MemSaveConv2d

class memsave_torch.nn.MemSaveConv2d(in_channels: int, out_channels: int, kernel_size, stride=1, padding=0, dilation=1, groups: int = 1, bias: bool = True, padding_mode: str = 'zeros', device=None, dtype=None)

MemSaveConv2d.

Inits a Conv2d layer with the given params.

Parameters:

• in_channels – in_channels

• out_channels – out_channels

• kernel_size – kernel_size

• stride – stride

• padding – padding

• dilation – dilation

• groups – groups

• bias – bias

• padding_mode – padding_mode

• device – device

• dtype – dtype

forward(input: Tensor) → Tensor

Forward pass.

Parameters:

input – 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_Conv2d(conv2d: Conv2d)

Converts a nn.Conv2d layer to MemSaveConv2d.

Parameters:

conv2d – The nn.Conv2d layer

Returns:

The MemSaveConv2d object

Return type:

obj

Hint

The usage is the same as torch.nn.Conv2d

For usage examples, please refer to the linked torch documentation