MemSaveConvTranspose2d

class memsave_torch.nn.MemSaveConvTranspose2d(in_channels: int, out_channels: int, kernel_size: int | Tuple[int, int], stride: int | Tuple[int, int] = 1, padding: int | Tuple[int, int] = 0, output_padding: int | Tuple[int, int] = 0, groups: int = 1, bias: bool = True, dilation: int | Tuple[int, int] = 1, padding_mode: str = 'zeros', device=None, dtype=None)

Differentiability-agnostic 2d transpose convolution layer.

Initializes internal Module state, shared by both nn.Module and ScriptModule.

forward(input: Tensor) → Tensor

Forward pass.

Parameters:

input (torch.Tensor) – Input to the network [B, C_in, H, W]

Returns:

Output [B, C_out, H_out, W_out]

Return type:

torch.Tensor

classmethod from_nn_ConvTranspose2d(convT2d: ConvTranspose2d)

Converts a nn.ConvTranspose2d layer to MemSaveConvTranspose2d.

Parameters:

convT2d (nn.ConvTranspose2d) – The nn.ConvTranspose2d layer

Returns:

The MemSaveConvTranspose2d object

Return type:

MemSaveConvTranspose2d

Hint

The usage is the same as torch.nn.ConvTranspose2d

For usage examples, please refer to the linked torch documentation