Conv2DTranspose

class dragon.vm.tensorflow.keras.layers.Conv2DTranspose(
  filters,
  kernel_size,
  strides=1, 1,
  padding='valid',
  output_padding=None,
  data_format=None,
  dilation_rate=1, 1,
  activation=None,
  use_bias=True,
  kernel_initializer='glorot_uniform',
  bias_initializer='zeros',
  kernel_regularizer=None,
  bias_regularizer=None,
  **kwargs
)[source]

The 2d deconvolution layer.

__init__

Conv2DTranspose.__init__(
  filters,
  kernel_size,
  strides=1, 1,
  padding='valid',
  output_padding=None,
  data_format=None,
  dilation_rate=1, 1,
  activation=None,
  use_bias=True,
  kernel_initializer='glorot_uniform',
  bias_initializer='zeros',
  kernel_regularizer=None,
  bias_regularizer=None,
  **kwargs
)[source]

Create a Conv2DTranspose Layer.

Parameters:
  • filters (int) – The number of output filters.
  • kernel_size (Sequence[int]) – The shape of convolution kernel.
  • strides (Sequence[int], optional) – The stride(s) of sliding window.
  • padding (Union[{'valid', 'same'}, Sequence[int]], optional) – The padding algorithm or padding sizes.
  • output_padding (Sequence[int], optional) – The sizes of padded to the output.
  • data_format ({'channels_first', 'channels_last'}, optional) – The optional data format.
  • dilation_rate (Sequence[int], optional) – The rate(s) of dilated kernel.
  • activation (Union[callable, str], optional) – The optional activation function.
  • use_bias (bool, optional, default=True) – True to apply a bias.
  • kernel_initializer (Union[callable, str], optional) – The initializer for kernel.
  • bias_initializer (Union[callable, str], optional) – The initializer for bias.
  • kernel_regularizer (Union[callable, str], optional) – The regularizer for kernel.
  • bias_regularizer (Union[callable, str], optional) – The regularizer for bias.