mobilenet_v1.py 文件源码

def separable_conv2d_same(inputs, kernel_size, stride, rate=1, scope=None):
  """Strided 2-D separable convolution with 'SAME' padding.
  Args:
    inputs: A 4-D tensor of size [batch, height_in, width_in, channels].
    kernel_size: An int with the kernel_size of the filters.
    stride: An integer, the output stride.
    rate: An integer, rate for atrous convolution.
    scope: Scope.
  Returns:
    output: A 4-D tensor of size [batch, height_out, width_out, channels] with
      the convolution output.
  """

  # By passing filters=None
  # separable_conv2d produces only a depth-wise convolution layer
  if stride == 1:
    return slim.separable_conv2d(inputs, None, kernel_size, 
                                  depth_multiplier=1, stride=1, rate=rate,
                                  padding='SAME', scope=scope)
  else:
    kernel_size_effective = kernel_size + (kernel_size - 1) * (rate - 1)
    pad_total = kernel_size_effective - 1
    pad_beg = pad_total // 2
    pad_end = pad_total - pad_beg
    inputs = tf.pad(inputs,
                    [[0, 0], [pad_beg, pad_end], [pad_beg, pad_end], [0, 0]])
    return slim.separable_conv2d(inputs, None, kernel_size, 
                                  depth_multiplier=1, stride=stride, rate=rate, 
                                  padding='VALID', scope=scope)

# The following is adapted from:
# https://github.com/tensorflow/models/blob/master/slim/nets/mobilenet_v1.py

# Conv and DepthSepConv named tuple define layers of the MobileNet architecture
# Conv defines 3x3 convolution layers
# DepthSepConv defines 3x3 depthwise convolution followed by 1x1 convolution.
# stride is the stride of the convolution
# depth is the number of channels or filters in a layer