ml4gw.nn.resnet.resnet_2d

In large part lifted from https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py but with arbitrary kernel sizes

Functions

conv1(in_planes, out_planes[, stride])

Kernel-size 1 convolution

convN(in_planes, out_planes[, kernel_size, ...])

2d convolution with padding

Classes

BasicBlock(inplanes, planes[, kernel_size, ...])

Defines the structure of the blocks used to build the ResNet

Bottleneck(inplanes, planes[, kernel_size, ...])

Bottleneck blocks implement one extra convolution compared to basic blocks.

BottleneckResNet2D(in_channels, layers, classes)

A version of ResNet that uses bottleneck blocks

ResNet2D(in_channels, layers, classes[, ...])

2D ResNet architecture
class ml4gw.nn.resnet.resnet_2d.BasicBlock(inplanes, planes, kernel_size=3, stride=1, downsample=None, groups=1, base_width=64, dilation=1, norm_layer=None)

Bases: Module

Defines the structure of the blocks used to build the ResNet

Parameters:

  • inplanes (int)

  • planes (int)

  • kernel_size (int)

  • stride (int)

  • downsample (Module | None)

  • groups (int)

  • base_width (int)

  • dilation (int)

  • norm_layer (Callable[[...], Module] | None)

expansion: int = 1
forward(x)
Return type:

Tensor

Parameters:

x (Tensor)

class ml4gw.nn.resnet.resnet_2d.Bottleneck(inplanes, planes, kernel_size=3, stride=1, downsample=None, groups=1, base_width=64, dilation=1, norm_layer=None)

Bases: Module

Bottleneck blocks implement one extra convolution compared to basic blocks. In this layers, the planes parameter is generally meant to _downsize_ the number of feature maps first, which then get expanded out to planes * Bottleneck.expansion feature maps at the output of the layer.

Parameters:

  • inplanes (int)

  • planes (int)

  • kernel_size (int)

  • stride (int)

  • downsample (Module | None)

  • groups (int)

  • base_width (int)

  • dilation (int)

  • norm_layer (Callable[[...], Module] | None)

expansion: int = 4
forward(x)
Return type:

Tensor

Parameters:

x (Tensor)

class ml4gw.nn.resnet.resnet_2d.BottleneckResNet2D(in_channels, layers, classes, kernel_size=3, zero_init_residual=False, groups=1, width_per_group=64, stride_type=None, norm_layer=None)

Bases: ResNet2D

A version of ResNet that uses bottleneck blocks

Parameters:

  • in_channels (int)

  • layers (List[int])

  • classes (int)

  • kernel_size (int)

  • zero_init_residual (bool)

  • groups (int)

  • width_per_group (int)

  • stride_type (List[Literal['stride', 'dilation']] | None)

  • norm_layer (Callable[[int], Module] | None)

block

alias of Bottleneck

class ml4gw.nn.resnet.resnet_2d.ResNet2D(in_channels, layers, classes, kernel_size=3, zero_init_residual=False, groups=1, width_per_group=64, stride_type=None, norm_layer=None)

Bases: Module

2D ResNet architecture

Simple extension of ResNet with arbitrary kernel sizes to support the longer timeseries used in BBH detection.

Parameters:

  • in_channels (int) -- The number of channels in input tensor.

  • layers (List[int]) -- A list representing the number of residual blocks to include in each "layer" of the network. Total layers (e.g. 50 in ResNet50) is 2 + sum(layers) * factor, where factor is 2 for vanilla ResNet and 3 for BottleneckResNet.

  • kernel_size (int) -- The size of the convolutional kernel to use in all residual layers. _NOT_ the size of the input kernel to the network, which is determined at run-time.

  • zero_init_residual (bool) -- Flag indicating whether to initialize the weights of the batch-norm layer in each block to 0 so that residuals are initialized as identities. Can improve training results.

  • groups (int) -- Number of convolutional groups to use in all layers. Grouped convolutions induce local connections between feature maps at subsequent layers rather than global. Generally won't need this to be >1, and wil raise an error if >1 when using vanilla ResNet.

  • width_per_group (int) -- Base width of each of the feature map groups, which is scaled up by the typical expansion factor at each layer of the network. Meaningless for vanilla ResNet.

  • stride_type (Optional[List[Literal['stride', 'dilation']]]) -- Whether to achieve downsampling on the time axis by strided or dilated convolutions for each layer. If left as None, strided convolutions will be used at each layer. Otherwise, stride_type should be one element shorter than layers and indicate either stride or dilation for each layer after the first.

  • norm_groups -- The number of groups to use in GroupNorm layers throughout the model. If left as -1, the number of groups will be equal to the number of channels, making this equilavent to LayerNorm

  • classes (int)

  • norm_layer (Callable[[int], Module] | None)

block

alias of BasicBlock

forward(x)
Return type:

Tensor

Parameters:

x (Tensor)

ml4gw.nn.resnet.resnet_2d.conv1(in_planes, out_planes, stride=1)

Kernel-size 1 convolution

Return type:

Conv2d

Parameters:

  • in_planes (int)

  • out_planes (int)

  • stride (int)

ml4gw.nn.resnet.resnet_2d.convN(in_planes, out_planes, kernel_size=3, stride=1, groups=1, dilation=1)

2d convolution with padding

Return type:

Conv2d

Parameters:

  • in_planes (int)

  • out_planes (int)

  • kernel_size (int)

  • stride (int)

  • groups (int)

  • dilation (int)