Question

我正在尝试通过编辑retrain.py脚本在softmax图层之前将另一个FC图层添加到初始模型中。（tensorflow \例子\ image_retraining \ retrain.py）

因此输入将从2048变为1024而不是仅仅是2048

所以权重应该是：

（2048,1024）（1024，num_of_classes）

以下是我尝试添加额外图层的方法。我无法测试它此刻，所以我只是想确保我正确地做到了。我特别不确定cross_entropy部分，因为我希望它能使用 logits在其自己的范围内。我对tensorflow的工作原理还不太满意。

def add_final_training_ops(class_count, final_tensor_name, bottleneck_tensor,
                           bottleneck_tensor_size):
 """

  Args:
    class_count: Integer of how many categories of things we're trying to
    recognize.
    final_tensor_name: Name string for the new final node that produces results.
    bottleneck_tensor: The output of the main CNN graph.
    bottleneck_tensor_size: How many entries in the bottleneck vector.

  Returns:
    The tensors for the training and cross entropy results, and tensors for the
    bottleneck input and ground truth input.
  """
  with tf.name_scope('input'):
    bottleneck_input = tf.placeholder_with_default(
        bottleneck_tensor,
        shape=[None, bottleneck_tensor_size],
        name='BottleneckInputPlaceholder')


    ground_truth_input = tf.placeholder(tf.float32,
                                        [None, class_count],
                                        name='GroundTruthInput')


  layer_name = 'second_to_final_fC_layer_ops'
  with tf.name_scope(layer_name):
    with tf.name_scope('weights'):
      initial_value = tf.truncated_normal(
          [bottleneck_tensor_size, 1024], stddev=0.001)

      layer_weights = tf.Variable(initial_value, name='final_weights')

      variable_summaries(layer_weights)
    with tf.name_scope('biases'):
      layer_biases = tf.Variable(tf.zeros([1024]), name='final_biases')
      variable_summaries(layer_biases)
    with tf.name_scope('Wx_plus_b'):
      logits = tf.matmul(bottleneck_input, layer_weights) + layer_biases
      tf.summary.histogram('pre_activations', logits)
    with tf.name_scope('Relu_activation'):
      relu_activiated =tf.nn.relu(logits, name= 'Relu')
      tf.summary.histogram('final_relu_activation')


  layer_name = 'final_training_ops'
  with tf.name_scope(layer_name):
    with tf.name_scope('weights'):
      initial_value = tf.truncated_normal(
          [1024, class_count], stddev=0.001)

      layer_weights = tf.Variable(initial_value, name='final_weights')

      variable_summaries(layer_weights)
    with tf.name_scope('biases'):
      layer_biases = tf.Variable(tf.zeros([class_count]), name='final_biases')
      variable_summaries(layer_biases)
    with tf.name_scope('Wx_plus_b'):
      logits = tf.matmul(bottleneck_input, layer_weights) + layer_biases
      tf.summary.histogram('pre_activations', logits)

  final_tensor = tf.nn.softmax(logits, name=final_tensor_name)
  tf.summary.histogram('activations', final_tensor)


  with tf.name_scope('cross_entropy'):
    cross_entropy = tf.nn.softmax_cross_entropy_with_logits(
        labels=ground_truth_input, logits=logits)
    with tf.name_scope('total'):
      cross_entropy_mean = tf.reduce_mean(cross_entropy)
  tf.summary.scalar('cross_entropy', cross_entropy_mean)

  with tf.name_scope('train'):
    optimizer = tf.train.GradientDescentOptimizer(FLAGS.learning_rate)
    train_step = optimizer.minimize(cross_entropy_mean)

  return (train_step, cross_entropy_mean, bottleneck_input, ground_truth_input,
          final_tensor)

谢谢（只是加入@mrry）。

通过转移学习添加两个附加层以启动

0 个答案: