conv2d_transpose

dragon.vm.tensorflow.nn.conv2d_transpose(
  input,
  filters,
  output_shape=None,
  strides=1,
  padding='SAME',
  output_padding=None,
  data_format='NHWC',
  dilations=None,
  name=None
)[source]

Apply the 2d deconvolution.

  • If data_format is 'NCHW', excepts input shape \((N, C_{\text{in}}, H, W)\), filters shape \((C_{\text{in}}, C_{\text{out}}, H_{\text{f}}, W_{\text{f}})\), and output shape is \((N, C_{\text{out}}, H_{\text{out}}, W_{\text{out}})\).
  • If data_format is 'NHWC', excepts input shape \((N, H, W, C_{\text{in}})\), filters shape \((C_{\text{in}}, H_{\text{f}}, W_{\text{f}}, C_{\text{out}})\), and output shape is \((N, H_{\text{out}}, W_{\text{out}}, C_{\text{out}})\).
  • padding could be 'VALID', 'SAME' or explicit padding size.

Examples:

x = tf.ones((1, 2, 2, 2))
filters = tf.ones((3, 1, 1, 2))
y = tf.nn.conv2d_transpose(x, filters, output_shape=(2, 2))
assert y.shape == (1, 2, 2, 3)
Parameters:
  • input (dragon.Tensor) The input tensor.
  • filters (dragon.Tensor) The filters tensor.
  • output_shape (Union[Sequence[int], dragon.Tensor], optional) The optional output shape.
  • strides (Union[int, Sequence[int]], default=1) The stride of convolution window.
  • padding (Union[int, Sequence[int], str]) The padding algorithm or size.
  • output_padding (Union[Sequence[int], dragon.Tensor], optional) The additional size added to the output shape.
  • data_format (str, optional, default='NHWC') 'NCHW' or 'NHWC'.
  • dilations (Union[int, Sequence[int]], optional, default=1) The rate of dilated filters.
  • name (str, optional) The operation name.
Returns:

dragon.Tensor The output tensor.