spikingjelly.clock_driven.ann2snn.examples.model_sample.imagenet package

Submodules

spikingjelly.clock_driven.ann2snn.examples.model_sample.imagenet.resnet module

class spikingjelly.clock_driven.ann2snn.examples.model_sample.imagenet.resnet.ResNet(block, layers, num_classes=1000, zero_init_residual=False, groups=1, width_per_group=64, replace_stride_with_dilation=None, norm_layer=None)[源代码]

基类：torch.nn.modules.module.Module

forward(x)[源代码]
training: bool
spikingjelly.clock_driven.ann2snn.examples.model_sample.imagenet.resnet.resnet18(pretrained=False, progress=True, **kwargs)[源代码]

ResNet-18 model from “Deep Residual Learning for Image Recognition”

参数

  • pretrained (bool) – If True, returns a model pre-trained on ImageNet

  • progress (bool) – If True, displays a progress bar of the download to stderr

spikingjelly.clock_driven.ann2snn.examples.model_sample.imagenet.resnet.resnet34(pretrained=False, progress=True, **kwargs)[源代码]

ResNet-34 model from “Deep Residual Learning for Image Recognition”

参数

  • pretrained (bool) – If True, returns a model pre-trained on ImageNet

  • progress (bool) – If True, displays a progress bar of the download to stderr

spikingjelly.clock_driven.ann2snn.examples.model_sample.imagenet.resnet.resnet50(pretrained=False, progress=True, **kwargs)[源代码]

ResNet-50 model from “Deep Residual Learning for Image Recognition”

参数

  • pretrained (bool) – If True, returns a model pre-trained on ImageNet

  • progress (bool) – If True, displays a progress bar of the download to stderr

spikingjelly.clock_driven.ann2snn.examples.model_sample.imagenet.resnet.resnet101(pretrained=False, progress=True, **kwargs)[源代码]

ResNet-101 model from “Deep Residual Learning for Image Recognition”

参数

  • pretrained (bool) – If True, returns a model pre-trained on ImageNet

  • progress (bool) – If True, displays a progress bar of the download to stderr

spikingjelly.clock_driven.ann2snn.examples.model_sample.imagenet.resnet.resnet152(pretrained=False, progress=True, **kwargs)[源代码]

ResNet-152 model from “Deep Residual Learning for Image Recognition”

参数

  • pretrained (bool) – If True, returns a model pre-trained on ImageNet

  • progress (bool) – If True, displays a progress bar of the download to stderr

spikingjelly.clock_driven.ann2snn.examples.model_sample.imagenet.resnet.resnext50_32x4d(pretrained=False, progress=True, **kwargs)[源代码]

ResNeXt-50 32x4d model from “Aggregated Residual Transformation for Deep Neural Networks”

参数

  • pretrained (bool) – If True, returns a model pre-trained on ImageNet

  • progress (bool) – If True, displays a progress bar of the download to stderr

spikingjelly.clock_driven.ann2snn.examples.model_sample.imagenet.resnet.resnext101_32x8d(pretrained=False, progress=True, **kwargs)[源代码]

ResNeXt-101 32x8d model from “Aggregated Residual Transformation for Deep Neural Networks”

参数

  • pretrained (bool) – If True, returns a model pre-trained on ImageNet

  • progress (bool) – If True, displays a progress bar of the download to stderr

spikingjelly.clock_driven.ann2snn.examples.model_sample.imagenet.resnet.wide_resnet50_2(pretrained=False, progress=True, **kwargs)[源代码]

Wide ResNet-50-2 model from “Wide Residual Networks”

The model is the same as ResNet except for the bottleneck number of channels which is twice larger in every block. The number of channels in outer 1x1 convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048 channels, and in Wide ResNet-50-2 has 2048-1024-2048.

参数

  • pretrained (bool) – If True, returns a model pre-trained on ImageNet

  • progress (bool) – If True, displays a progress bar of the download to stderr

spikingjelly.clock_driven.ann2snn.examples.model_sample.imagenet.resnet.wide_resnet101_2(pretrained=False, progress=True, **kwargs)[源代码]

Wide ResNet-101-2 model from “Wide Residual Networks”

The model is the same as ResNet except for the bottleneck number of channels which is twice larger in every block. The number of channels in outer 1x1 convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048 channels, and in Wide ResNet-50-2 has 2048-1024-2048.

参数

  • pretrained (bool) – If True, returns a model pre-trained on ImageNet

  • progress (bool) – If True, displays a progress bar of the download to stderr

Module contents