab": { "autoexec": { "startup": false, "wait_interval": 0 }, "output_extras": [ { "item_id": 1 } ] }, "colab_type": "code", "collapsed": false, "executionInfo": { "elapsed": 11948, "status": "ok", "timestamp": 1446658914837, "user": { "color": "", "displayName": "", "isAnonymous": false, "isMe": true, "permissionId": "", "photoUrl": "", "sessionId": "0", "userId": "" }, "user_tz": 480 }, "id": "y3-cj1bpmuxc", "outputId": "016b1a51-0290-4b08-efdb-8c95ffc3cd01" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training set (200000, 28, 28) (200000,)\n", "Validation set (10000, 28, 28) (10000,)\n", "Test set (10000, 28, 28) (10000,)\n" ] } ], "source": [ "pickle_file = 'notMNIST.pickle'\n", "\n", "with open(pickle_file, 'rb') as f:\n", " save = pickle.load(f)\n", " train_dataset = save['train_dataset']\n", " train_labels = save['train_labels']\n", " valid_dataset = save['valid_dataset']\n", " valid_labels = save['valid_labels']\n", " test_dataset = save['test_dataset']\n", " test_labels = save['test_labels']\n", " del save # hint to help gc free up memory\n", " print('Training set', train_dataset.shape, train_labels.shape)\n", " print('Validation set', valid_dataset.shape, valid_labels.shape)\n", " print('Test set', test_dataset.shape, test_labels.shape)" ] }, { "cell_type": "markdown", "metadata": { "colab_type": "text", "id": "L7aHrm6nGDMB" }, "source": [ "Reformat into a TensorFlow-friendly shape:\n", "- convolutions need the image data formatted as a cube (width by height by #channels)\n", "- labels as float 1-hot encodings." ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "cellView": "both", "colab": { "autoexec": { "startup": false, "wait_interval": 0 }, "output_extras": [ { "item_id": 1 } ] }, "colab_type": "code", "collapsed": false, "executionInfo": { "elapsed": 11952, "status": "ok", "timestamp": 1446658914857, "user": { "color": "", "displayName": "", "isAnonymous": false, "isMe": true, "permissionId": "", "photoUrl": "", "sessionId": "0", "userId": "" }, "user_tz": 480 }, "id": "IRSyYiIIGIzS", "outputId": "650a208c-8359-4852-f4f5-8bf10e80ef6c" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training set (200000, 28, 28, 1) (200000, 10)\n", "Validation set (10000, 28, 28, 1) (10000, 10)\n", "Test set (10000, 28, 28, 1) (10000, 10)\n" ] } ], "source": [ "image_size = 28\n", "num_labels = 10\n", "num_channels = 1 # grayscale\n", "\n", "import numpy as np\n", "\n", "def reformat(dataset, labels):\n", " dataset = dataset.reshape(\n", " (-1, image_size, image_size, num_channels)).astype(np.float32)\n", " labels = (np.arange(num_labels) == labels[:,None]).astype(np.float32)\n", " return dataset, labels\n", "train_dataset, train_labels = reformat(train_dataset, train_labels)\n", "valid_dataset, valid_labels = reformat(valid_dataset, valid_labels)\n", "test_dataset, test_labels = reformat(test_dataset, test_labels)\n", "print('Training set', train_dataset.shape, train_labels.shape)\n", "print('Validation set', valid_dataset.shape, valid_labels.shape)\n", "print('Test set', test_dataset.shape, test_labels.shape)" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "cellView": "both", "colab": { "autoexec": { "startup": false, "wait_interval": 0 } }, "colab_type": "code", "collapsed": true, "id": "AgQDIREv02p1" }, "outputs": [], "source": [ "def accuracy(predictions, labels):\n", " return (100.0 * np.sum(np.argmax(predictions, 1) == np.argmax(labels, 1))\n", " / predictions.shape[0])" ] }, { "cell_type": "markdown", "metadata": { "colab_type": "text", "id": "5rhgjmROXu2O" }, "source": [ "Let's build a small network with two convolutional layers, followed by one fully connected layer. Convolutional networks are more expensive computationally, so we'll limit its depth and number of fully connected nodes." ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "cellView": "both", "colab": { "autoexec": { "startup": false, "wait_interval": 0 } }, "colab_type": "code", "collapsed": true, "id": "IZYv70SvvOan" }, "outputs": [], "source": [ "batch_size = 16\n", "patch_size = 5\n", "depth = 16\n", "num_hidden = 64\n", "\n", "graph = tf.Graph()\n", "\n", "with graph.as_default():\n", "\n", " # Input data.\n", " tf_train_dataset = tf.placeholder(\n", " tf.float32, shape=(batch_size, image_size, image_size, num_channels))\n", " tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels))\n", " tf_valid_dataset = tf.constant(valid_dataset)\n", " tf_test_dataset = tf.constant(test_dataset)\n", " \n", " # Variables.\n", " layer1_weights = tf.Variable(tf.truncated_normal(\n", " [patch_size, patch_size, num_channels, depth], stddev=0.1))\n", " layer1_biases = tf.Variable(tf.zeros([depth]))\n", " layer2_weights = tf.Variable(tf.truncated_normal(\n", " [patch_size, patch_size, depth, depth], stddev=0.1))\n", " layer2_biases = tf.Variable(tf.constant(1.0, shape=[depth]))\n", " layer3_weights = tf.Variable(tf.truncated_normal(\n", " [image_size // 4 * image_size // 4 * depth, num_hidden], stddev=0.1))\n", " layer3_biases = tf.Variable(tf.constant(1.0, shape=[num_hidden]))\n", " layer4_weights = tf.Variable(tf.truncated_normal(\n", " [num_hidden, num_labels], stddev=0.1))\n", " layer4_biases = tf.Variable(tf.constant(1.0, shape=[num_labels]))\n", " \n", " # Model.\n", " def model(data):\n", " conv = tf.nn.conv2d(data, layer1_weights, [1, 2, 2, 1], padding='SAME')\n", " hidden = tf.nn.relu(conv + layer1_biases)\n", " conv = tf.nn.conv2d(hidden, layer2_weights, [1, 2, 2, 1], padding='SAME')\n", " hidden = tf.nn.relu(conv + layer2_biases)\n", " shape = hidden.get_shape().as_list()\n", " reshape = tf.reshape(hidden, [shape[0], shape[1] * shape[2] * shape[3]])\n", " hidden = tf.nn.relu(tf.matmul(reshape, layer3_weights) + layer3_biases)\n", " return tf.matmul(hidden, layer4_weights) + layer4_biases\n", " \n", " # Training computation.\n", " logits = model(tf_train_dataset)\n", " loss = tf.reduce_mean(\n", " tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels))\n", " \n", " # Optimizer.\n", " optimizer = tf.train.GradientDescentOptimizer(0.05).minimize(loss)\n", " \n", " # Predictions for the training, validation, and test data.\n", " train_prediction = tf.nn.softmax(logits)\n", " valid_prediction = tf.nn.softmax(model(tf_valid_dataset))\n", " test_prediction = tf.nn.softmax(model(tf_test_dataset))" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "cellView": "both", "colab": { "autoexec": { "startup": false, "wait_interval": 0 }, "output_extras": [ { "item_id": 37 } ] }, "colab_type": "code", "collapsed": false, "executionInfo": { "elapsed": 63292, "status": "ok", "timestamp": 1446658966251, "user": { "color": "", "displayName": "", "isAnonymous": false, "isMe": true, "permissionId": "", "photoUrl": "", "sessionId": "0", "userId": "" }, "user_tz": 480 }, "id": "noKFb2UovVFR", "outputId": "28941338-2ef9-4088-8bd1-44295661e628" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Initialized\n", "Minibatch loss at step 0: 3.139105\n", "Minibatch accuracy: 12.5%\n", "Validation accuracy: 11.9%\n", "Minibatch loss at step 100: 1.115680\n", "Minibatch accuracy: 62.5%\n", "Validation accuracy: 67.1%\n", "Minibatch loss at step 200: 0.356532\n", "Minibatch accuracy: 87.5%\n", "Validation accuracy: 78.4%\n", "Minibatch loss at step 300: 0.310974\n", "Minibatch accuracy: 93.8%\n", "Validation accuracy: 78.7%\n", "Minibatch loss at step 