hxtorch.perceptron.nn.Conv2d

class hxtorch.perceptron.nn.Conv2d(in_channels: numbers.Integral, out_channels: numbers.Integral, kernel_size: Union[numbers.Integral, Tuple[numbers.Integral, numbers.Integral]], stride: numbers.Integral = 1, padding: Union[numbers.Integral, Tuple[numbers.Integral, numbers.Integral]] = 0, dilation: numbers.Integral = 1, groups: numbers.Integral = 1, bias: bool = True, padding_mode: str = 'zeros', num_sends: Optional[numbers.Integral, None] = None, wait_between_events: numbers.Integral = 5, mock: bool = False, *, input_transform: Optional[Callable[[torch.Tensor], torch.Tensor], None] = None, weight_transform: Optional[Callable[[torch.Tensor], torch.Tensor], None] = <function clamp_weight_>)

Bases: hxtorch.perceptron.nn.ConvNd, torch.nn.modules.conv.Conv2d

Applies a 2D convolution over an input image composed of several input planes.

__init__(in_channels: numbers.Integral, out_channels: numbers.Integral, kernel_size: Union[numbers.Integral, Tuple[numbers.Integral, numbers.Integral]], stride: numbers.Integral = 1, padding: Union[numbers.Integral, Tuple[numbers.Integral, numbers.Integral]] = 0, dilation: numbers.Integral = 1, groups: numbers.Integral = 1, bias: bool = True, padding_mode: str = 'zeros', num_sends: Optional[numbers.Integral, None] = None, wait_between_events: numbers.Integral = 5, mock: bool = False, *, input_transform: Optional[Callable[[torch.Tensor], torch.Tensor], None] = None, weight_transform: Optional[Callable[[torch.Tensor], torch.Tensor], None] = <function clamp_weight_>)
Parameters

  • in_channels – Number of channels in the input

  • 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

  • padding_mode – ‘zeros’, ‘reflect’, ‘replicate’ or ‘circular’

  • dilation – Spacing between kernel elements

  • groups – Number of blocked connections from input channels to output channels

  • bias – If True, adds a learnable bias to the output

  • num_sends – Number of sends of the input. Values greater than 1 result in higher output to the neurons and increases the s/n ratio. For None this is automatically adjusted during initialization.

  • mock – Enable mock mode.

  • wait_between_events – Wait time between two successive vector inputs, in FPGA clock cycles. Shorter wait time can lead to saturation of the synaptic input.

  • input_transform – Function that receives the input and returns a tensor to be used as input to the chip.

  • weight_transform – Function that receives the weight and returns a tensor to be used as weight matrix on the chip.

Methods

__init__(in_channels, out_channels, kernel_size)

param in_channels

Number of channels in the input

Attributes