Question

我正在尝试完成以下张量流教程和（尝试问题4）：https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/udacity/3_regularization.ipynb

但是，我想我可能会将权重数组设置为错误。只要我将hidden_layer更改为[image_size * image_size,1024,num_labels]（即只有一个隐藏图层），就可以正常使用。目前我得到了NaN的损失。

一个可能的解决方案就是该块 for i in range(1,len(weights)-1): relus = tf.nn.dropout(tf.nn.relu(tf.matmul(relus, weights[i]) + biases[i]),p_hide) 由于我正在破坏relus的过去价值而神经网络需要他们进行反向传播，因此导致问题。实际上，当存在一个隐藏层时，该块不会被执行。

batch_size = 128
hidden_layer = [image_size * image_size,1024,300,num_labels]
l2_regulariser = 0.005
p_hide = 0.5

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 = [None]*(len(hidden_layer)-1)
    biases = [None]*(len(hidden_layer)-1)
    for i in range(len(weights)):
        weights[i] = tf.Variable(tf.truncated_normal([hidden_layer[i], hidden_layer[i+1]]))
        biases[i] = tf.Variable(tf.zeros([hidden_layer[i+1]]))

    # Training computation.
    relus = tf.nn.dropout(tf.nn.relu(tf.matmul(tf_train_dataset, weights[0]) + biases[0]),p_hide)
    for i in range(1,len(weights)-1):
        relus = tf.nn.dropout(tf.nn.relu(tf.matmul(relus, weights[i]) + biases[i]),p_hide)
    logits = tf.matmul(relus, weights[len(weights)-1]) + biases[len(weights)-1]

    loss = 0
    for weight in weights:
        loss += tf.nn.l2_loss(weight)

    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits, tf_train_labels))+ l2_regulariser*loss


    # Optimizer.
    global_step = tf.Variable(0)  # count the number of steps taken.
    learning_rate = tf.train.exponential_decay(0.5, global_step, decay_steps=20, decay_rate=0.9)
    optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss)  


    # Predictions for the training, validation, and test data.
    train_prediction = tf.nn.softmax(logits)

    relus = tf.nn.relu(tf.matmul(tf_valid_dataset, weights[0]) + biases[0])
    for i in range(1,len(weights)-1):
        relus = tf.nn.relu(tf.matmul(relus, weights[i]) + biases[i])
    valid_prediction = tf.nn.softmax(tf.matmul(relus, weights[len(weights)-1]) + biases[len(weights)-1])

    relus = tf.nn.relu(tf.matmul(tf_test_dataset, weights[0]) + biases[0])
    for i in range(1,len(weights)-1):
        relus = tf.nn.relu(tf.matmul(relus, weights[i]) + biases[i])
    test_prediction = tf.nn.softmax(tf.matmul(relus, weights[len(weights)-1]) + biases[len(weights)-1])

######################
# The NN training part
######################
num_steps = 3001

with tf.Session(graph=graph) as session:
  tf.initialize_all_variables().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)
    # 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, global_step : int(step)}
    _, 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

你最好初始化你的体重：

tf.truncated_normal([hidden_layer[i], hidden_layer[i+1]], stddev=0.1)

最重要的是，你应该将学习率降低到0.01，0.001 ...

附近

我认为你会失去NaN，因为学习率太高而且会打破网络（你的体重会爆炸）。

多级神经网络

1 个答案: