理工酷

我正在学习ANN，它是Udacity DeepLearning课程的一部分。

我的一项作业涉及使用L2损失将泛化引入具有一个隐藏ReLU层的网络。我想知道如何正确地引入它，以便所有权重都受到惩罚，而不仅仅是输出层的权重。 没有泛化的网络代码在下面。

引入L2的一种明显方法是将损失计算替换为以下内容（如果beta为0.01）：

loss = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(out_layer, tf_train_labels) + 0.01*tf.nn.l2_loss(out_weights))

但是在这种情况下，它将考虑输出层权重的值。我们如何适当地惩罚进入隐藏的ReLU层的权重，还是对输出层进行惩罚会以某种方式控制隐藏权重？

#some importingfrom __future__ import print_functionimport numpy as npimport tensorflow as tffrom six.moves import cPickle as picklefrom six.moves import range
#loading data
pickle_file = '/home/maxkhk/Documents/Udacity/DeepLearningCourse/SourceCode/tensorflow/examples/udacity/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)

#prepare data to have right format for tensorflow#i.e. data is flat matrix, labels are onehot

image_size = 28
num_labels = 10
def reformat(dataset, labels):
  dataset = dataset.reshape((-1, image_size * image_size)).astype(np.float32)
  # Map 0 to [1.0, 0.0, 0.0 ...], 1 to [0.0, 1.0, 0.0 ...]
  labels = (np.arange(num_labels) == labels[:,None]).astype(np.float32)
  return dataset, labels
train_dataset, train_labels = reformat(train_dataset, train_labels)
valid_dataset, valid_labels = reformat(valid_dataset, valid_labels)
test_dataset, test_labels = reformat(test_dataset, test_labels)
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)

#now is the interesting part - we are building a network with#one hidden ReLU layer and out usual output linear layer
#we are going to use SGD so here is our size of batch
batch_size = 128
#building tensorflow graph
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)

  #now let's build our new hidden layer
  #that's how many hidden neurons we want
  num_hidden_neurons = 1024
  #its weights
  hidden_weights = tf.Variable(
    tf.truncated_normal([image_size * image_size, num_hidden_neurons]))
  hidden_biases = tf.Variable(tf.zeros([num_hidden_neurons]))

  #now the layer itself. It multiplies data by weights, adds biases
  #and takes ReLU over result
  hidden_layer = tf.nn.relu(tf.matmul(tf_train_dataset, hidden_weights) + hidden_biases)

  #time to go for output linear layer
  #out weights connect hidden neurons to output labels
  #biases are added to output labels  
  out_weights = tf.Variable(
    tf.truncated_normal([num_hidden_neurons, num_labels]))  

  out_biases = tf.Variable(tf.zeros([num_labels]))  

  #compute output  
  out_layer = tf.matmul(hidden_layer,out_weights) + out_biases
  #our real output is a softmax of prior result
  #and we also compute its cross-entropy to get our loss
  loss = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(out_layer, tf_train_labels))

  #now we just minimize this loss to actually train the network
  optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss)

  #nice, now let's calculate the predictions on each dataset for evaluating the
  #performance so far
  # Predictions for the training, validation, and test data.
  train_prediction = tf.nn.softmax(out_layer)
  valid_relu = tf.nn.relu(  tf.matmul(tf_valid_dataset, hidden_weights) + hidden_biases)
  valid_prediction = tf.nn.softmax( tf.matmul(valid_relu, out_weights) + out_biases) 

  test_relu = tf.nn.relu( tf.matmul( tf_test_dataset, hidden_weights) + hidden_biases)
  test_prediction = tf.nn.softmax(tf.matmul(test_relu, out_weights) + out_biases)