tesnorflow Conv2DTranspose

tensorflow/python/layers/convolutional.py   
  # Infer the dynamic output shape:
    out_height = utils.deconv_output_length(height,
                                            kernel_h,
                                            self.padding,
                                            stride_h)
    out_width = utils.deconv_output_length(width,
                                           kernel_w,
                                           self.padding,
                                           stride_w)
    if self.data_format == 'channels_first':
      output_shape = (batch_size, self.filters, out_height, out_width)
      strides = (1, 1, stride_h, stride_w)
    else:
      output_shape = (batch_size, out_height, out_width, self.filters)
      strides = (1, stride_h, stride_w, 1)

    output_shape_tensor = array_ops.stack(output_shape)
    outputs = nn.conv2d_transpose(
        inputs,
        self.kernel,
        output_shape_tensor,
        strides,
        padding=self.padding.upper(),
        data_format=utils.convert_data_format(self.data_format, ndim=4))

/tensorflow/python/layers/utils.py
def deconv_output_length(input_length, filter_size, padding, stride):
  """Determines output length of a transposed convolution given input length.
  Arguments:
      input_length: integer.
      filter_size: integer.
      padding: one of "same", "valid", "full".
      stride: integer.
  Returns:
      The output length (integer).
  """
  if input_length is None:
    return None
  input_length *= stride
  if padding == 'valid':
    input_length += max(filter_size - stride, 0)
  elif padding == 'full':
    input_length -= (stride + filter_size - 2)
  return input_length

　　

注意 deconv中的kernel 是需要rotate 180度 才直接相乘的，而conv中不用旋转直接相乘。