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, realistic_read_write=False, weight_scaling_omega=None)

Bases: aihwkit.nn.modules.conv._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 (Union[int, Tuple]) – size of the convolving kernel.

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

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

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

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

• bias (bool) – whether to use a bias row on the analog tile or not.

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

• rpu_config (Optional[Union[FloatingPointRPUConfig, SingleRPUConfig, UnitCellRPUConfig, InferenceRPUConfig, DigitalRankUpdateRPUConfig]]) – resistive processing unit configuration.

• realistic_read_write (bool) – whether to enable realistic read/write for setting initial weights and during reading of the weights.

• weight_scaling_omega (Optional[bool]) – depreciated, use aihwkit.simulator.configs.utils.MappingParameter instead to specify weight scaling

analog_bias: bool

digital_bias: bool

dilation: Tuple[int, ...]

fold_indices: torch.Tensor

classmethod from_digital(module, rpu_config=None, realistic_read_write=False)

Return an AnalogConv1d layer from a torch Conv1d layer.

Parameters

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

• rpu_config (Optional[Union[FloatingPointRPUConfig, SingleRPUConfig, UnitCellRPUConfig, InferenceRPUConfig, DigitalRankUpdateRPUConfig]]) – RPU config to apply to all converted tiles. Applied to all converted tiles.

• realistic_read_write (bool) –

  Whether to use closed-loop programming when setting the weights. Applied to all converted tiles.

  Note

  Make sure that the weight max and min settings of the device support the desired analog weight range.

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

groups: int

in_channels: int

in_features: int

input_size: float

kernel_size: Tuple[int, ...]

out_channels: int

out_features: int

output_padding: Tuple[int, ...]

padding: Tuple[int, ...]

padding_mode: str

realistic_read_write: bool

stride: Tuple[int, ...]

transposed: bool

use_bias: bool

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, realistic_read_write=False, weight_scaling_omega=None, use_indexed=None)

Bases: aihwkit.nn.modules.conv._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 (Union[int, Tuple]) – size of the convolving kernel.

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

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

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

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

• bias (bool) – whether to use a bias row on the analog tile or not.

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

• rpu_config (Optional[Union[FloatingPointRPUConfig, SingleRPUConfig, UnitCellRPUConfig, InferenceRPUConfig, DigitalRankUpdateRPUConfig]]) – resistive processing unit configuration.

• realistic_read_write (bool) – whether to enable realistic read/write for setting initial weights and read out of weights.

• weight_scaling_omega (Optional[bool]) – depreciated, use aihwkit.simulator.configs.utils.MappingParameter instead to specify weight scaling

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

analog_bias: bool

digital_bias: bool

dilation: Tuple[int, ...]

fold_indices: torch.Tensor

classmethod from_digital(module, rpu_config=None, realistic_read_write=False)

Return an AnalogConv2d layer from a torch Conv2d layer.

Parameters

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

• rpu_config (Optional[Union[FloatingPointRPUConfig, SingleRPUConfig, UnitCellRPUConfig, InferenceRPUConfig, DigitalRankUpdateRPUConfig]]) – RPU config to apply to all converted tiles. Applied to all converted tiles.

• realistic_read_write (bool) –

  Whether to use closed-loop programming when setting the weights. Applied to all converted tiles.

  Note

  Make sure that the weight max and min settings of the device support the desired analog weight range.

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

groups: int

in_channels: int

in_features: int

input_size: float

kernel_size: Tuple[int, ...]

out_channels: int

out_features: int

output_padding: Tuple[int, ...]

padding: Tuple[int, ...]

padding_mode: str

realistic_read_write: bool

stride: Tuple[int, ...]

transposed: bool

use_bias: bool

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, realistic_read_write=False, weight_scaling_omega=None)

Bases: aihwkit.nn.modules.conv._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 (Union[int, Tuple]) – size of the convolving kernel.

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

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

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

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

• bias (bool) – whether to use a bias row on the analog tile or not.

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

• rpu_config (Optional[Union[FloatingPointRPUConfig, SingleRPUConfig, UnitCellRPUConfig, InferenceRPUConfig, DigitalRankUpdateRPUConfig]]) – resistive processing unit configuration.

• realistic_read_write (bool) – whether to enable realistic read/write for setting initial weights and read out of weights.

• weight_scaling_omega (Optional[bool]) – depreciated, use aihwkit.simulator.configs.utils.MappingParameter instead to specify weight scaling

analog_bias: bool

digital_bias: bool

dilation: Tuple[int, ...]

fold_indices: torch.Tensor

classmethod from_digital(module, rpu_config=None, realistic_read_write=False)

Return an AnalogConv3d layer from a torch Conv3d layer.

Parameters

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

• rpu_config (Optional[Union[FloatingPointRPUConfig, SingleRPUConfig, UnitCellRPUConfig, InferenceRPUConfig, DigitalRankUpdateRPUConfig]]) – RPU config to apply to all converted tiles. Applied to all converted tiles.

• realistic_read_write (bool) –

  Whether to use closed-loop programming when setting the weights. Applied to all converted tiles.

  Note

  Make sure that the weight max and min settings of the device support the desired analog weight range.

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

groups: int

in_channels: int

in_features: int

input_size: float

kernel_size: Tuple[int, ...]

out_channels: int

out_features: int

output_padding: Tuple[int, ...]

padding: Tuple[int, ...]

padding_mode: str

realistic_read_write: bool

stride: Tuple[int, ...]

transposed: bool

use_bias: bool