Reprinted from: http://jermmy.xyz/2017/02/16/2017-2-16-learn-tensorflow-build-cnn-model/
Recently , I learned a bit of TensorFlow from the deep learning course on Udacity. Here is a code template for building a simple CNN network with TensorFlow.
python code
pickle_file = 'notMNIST.pickle' with open(pickle_file, 'rb') as f: save = pickle.load(f) train_dataset = save['train_dataset'] train_labels = save['train_labels'] valid_dataset = save['valid_dataset'] valid_labels = save['valid_labels'] test_dataset = save['test_dataset'] test_labels = save['test_labels'] del save # hint to help gc free up memory print('Training set', train_dataset.shape, train_labels.shape) print('Validation set', valid_dataset.shape, valid_labels.shape) print('Test set', test_dataset.shape, test_labels.shape) image_size = 28 num_labels = 10 num_channels = 1 # grayscale batch_size = 16 patch_size = 5 depth = 16 num_hidden = 64 graph = tf.Graph() with graph.as_default(): # Input data. tf_train_dataset = tf.placeholder( tf.float32, shape=(batch_size, image_size, image_size, num_channels)) tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels)) tf_valid_dataset = tf.constant(valid_dataset) tf_test_dataset = tf.constant(test_dataset) # Variables. layer1_weights = tf.Variable(tf.truncated_normal([patch_size, patch_size, num_channels, depth], stddev=0.1)) layer1_biases = tf.Variable(tf.zeros([depth])) layer2_weights = tf.Variable(tf.truncated_normal([patch_size, patch_size, depth, depth], stddev=0.1)) layer2_biases = tf.Variable(tf.constant(1.0, shape=[depth])) layer3_weights = tf.Variable( tf.truncated_normal([image_size // 4 * image_size // 4 * depth, num_hidden], stddev=0.1)) layer3_biases = tf.Variable(tf.constant(1.0, shape=[num_hidden])) layer4_weights = tf.Variable(tf.truncated_normal([num_hidden, num_labels], stddev=0.1)) layer4_biases = tf.Variable(tf.constant(1.0, shape=[num_labels])) # Model. def model(data): conv1 = tf.nn.relu(tf.nn.conv2d(data, layer1_weights, [1, 1, 1, 1], padding='SAME') + layer1_biases) pool1 = tf.nn.max_pool(conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') conv2 = tf.nn.relu(tf.nn.conv2d(pool1, layer2_weights, [1, 1, 1, 1], padding='SAME') + layer2_biases) pool2 = tf.nn.max_pool(conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME') shape = pool2.get_shape().as_list() reshape = tf.reshape(pool2, [shape[0], shape[1] * shape[2] * shape[3]]) fc1 = tf.nn.relu(tf.matmul(reshape, layer3_weights) + layer3_biases) return tf.matmul(fc1, layer4_weights) + layer4_biases # Training computation. logits = model(tf_train_dataset) loss = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels)) # Optimizer. optimizer = tf.train.GradientDescentOptimizer(0.05).minimize(loss) # Predictions for the training, validation, and test data. train_prediction = tf.nn.softmax(logits) valid_prediction = tf.nn.softmax(model(tf_valid_dataset)) test_prediction = tf.nn.softmax(model(tf_test_dataset)) num_steps = 1001 with tf.Session(graph=graph) as session: tf.initialize_all_variables().run() print('Initialized') for step in range(num_steps): offset = (step * batch_size) % (train_labels.shape[0] - batch_size) batch_data = train_dataset[offset:(offset + batch_size), :, :, :] batch_labels = train_labels[offset:(offset + batch_size), :] feed_dict = {tf_train_dataset: batch_data, tf_train_labels: batch_labels} _, l, predictions = session.run( [optimizer, loss, train_prediction], feed_dict=feed_dict) if (step % 50 == 0): print('Minibatch loss at step %d: %f' % (step, l)) print('Minibatch accuracy: %.1f%%' % accuracy(predictions, batch_labels)) print('Validation accuracy: %.1f%%' % accuracy( valid_prediction.eval(), valid_labels)) print('Max pool Test accuracy: %.1f%%' % accuracy(test_prediction.eval(), test_labels))Volumes and Neural Networks