400: 0.602386\n", "Minibatch accuracy: 68.8%\n", "Validation accuracy: 79.5%\n", "Minibatch loss at step 500: 0.441770\n", "Minibatch accuracy: 87.5%\n", "Validation accuracy: 81.2%\n", "Minibatch loss at step 600: 0.840172\n", "Minibatch accuracy: 75.0%\n", "Validation accuracy: 82.3%\n", "Minibatch loss at step 700: 1.235861\n", "Minibatch accuracy: 68.8%\n", "Validation accuracy: 82.9%\n", "Minibatch loss at step 800: 0.885891\n", "Minibatch accuracy: 81.2%\n", "Validation accuracy: 82.5%\n", "Minibatch loss at step 900: 0.300222\n", "Minibatch accuracy: 87.5%\n", "Validation accuracy: 82.6%\n", "Minibatch loss at step 1000: 0.506481\n", "Minibatch accuracy: 87.5%\n", "Validation accuracy: 84.0%\n", "Test accuracy: 90.1%\n" ] } ], "source": [ "num_steps = 1001\n", "\n", "with tf.Session(graph=graph) as session:\n", " tf.initialize_all_variables().run()\n", " print('Initialized')\n", " for step in range(num_steps):\n", " offset = (step * batch_size) % (train_labels.shape[0] - batch_size)\n", " batch_data = train_dataset[offset:(offset + batch_size), :, :, :]\n", " batch_labels = train_labels[offset:(offset + batch_size), :]\n", " feed_dict = {tf_train_dataset : batch_data, tf_train_labels : batch_labels}\n", " _, l, predictions = session.run(\n", " [optimizer, loss, train_prediction], feed_dict=feed_dict)\n", " if (step % 100 == 0):\n", " print('Minibatch loss at step %d: %f' % (step, l))\n", " print('Minibatch accuracy: %.1f%%' % accuracy(predictions, batch_labels))\n", " print('Validation accuracy: %.1f%%' % accuracy(\n", " valid_prediction.eval(), valid_labels))\n", " print('Test accuracy: %.1f%%' % accuracy(test_prediction.eval(), test_labels))" ] }, { "cell_type": "markdown", "metadata": { "colab_type": "text", "id": "KedKkn4EutIK" }, "source": [ "---\n", "Problem 1\n", "---------\n", "\n", "The convolutional model above uses convolutions with stride 2 to reduce the dimensionality. Replace the strides by a max pooling operation (`nn.max_pool()`) of stride 2 and kernel size 2." ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "collapsed": true }, "outputs": [], "source": [ "batch_size = 16\n", "patch_size = 5\n", "depth = 16\n", "num_hidden = 64\n", "\n", "graph = tf.Graph()\n", "\n", "with graph.as_default():\n", "\n", " # Input data.\n", " tf_train_dataset = tf.placeholder(\n", " tf.float32, shape=(batch_size, image_size, image_size, num_channels))\n", " tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels))\n", " tf_valid_dataset = tf.constant(valid_dataset)\n", " tf_test_dataset = tf.constant(test_dataset)\n", " \n", " # Variables.\n", " layer1_weights = tf.Variable(tf.truncated_normal(\n", " [patch_size, patch_size, num_channels, depth], stddev=0.1))\n", " layer1_biases = tf.Variable(tf.zeros([depth]))\n", " layer2_weights = tf.Variable(tf.truncated_normal(\n", " [patch_size, patch_size, depth, depth], stddev=0.1))\n", " layer2_biases = tf.Variable(tf.constant(1.0, shape=[depth]))\n", " layer3_weights = tf.Variable(tf.truncated_normal(\n", " [image_size // 4 * image_size // 4 * depth, num_hidden], stddev=0.1))\n", " layer3_biases = tf.Variable(tf.constant(1.0, shape=[num_hidden]))\n", " layer4_weights = tf.Variable(tf.truncated_normal(\n", " [num_hidden, num_labels], stddev=0.1))\n", " layer4_biases = tf.Variable(tf.constant(1.0, shape=[num_labels]))\n", " \n", " # Model.