ActivationConv¶
-
class
ActivationConv
(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, activation=None, **activation_kwargs)[source]¶ Bases:
sphinx.ext.autodoc.importer._MockObject
A combination of convolution with optional same-padding and arbitrary activation
See also
Conv2dWithSamePadding
Parameters: - in_channels (int) – channels of convolution input
- out_channels (int) – number of filters and output channes
- kernel_size (int or Iterable) – specifies the kernel dimensions. If int: same kernel size is used for all dimensions
- stride (int or Iterable, optional) – specifies the convolution strides (default: 1) If int: same stride is used for all dimensions
- padding (int or Iterable, optional) – specifies the input padding (default: 0) If int: same padding is used for all dimensions
- dilation (int or str or Iterable, optional) –
specifies the convolution dilation (default: 1) If int: same dilation is used for all dimensions If str: only supported string is ‘same’, which calculates the
necessary padding during forward - groups (int, optional) – number of convolution groups (default: 1)
- bias (bool, optional) – whether to include a bias or not (default: True)
- activation (str, optional) – the activation to apply; must be a valid name of module or function
in
torch.nn
ortorch.nn.functional
(the default is None, which won’t apply any activation)
-
forward
(input_tensor)[source]¶ convolves the input and applies activation afterwards
Parameters: input_tensor ( torch.Tensor
) – the input tensor to be convolvedReturns: tensor after convolution and activation Return type: torch.Tensor