Udacity深度学习，作业3，第3部分: Tensorflow dropout函数

Question

我现在是Udacity深度学习课程的作业3。我已经完成了大部分工作，并且它正在工作，但我注意到问题3，关于在tensorflow中使用'dropout‘，似乎降低了我的性能，而不是提高了它。

所以我想我做错了什么。我将把我的完整代码放在这里。如果有人能向我解释如何正确使用dropout，我将不胜感激。(或者确认我是否正确地使用了它，但在这种情况下它并没有帮助。)它的准确率从94%以上(没有丢失)下降到91.5%。如果你不使用L2正则化，降级会更大。

def create_nn(dataset, weights_hidden, biases_hidden, weights_out, biases_out):
    # Original layer
    logits = tf.add(tf.matmul(tf_train_dataset, weights_hidden), biases_hidden)
    # Drop Out layer 1
    logits = tf.nn.dropout(logits, 0.5)
    # Hidden Relu layer
    logits = tf.nn.relu(logits)
    # Drop Out layer 2
    logits = tf.nn.dropout(logits, 0.5)
    # Output: Connect hidden layer to a node for each class
    logits = tf.add(tf.matmul(logits, weights_out), biases_out)
    return logits


# Create model
batch_size = 128
hidden_layer_size = 1024
beta = 1e-3

graph = tf.Graph()
with graph.as_default():
    # Input data. For the training data, we use a placeholder that will be fed
    # at run time with a training minibatch.
    tf_train_dataset = tf.placeholder(tf.float32,
                                    shape=(batch_size, image_size * image_size))
    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.
    weights_hidden = tf.Variable(
        #tf.truncated_normal([image_size * image_size, num_labels]))
        tf.truncated_normal([image_size * image_size, hidden_layer_size]))
    #biases = tf.Variable(tf.zeros([num_labels]))
    biases_hidden = tf.Variable(tf.zeros([hidden_layer_size]))

    weights_out = tf.Variable(tf.truncated_normal([hidden_layer_size, num_labels]))
    biases_out = tf.Variable(tf.zeros([num_labels]))


    # Training computation.
    #logits = tf.matmul(tf_train_dataset, weights_out) + biases_out
    logits = create_nn(tf_train_dataset, weights_hidden, biases_hidden, weights_out, biases_out)

    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=tf_train_labels, logits=logits))
    loss += beta * (tf.nn.l2_loss(weights_hidden) + tf.nn.l2_loss(weights_out))

    # Optimizer.
    optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss)

    # Predictions for the training, validation, and test data.
    train_prediction = tf.nn.softmax(logits)
    #valid_prediction = tf.nn.softmax(tf.matmul(tf_valid_dataset, weights_out) + biases_out)
    #test_prediction = tf.nn.softmax(tf.matmul(tf_test_dataset, weights_out) + biases_out)
    valid_prediction = tf.nn.softmax(tf.matmul(tf.nn.relu(tf.matmul(tf_valid_dataset, weights_hidden) + biases_hidden), weights_out) + biases_out)
    test_prediction = tf.nn.softmax(tf.matmul(tf.nn.relu(tf.matmul(tf_test_dataset, weights_hidden) + biases_hidden), weights_out) + biases_out)


num_steps = 10000

with tf.Session(graph=graph) as session:
  tf.global_variables_initializer().run()
  print("Initialized")
  for step in range(num_steps):
    # Pick an offset within the training data, which has been randomized.
    # Note: we could use better randomization across epochs.
    offset = (step * batch_size) % (train_labels.shape[0] - batch_size)
    #offset = (step * batch_size) % (3*128 - batch_size)
    #print(offset)
    # Generate a minibatch.
    batch_data = train_dataset[offset:(offset + batch_size), :]
    batch_labels = train_labels[offset:(offset + batch_size), :]
    # Prepare a dictionary telling the session where to feed the minibatch.
    # The key of the dictionary is the placeholder node of the graph to be fed,
    # and the value is the numpy array to feed to it.
    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 % 500 == 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("Test accuracy: %.1f%%" % accuracy(test_prediction.eval(), test_labels))

Answer 1

您需要在推理过程中关闭dropout。这可能在一开始并不明显，但dropout在NN体系结构中是硬编码的事实意味着它将在推理过程中影响测试数据。您可以通过创建占位符keep_prob而不是直接提供值0.5来避免这种情况。例如：

keep_prob = tf.placeholder(tf.float32)
logits = tf.nn.dropout(logits, keep_prob)

要在训练期间启用dropout，请将keep_prob值设置为0.5：

feed_dict = {tf_train_dataset : batch_data, tf_train_labels : batch_labels, keep_prob: 0.5}

在推断/评估过程中，您应该能够这样做，在eval中将keep_prob设置为1.0

accuracy.eval(feed_dict={x: test_prediction, y_: test_labels, keep_prob: 1.0}

编辑：

我实际上用你的代码试过了，在这个网络规模下，我得到了大约93.5%，20%的失落率。

参考文献：

• Deep MNIST for Experts：有一个使用MNIST
• Dropout Regularization in Deep Learning Models With Keras
• Dropout: A Simple Way to Prevent Neural Networks from Overfitting

的上述示例(dropout on /off

Answer 2

我认为有两件事会导致这个问题。

首先，我不建议在第一层中使用dropout (也就是50%，如果有必要的话，使用更低的，在10-25%的范围内)，因为当你使用如此高的dropout时，甚至更高级别的特征都不会被学习和传播到更深的层。也可以尝试从10%到50%的失落率范围，看看准确度是如何变化的。没有办法事先知道什么值是有效的。

其次，你通常不会在推理时使用dropout。将dropout的keep_prob参数中的传递修复为占位符，并在推断时将其设置为1。