\n", " def model(data):\n", " conv = tf.nn.conv2d(data, layer1_weights, [1, 1, 1, 1], padding='SAME')\n", " pool = tf.nn.max_pool(conv, [1, 2, 2, 1], [1, 2, 2, 1], padding='SAME')\n", " hidden = tf.nn.relu(pool + layer1_biases)\n", " conv = tf.nn.conv2d(hidden, layer2_weights, [1, 1, 1, 1], padding='SAME')\n", " pool = tf.nn.max_pool(conv, [1, 2, 2, 1], [1, 2, 2, 1], padding='SAME')\n", " hidden = tf.nn.relu(pool + layer2_biases)\n", " shape = hidden.get_shape().as_list()\n", " reshape = tf.reshape(hidden, [shape[0], shape[1] * shape[2] * shape[3]])\n", " hidden = tf.nn.relu(tf.matmul(reshape, layer3_weights) + layer3_biases)\n", " return tf.matmul(hidden, layer4_weights) + layer4_biases\n", " \n", " # Training computation.\n", " logits = model(tf_train_dataset)\n", " loss = tf.reduce_mean(\n", " tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels))\n", " \n", " # Optimizer.\n", " optimizer = tf.train.GradientDescentOptimizer(0.05).minimize(loss)\n", " \n", " # Predictions for the training, validation, and test data.\n", " train_prediction = tf.nn.softmax(logits)\n", " valid_prediction = tf.nn.softmax(model(tf_valid_dataset))\n", " test_prediction = tf.nn.softmax(model(tf_test_dataset))" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "collapsed": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Initialized\n", "Minibatch loss at step 0: 2.883915\n", "Minibatch accuracy: 12.5%\n", "Validation accuracy: 10.0%\n", "Minibatch loss at step 100: 1.051122\n", "Minibatch accuracy: 56.2%\n", "Validation accuracy: 59.1%\n", "Minibatch loss at step 200: 0.415176\n", "Minibatch accuracy: 87.5%\n", "Validation accuracy: 76.4%\n", "Minibatch loss at step 300: 0.316238\n", "Minibatch accuracy: 87.5%\n", "Validation accuracy: 81.7%\n", "Minibatch loss at step 400: 0.553747\n", "Minibatch accuracy: 75.0%\n", "Validation accuracy: 80.0%\n", "Minibatch loss at step 500: 0.250361\n", "Minibatch accuracy: 93.8%\n", "Validation accuracy: 81.5%\n", "Minibatch loss at step 600: 0.627140\n", "Minibatch accuracy: 68.8%\n", "Validation accuracy: 83.7%\n", "Minibatch loss at step 700: 1.068274\n", "Minibatch accuracy: 75.0%\n", "Validation accuracy: 84.3%\n", "Minibatch loss at step 800: 0.719155\n", "Minibatch accuracy: 75.0%\n", "Validation accuracy: 83.8%\n", "Minibatch loss at step 900: 0.629290\n", "Minibatch accuracy: 81.2%\n", "Validation accuracy: 84.5%\n", "Minibatch loss at step 1000: 0.510888\n", "Minibatch accuracy: 81.2%\n", "Validation accuracy: 84.2%\n", "Test accuracy: 89.8%\n" ] } ], "source": [ "num_steps = 1001\n", "\n", "with tf.Session(graph=graph) as session:\n", " tf.initialize_all_variables().run()\n", " print('Initialized')\n", " for step in range(num_steps):\n", " offset = (step * batch_size) % (train_labels.shape[0] - batch_size)\n", " batch_data = train_dataset[offset:(offset + batch_size), :, :, :]\n", " batch_labels = train_labels[offset:(offset + batch_size), :]\n", " feed_dict = {tf_train_dataset : batch_data, tf_train_labels : batch_labels}\n", " _, l, predictions = session.run(\n", " [optimizer, loss, train_prediction], feed_dict=feed_dict)\n", " if (step % 100 == 0):\n", " print('Minibatch loss at step %d: %f' % (step, l))\n", " print('Minibatch accuracy: %.1f%%' % accuracy(predictions, batch_labels))\n", " print('Validation accuracy: %.1f%%' % accuracy(\n", " valid_prediction.eval(), valid_labels))\n", " print('Test accuracy: %.1f%%' % accuracy(test_prediction.eval(), test_labels))" ] }, { "cell_type": "markdown", "metadata": { "colab_type": "text", "id": "klf21gpbAgb-" }, "source": [ "---\n", "Problem 2\n", "---------\n", "\n", "Try to get the best performance you can using a convolutional net. Look for example at the classic [LeNet5](http://yann.lecun.com/exdb/lenet/) architecture, adding Dropout, and/or adding learning rate decay." ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "collapsed": false }, "outputs": [], "source": [ "batch_size = 16\n", "patch_size = 5\n", "depth = 16\n", "num_hidden = 64\n", "\n", "graph = tf.Graph()\n", "\n", "with graph.as_default():\n", "\n", " # Input data.