TensorFlow学习笔记：搭建CNN模型

最近跟着 Udacity 上的深度学习课程学了一丢丢 TensorFlow，这里记录一下用 TensorFlow搭建简单 CNN 网络的代码模板。

python代码

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))

卷积网络结构

conv

<br>