MemSaveConvTranspose3d¶

class memsave_torch.nn.MemSaveConvTranspose3d(in_channels: int, out_channels: int, kernel_size: int | Tuple[int, int, int], stride: int | Tuple[int, int, int] = 1, padding: int | Tuple[int, int, int] = 0, output_padding: int | Tuple[int, int, int] = 0, groups: int = 1, bias: bool = True, dilation: int | Tuple[int, int, int] = 1, padding_mode: str = 'zeros', device=None, dtype=None)¶

Differentiability-agnostic 3d 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, D, H, W]
Returns:: Output [B, C_out, D_out, H_out, W_out]
Return type:: torch.Tensor

classmethod from_nn_ConvTranspose3d(convT3d: ConvTranspose3d)¶

Converts a nn.ConvTranspose3d layer to MemSaveConvTranspose3d.

Parameters:: convT3d (nn.ConvTranspose3d) – The nn.ConvTranspose3d layer
Returns:: The MemSaveConvTranspose3d object
Return type:: MemSaveConvTranspose3d

Hint

For usage examples, please refer to the linked torch documentation