\n", " tf_train_dataset = tf.placeholder(\n", " tf.float32, shape=(batch_size, image_size, image_size, num_channels))\n", " tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels))\n", " tf_valid_dataset = tf.constant(valid_dataset)\n", " tf_test_dataset = tf.constant(test_dataset)\n", "\n", " # Placeholder to control dropout probability.\n", " keep_prob = tf.placeholder(tf.float32)\n", " \n", " # Variables.\n", " layer1_weights = tf.Variable(tf.truncated_normal(\n", " [patch_size, patch_size, num_channels, depth], stddev=0.1))\n", " layer1_biases = tf.Variable(tf.zeros([depth]))\n", " layer2_weights = tf.Variable(tf.truncated_normal(\n", " [patch_size, patch_size, depth, depth], stddev=0.1))\n", " layer2_biases = tf.Variable(tf.constant(1.0, shape=[depth]))\n", " layer3_weights = tf.Variable(tf.truncated_normal(\n", " [image_size // 4 * image_size // 4 * depth, num_hidden], stddev=0.1))\n", " layer3_biases = tf.Variable(tf.constant(1.0, shape=[num_hidden]))\n", " layer4_weights = tf.Variable(tf.truncated_normal(\n", " [num_hidden, num_labels], stddev=0.1))\n", " layer4_biases = tf.Variable(tf.constant(1.0, shape=[num_labels]))\n", " \n", " # Model.\n", " def model(data):\n", " conv = tf.nn.conv2d(data, layer1_weights, [1, 1, 1, 1], padding='SAME')\n", " pool = tf.nn.max_pool(conv, [1, 2, 2, 1], [1, 2, 2, 1], padding='SAME')\n", " hidden = tf.nn.relu(pool + layer1_biases)\n", " conv = tf.nn.conv2d(hidden, layer2_weights, [1, 1, 1, 1], padding='SAME')\n", " pool = tf.nn.max_pool(conv, [1, 2, 2, 1], [1, 2, 2, 1], padding='SAME')\n", " hidden = tf.nn.relu(pool + layer2_biases)\n", " shape = hidden.get_shape().as_list()\n", " reshape = tf.reshape(hidden, [shape[0], shape[1] * shape[2] * shape[3]])\n", " hidden = tf.nn.relu(tf.matmul(reshape, layer3_weights) + layer3_biases)\n", " drop = tf.nn.dropout(hidden, keep_prob)\n", " return tf.matmul(drop, layer4_weights) + layer4_biases\n", " \n", " # Training computation.\n", " logits = model(tf_train_dataset)\n", " loss = tf.reduce_mean(\n", " tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels))\n", " \n", " # Optimizer.\n", " optimizer = tf.train.GradientDescentOptimizer(0.05).minimize(loss)\n", " \n", " # Predictions for the training, validation, and test data.\n", " train_prediction = tf.nn.softmax(logits)\n", " valid_prediction = tf.nn.softmax(model(tf_valid_dataset))\n", " test_prediction = tf.nn.softmax(model(tf_test_dataset))" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "collapsed": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Initialized\n", "Minibatch loss at step 0: 4.529957\n", "Minibatch accuracy: 18.8%\n", "Validation accuracy: 12.3%\n", "Minibatch loss at step 100: 1.826838\n", "Minibatch accuracy: 50.0%\n", "Validation accuracy: 46.1%\n", "Minibatch loss at step 200: 1.026006\n", "Minibatch accuracy: 62.5%\n", "Validation accuracy: 69.2%\n", "Minibatch loss at step 300: 0.719998\n", "Minibatch accuracy: 87.5%\n", "Validation accuracy: 76.9%\n", "Minibatch loss at step 400: 1.125187\n", "Minibatch accuracy: 62.5%\n", "Validation accuracy: 78.8%\n", "Minibatch loss at step 500: 0.659142\n", "Minibatch accuracy: 68.8%\n", "Validation accuracy: 80.9%\n", "Minibatch loss at step 600: 1.144517\n", "Minibatch accuracy: 62.5%\n", "Validation accuracy: 81.3%\n", "Minibatch loss at step 700: 1.284646\n", "Minibatch accuracy: 62.5%\n", "Validation accuracy: 81.7%\n", "Minibatch loss at step 800: 1.318694\n", "Minibatch accuracy: 68.8%\n", "Validation accuracy: 82.3%\n", "Minibatch loss at step 900: 0.596128\n", "Minibatch accuracy: 81.2%\n", "Validation