aihwkit.nn.modules.conv module

Convolution layers.

class aihwkit.nn.modules.conv.AnalogConv1d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros', rpu_config=None, tile_module_class=None)

Bases: _AnalogConvNd

1D convolution layer that uses an analog tile.

Applies a 1D convolution over an input signal composed of several input planes, using an analog tile for its forward, backward and update passes.

Note

The tensor parameters of this layer (.weight and .bias) are not guaranteed to contain the same values as the internal weights and biases stored in the analog tile. Please use set_weights and get_weights when attempting to read or modify the weight/bias. This read/write process can simulate the (noisy and inexact) analog writing and reading of the resistive elements.

Parameters:

• in_channels (int) – number of channels in the input image.

• out_channels (int) – number of channels produced by the convolution.

• kernel_size (Tuple[int, ...]) – size of the convolving kernel.

• stride (Tuple[int, ...]) – stride of the convolution.

• padding (str | Tuple[int, ...]) – zero-padding added to both sides of the input.

• dilation (Tuple[int, ...]) – spacing between kernel elements.

• groups (int) – number of blocked connections from input channels to output channels.

• bias (Tensor | None) – whether to use a bias row on the analog tile or not.

• padding_mode (str) – padding strategy. Only 'zeros' is supported.

• rpu_config (RPUConfigBase | None) – resistive processing unit configuration.

• tile_module_class (Type | None) – Class for the tile module (default will be specified from the RPUConfig).

NEEDS_INDEXED = True

classmethod from_digital(module, rpu_config, tile_module_class=None)

Return an AnalogConv1d layer from a torch Conv1d layer.

Parameters:

• module (Conv1d) – The torch module to convert. All layers that are defined in the conversion_map.

• rpu_config (RPUConfigBase) – RPU config to apply to all converted tiles. Applied to all converted tiles.

• tile_module_class (Type | None) – Class for the tile module (default will be specified from the RPUConfig).

Returns:

an AnalogConv1d layer based on the digital Conv1d module.

Return type:

AnalogConv1d

get_tile_size(in_channels, groups, kernel_size)

Calculate the tile size.

Parameters:

• in_channels (int) –

• groups (int) –

• kernel_size (Tuple[int, ...]) –

Return type:

int

classmethod to_digital(module, realistic=False)

Return an nn.Conv1d layer from an AnalogConv1d layer.

Parameters:

• module (AnalogConv1d) – The analog module to convert.

• realistic (bool) – whehter to estimate the weights with the non-ideal forward pass. If not set, analog weights are (unrealistically) copies exactly

Returns:

an torch Linear layer with the same dimension and weights as the analog linear layer.

Return type:

Conv1d

class aihwkit.nn.modules.conv.AnalogConv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros', rpu_config=None, tile_module_class=None, use_indexed=None)

Bases: _AnalogConvNd

2D convolution layer that uses an analog tile.

Applies a 2D convolution over an input signal composed of several input planes, using an analog tile for its forward, backward and update passes.

Note

The tensor parameters of this layer (.weight and .bias) are not guaranteed to contain the same values as the internal weights and biases stored in the analog tile. Please use set_weights and get_weights when attempting to read or modify the weight/bias. This read/write process can simulate the (noisy and inexact) analog writing and reading of the resistive elements.

Parameters:

• in_channels (int) – number of channels in the input image.

• out_channels (int) – number of channels produced by the convolution.

• kernel_size (Tuple[int, ...]) – size of the convolving kernel.

• stride (Tuple[int, ...]) – stride of the convolution.

• padding (str | Tuple[int, ...]) – zero-padding added to both sides of the input.

• dilation (Tuple[int, ...]) – spacing between kernel elements.

• groups (int) – number of blocked connections from input channels to output channels.

• bias (Tensor | None) – whether to use a bias row on the analog tile or not.

• padding_mode (str) – padding strategy. Only 'zeros' is supported.

• rpu_config (RPUConfigBase | None) – resistive processing unit configuration.

