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)[source]

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 – number of channels in the input image.

  • out_channels – number of channels produced by the convolution.

  • kernel_size – size of the convolving kernel.

  • stride – stride of the convolution.

  • padding – zero-padding added to both sides of the input.

  • dilation – spacing between kernel elements.

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

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

  • padding_mode – padding strategy. Only 'zeros' is supported.

  • rpu_config – resistive processing unit configuration.

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

  • weight_scaling_omega – If non-zero, the analog weights will be scaled by weight_scaling_omega divided by the absolute maximum value of the original weight matrix.

analog_bias
digital_bias
dilation
fold_indices
classmethod from_digital(module, rpu_config=None, realistic_read_write=False)[source]

Return an AnalogConv1d layer from a torch Conv1d layer.

Parameters
Returns

an AnalogConv1d layer based on the digital Conv1d module.

Return type

aihwkit.nn.modules.conv.AnalogConv1d

get_tensor_view(tensor_to_view)[source]

Return the correct view to the input tensor.

Parameters

tensor_to_view (torch.Tensor) – tensor to modify view of

Returns

tensor_to_view with correct view

Return type

tensor

get_tile_size(in_channels, groups, kernel_size)[source]

Calculate the tile size.

Parameters

  • in_channels (int) –

  • groups (int) –

  • kernel_size (Tuple[int, ..]) –

Return type

int

groups
in_channels
in_features
input_size
kernel_size
out_channels
out_features
output_padding
padding
padding_mode
realistic_read_write
stride
transposed
use_bias
weight_scaling_omega
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)[source]

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 – number of channels in the input image.

  • out_channels – number of channels produced by the convolution.

  • kernel_size – size of the convolving kernel.

  • stride – stride of the convolution.

  • padding – zero-padding added to both sides of the input.

  • dilation – spacing between kernel elements.

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

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

  • padding_mode – padding strategy. Only 'zeros' is supported.

  • rpu_config – resistive processing unit configuration.

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

  • weight_scaling_omega – If non-zero, the analog weights will be scaled by weight_scaling_omega divided by the absolute maximum value of the original weight matrix.

analog_bias
digital_bias
dilation
fold_indices
classmethod from_digital(module, rpu_config=None, realistic_read_write=False)[source]

Return an AnalogConv2d layer from a torch Conv2d layer.

Parameters
Returns

an AnalogConv2d layer based on the digital Conv2d module.

Return type

aihwkit.nn.modules.conv.AnalogConv2d

get_tensor_view(tensor_to_view)[source]

Return the correct view to the input tensor.

Parameters

tensor_to_view (torch.Tensor) – tensor to modify view of

Returns

tensor_to_view with correct view

Return type

tensor

get_tile_size(in_channels, groups, kernel_size)[source]

Calculate the tile size.

Parameters

  • in_channels (int) –

  • groups (int) –

  • kernel_size (Tuple[int, ..]) –

Return type

int

groups
in_channels
in_features
input_size
kernel_size
out_channels
out_features
output_padding
padding
padding_mode
realistic_read_write
stride
transposed
use_bias
weight_scaling_omega
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)[source]

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 – number of channels in the input image.

  • out_channels – number of channels produced by the convolution.

  • kernel_size – size of the convolving kernel.

  • stride – stride of the convolution.

  • padding – zero-padding added to both sides of the input.

  • dilation – spacing between kernel elements.

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

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

  • padding_mode – padding strategy. Only 'zeros' is supported.

  • rpu_config – resistive processing unit configuration.

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

  • weight_scaling_omega – If non-zero, the analog weights will be scaled by weight_scaling_omega divided by the absolute maximum value of the original weight matrix.

analog_bias
digital_bias
dilation
fold_indices
classmethod from_digital(module, rpu_config=None, realistic_read_write=False)[source]

Return an AnalogConv3d layer from a torch Conv3d layer.

Parameters
Returns

an AnalogConv3d layer based on the digital Conv3d module.

Return type

aihwkit.nn.modules.conv.AnalogConv3d

get_tensor_view(tensor_to_view)[source]

Return the correct view to the input tensor.

Parameters

tensor_to_view (torch.Tensor) – tensor to modify view of

Returns

tensor_to_view with correct view

Return type

tensor

get_tile_size(in_channels, groups, kernel_size)[source]

Calculate the tile size.

Parameters

  • in_channels (int) –

  • groups (int) –

  • kernel_size (Tuple[int, ..]) –

Return type

int

groups
in_channels
in_features
input_size
kernel_size
out_channels
out_features
output_padding
padding
padding_mode
realistic_read_write
stride
transposed
use_bias
weight_scaling_omega