accuracy: 83.2%\n", "Minibatch loss at step 1000: 0.593340\n", "Minibatch accuracy: 81.2%\n", "Validation accuracy: 83.5%\n", "Minibatch loss at step 1100: 1.036340\n", "Minibatch accuracy: 81.2%\n", "Validation accuracy: 83.8%\n", "Minibatch loss at step 1200: 0.578478\n", "Minibatch accuracy: 81.2%\n", "Validation accuracy: 84.5%\n", "Minibatch loss at step 1300: 1.571593\n", "Minibatch accuracy: 43.8%\n", "Validation accuracy: 83.8%\n", "Minibatch loss at step 1400: 0.659016\n", "Minibatch accuracy: 75.0%\n", "Validation accuracy: 84.5%\n", "Minibatch loss at step 1500: 0.455753\n", "Minibatch accuracy: 93.8%\n", "Validation accuracy: 84.9%\n", "Minibatch loss at step 1600: 0.458268\n", "Minibatch accuracy: 81.2%\n", "Validation accuracy: 84.5%\n", "Minibatch loss at step 1700: 0.856795\n", "Minibatch accuracy: 81.2%\n", "Validation accuracy: 84.9%\n", "Minibatch loss at step 1800: 0.423227\n", "Minibatch accuracy: 81.2%\n", "Validation accuracy: 85.0%\n", "Minibatch loss at step 1900: 0.750963\n", "Minibatch accuracy: 87.5%\n", "Validation accuracy: 84.8%\n", "Minibatch loss at step 2000: 0.760005\n", "Minibatch accuracy: 75.0%\n", "Validation accuracy: 85.4%\n", "Minibatch loss at step 2100: 0.779080\n", "Minibatch accuracy: 75.0%\n", "Validation accuracy: 85.5%\n", "Minibatch loss at step 2200: 0.371877\n", "Minibatch accuracy: 93.8%\n", "Validation accuracy: 85.4%\n", "Minibatch loss at step 2300: 0.551173\n", "Minibatch accuracy: 87.5%\n", "Validation accuracy: 85.1%\n", "Minibatch loss at step 2400: 0.251618\n", "Minibatch accuracy: 93.8%\n", "Validation accuracy: 86.0%\n", "Minibatch loss at step 2500: 1.167190\n", "Minibatch accuracy: 68.8%\n", "Validation accuracy: 84.7%\n", "Minibatch loss at step 2600: 1.088484\n", "Minibatch accuracy: 56.2%\n", "Validation accuracy: 85.0%\n", "Minibatch loss at step 2700: 0.663480\n", "Minibatch accuracy: 81.2%\n", "Validation accuracy: 85.2%\n", "Minibatch loss at step 2800: 0.869098\n", "Minibatch accuracy: 68.8%\n", "Validation accuracy: 86.3%\n", "Minibatch loss at step 2900: 0.405881\n", "Minibatch accuracy: 81.2%\n", "Validation accuracy: 86.4%\n", "Minibatch loss at step 3000: 0.435097\n", "Minibatch accuracy: 87.5%\n", "Validation accuracy: 86.0%\n", "Test accuracy: 92.1%\n" ] } ], "source": [ "num_steps = 3001\n", "\n", "with tf.Session(graph=graph) as session:\n", " tf.initialize_all_variables().run()\n", " print('Initialized')\n", " for step in range(num_steps):\n", " offset = (step * batch_size) % (train_labels.shape[0] - batch_size)\n", " batch_data = train_dataset[offset:(offset + batch_size), :, :, :]\n", " batch_labels = train_labels[offset:(offset + batch_size), :]\n", " feed_dict = {tf_train_dataset : batch_data, tf_train_labels : batch_labels, keep_prob: 1.0}\n", " feed_dict_w_drop = {tf_train_dataset : batch_data, tf_train_labels : batch_labels, keep_prob: 0.5}\n", " _, l, predictions = session.run(\n", " [optimizer, loss, train_prediction], feed_dict=feed_dict_w_drop)\n", " if (step % 100 == 0):\n", " print('Minibatch loss at step %d: %f' % (step, l))\n", " print('Minibatch accuracy: %.1f%%' % accuracy(predictions, batch_labels))\n", " print('Validation accuracy: %.1f%%' % accuracy(\n", " valid_prediction.eval(feed_dict=feed_dict), valid_labels))\n", " print('Test accuracy: %.1f%%' % accuracy(test_prediction.eval(feed_dict=feed_dict), test_labels))" ] } ], "metadata": { "colab": { "default_view": {}, "name": "4_convolutions.ipynb", "provenance": [], "version": "0.3.2", "views": {} }, "kernelspec": { "display_name": "Python 2", "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": "2.7.11" } }, "nbformat": 4, "nbformat_minor": 0 }