• tile_module_class (Type | None) – Class for the tile module (default will be specified from the RPUConfig).

• use_indexed (bool | None) – Whether to use explicit unfolding or implicit indexing. If None (default), it will use implicit indexing for CUDA and explicit unfolding for CPU

classmethod from_digital(module, rpu_config, tile_module_class=None)

Return an AnalogConv2d layer from a torch Conv2d layer.

Parameters:

• module (Conv2d) – The torch module to convert. All layers that are defined in the conversion_map.

• rpu_config (RPUConfigBase) – RPU config to apply to all converted tiles. Applied to all converted tiles.

• tile_module_class (Type | None) – Class for the tile module (default will be specified from the RPUConfig).

Returns:

an AnalogConv2d layer based on the digital Conv2d module.

Return type:

AnalogConv2d

get_tile_size(in_channels, groups, kernel_size)

Calculate the tile size.

Parameters:

• in_channels (int) –

• groups (int) –

• kernel_size (Tuple[int, ...]) –

Return type:

int

classmethod to_digital(module, realistic=False)

Return an nn.Conv2d layer from an AnalogConv2d layer.

Parameters:

• module (AnalogConv2d) – The analog module to convert.

• realistic (bool) – whehter to estimate the weights with the non-ideal forward pass. If not set, analog weights are (unrealistically) copies exactly

Returns:

an torch Linear layer with the same dimension and weights as the analog linear layer.

Return type:

Conv2d

class aihwkit.nn.modules.conv.AnalogConv3d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros', rpu_config=None, tile_module_class=None)

Bases: _AnalogConvNd

3D convolution layer that uses an analog tile.

Applies a 3D convolution over an input signal composed of several input planes, using an analog tile for its forward, backward and update passes.

Note

The tensor parameters of this layer (.weight and .bias) are not guaranteed to contain the same values as the internal weights and biases stored in the analog tile. Please use set_weights and get_weights when attempting to read or modify the weight/bias. This read/write process can simulate the (noisy and inexact) analog writing and reading of the resistive elements.

Parameters:

• in_channels (int) – number of channels in the input image.

• out_channels (int) – number of channels produced by the convolution.

• kernel_size (Tuple[int, ...]) – size of the convolving kernel.

• stride (Tuple[int, ...]) – stride of the convolution.

• padding (str | Tuple[int, ...]) – zero-padding added to both sides of the input.

• dilation (Tuple[int, ...]) – spacing between kernel elements.

• groups (int) – number of blocked connections from input channels to output channels.

• bias (Tensor | None) – whether to use a bias row on the analog tile or not.

• padding_mode (str) – padding strategy. Only 'zeros' is supported.

• rpu_config (RPUConfigBase | None) – resistive processing unit configuration.

• tile_module_class (Type | None) – Class for the tile module (default will be specified from the RPUConfig).

NEEDS_INDEXED = True

classmethod from_digital(module, rpu_config, tile_module_class=None)

Return an AnalogConv3d layer from a torch Conv3d layer.

Parameters:

• module (Conv3d) – The torch module to convert. All layers that are defined in the conversion_map.

• rpu_config (RPUConfigBase) – RPU config to apply to all converted tiles. Applied to all converted tiles.

• tile_module_class (Type | None) – Class for the tile module (default will be specified from the RPUConfig).

Returns:

an AnalogConv3d layer based on the digital Conv3d module.

Return type:

AnalogConv3d

get_tile_size(in_channels, groups, kernel_size)

Calculate the tile size.

Parameters:

• in_channels (int) –

• groups (int) –

• kernel_size (Tuple[int, ...]) –

Return type:

int

classmethod to_digital(module, realistic=False)

Return an nn.Conv3d layer from an AnalogConv3d layer.

Parameters:

• module (AnalogConv3d) – The analog module to convert.

• realistic (bool) – whehter to estimate the weights with the non-ideal forward pass. If not set, analog weights are (unrealistically) copies exactly

Returns:

an torch Linear layer with the same dimension and weights as the analog linear layer.

Return type:

Conv3d