Computer Vision

compressors.models.cv.resnet101(pretrained: bool = False, progress: bool = True, **kwargs: Any) → compressors.models.cv.resnet.ResNet

ResNet-101 model from “Deep Residual Learning for Image Recognition”. :param pretrained: If True, returns a model pre-trained on ImageNet :type pretrained: bool :param progress: If True, displays a progress bar of the download to stderr :type progress: bool

compressors.models.cv.resnet152(pretrained: bool = False, progress: bool = True, **kwargs: Any) → compressors.models.cv.resnet.ResNet

ResNet-152 model from “Deep Residual Learning for Image Recognition”. :param pretrained: If True, returns a model pre-trained on ImageNet :type pretrained: bool :param progress: If True, displays a progress bar of the download to stderr :type progress: bool

compressors.models.cv.resnet18(pretrained: bool = False, progress: bool = True, **kwargs: Any) → compressors.models.cv.resnet.ResNet

ResNet-18 model from “Deep Residual Learning for Image Recognition”. :param pretrained: If True, returns a model pre-trained on ImageNet :type pretrained: bool :param progress: If True, displays a progress bar of the download to stderr :type progress: bool

compressors.models.cv.resnet34(pretrained: bool = False, progress: bool = True, **kwargs: Any) → compressors.models.cv.resnet.ResNet

ResNet-34 model from “Deep Residual Learning for Image Recognition”. :param pretrained: If True, returns a model pre-trained on ImageNet :type pretrained: bool :param progress: If True, displays a progress bar of the download to stderr :type progress: bool

compressors.models.cv.resnet50(pretrained: bool = False, progress: bool = True, **kwargs: Any) → compressors.models.cv.resnet.ResNet

ResNet-50 model from “Deep Residual Learning for Image Recognition”. :param pretrained: If True, returns a model pre-trained on ImageNet :type pretrained: bool :param progress: If True, displays a progress bar of the download to stderr :type progress: bool

compressors.models.cv.resnet_cifar_110(**kwargs) → compressors.models.cv.resnet_cifar.ResNetCifar

ResNet-110 model from “Deep Residual Learning for Image Recognition”. CIFAR version.

compressors.models.cv.resnet_cifar_14(**kwargs) → compressors.models.cv.resnet_cifar.ResNetCifar

ResNet-14 model from “Deep Residual Learning for Image Recognition”. CIFAR version.

compressors.models.cv.resnet_cifar_20(**kwargs) → compressors.models.cv.resnet_cifar.ResNetCifar

ResNet-20 model from “Deep Residual Learning for Image Recognition”. CIFAR version.

compressors.models.cv.resnet_cifar_32(**kwargs) → compressors.models.cv.resnet_cifar.ResNetCifar

ResNet-32 model from “Deep Residual Learning for Image Recognition”. CIFAR version.

compressors.models.cv.resnet_cifar_32x4(**kwargs) → compressors.models.cv.resnet_cifar.ResNetCifar

ResNet-32x4 model from “Wide Residual Networks”. CIFAR version.

compressors.models.cv.resnet_cifar_44(**kwargs) → compressors.models.cv.resnet_cifar.ResNetCifar

ResNet-44 model from “Deep Residual Learning for Image Recognition”. CIFAR version.

compressors.models.cv.resnet_cifar_56(**kwargs) → compressors.models.cv.resnet_cifar.ResNetCifar

ResNet-56 model from “Deep Residual Learning for Image Recognition”. CIFAR version.

compressors.models.cv.resnet_cifar_8(**kwargs) → compressors.models.cv.resnet_cifar.ResNetCifar

ResNet-8 model from “Deep Residual Learning for Image Recognition”. CIFAR version.

compressors.models.cv.resnet_cifar_8x4(**kwargs) → compressors.models.cv.resnet_cifar.ResNetCifar

ResNet-8x4 model from “Wide Residual Networks”. CIFAR version.

compressors.models.cv.resnext101_32x8d(pretrained: bool = False, progress: bool = True, **kwargs: Any) → compressors.models.cv.resnet.ResNet

ResNeXt-101 32x8d model from “Aggregated Residual Transformation for Deep Neural Networks”. :param pretrained: If True, returns a model pre-trained on ImageNet :type pretrained: bool :param progress: If True, displays a progress bar of the download to stderr :type progress: bool

compressors.models.cv.resnext50_32x4d(pretrained: bool = False, progress: bool = True, **kwargs: Any) → compressors.models.cv.resnet.ResNet

ResNeXt-50 32x4d model from “Aggregated Residual Transformation for Deep Neural Networks”. :param pretrained: If True, returns a model pre-trained on ImageNet :type pretrained: bool :param progress: If True, displays a progress bar of the download to stderr :type progress: bool

compressors.models.cv.wide_resnet101_2(pretrained: bool = False, progress: bool = True, **kwargs: Any) → compressors.models.cv.resnet.ResNet

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. :param pretrained: If True, returns a model pre-trained on ImageNet :type pretrained: bool :param progress: If True, displays a progress bar of the download to stderr :type progress: bool

compressors.models.cv.wide_resnet50_2(pretrained: bool = False, progress: bool = True, **kwargs: Any) → compressors.models.cv.resnet.ResNet

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. :param pretrained: If True, returns a model pre-trained on ImageNet :type pretrained: bool :param progress: If True, displays a progress bar of the download to stderr :type progress: bool