kpick.classifier.cifar_classification_models package

Submodules

kpick.classifier.cifar_classification_models.alexnet module

AlexNet for CIFAR10. FC layers are removed. Paddings are adjusted. Without BN, the start learning rate should be 0.01 (c) YANG, Wei

kpick.classifier.cifar_classification_models.alexnet.alexnet(**kwargs): AlexNet model architecture from the “One weird trick…” paper.

kpick.classifier.cifar_classification_models.densenet module

kpick.classifier.cifar_classification_models.densenet.densenet(**kwargs): Constructs a ResNet model.

kpick.classifier.cifar_classification_models.preresnet module

kpick.classifier.cifar_classification_models.preresnet.preresnet(**kwargs): Constructs a ResNet model.

kpick.classifier.cifar_classification_models.resnet module

kpick.classifier.cifar_classification_models.resnet.resnet(**kwargs): Constructs a ResNet model.

kpick.classifier.cifar_classification_models.resnet_roi module

kpick.classifier.cifar_classification_models.resnet_roi.resnet_roi(**kwargs): Constructs a ResNet model.

kpick.classifier.cifar_classification_models.resnext module

kpick.classifier.cifar_classification_models.resnext.resnext(**kwargs): Constructs a ResNeXt.

kpick.classifier.cifar_classification_models.vgg module

VGG for CIFAR10. FC layers are removed. (c) YANG, Wei

class kpick.classifier.cifar_classification_models.vgg.VGG(features, num_classes=1000)

Bases: Module

forward(x)

training: bool

kpick.classifier.cifar_classification_models.vgg.vgg11(**kwargs)

VGG 11-layer model (configuration “A”)

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

kpick.classifier.cifar_classification_models.vgg.vgg11_bn(**kwargs): VGG 11-layer model (configuration “A”) with batch normalization

kpick.classifier.cifar_classification_models.vgg.vgg13(**kwargs)

VGG 13-layer model (configuration “B”)

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

kpick.classifier.cifar_classification_models.vgg.vgg13_bn(**kwargs): VGG 13-layer model (configuration “B”) with batch normalization

kpick.classifier.cifar_classification_models.vgg.vgg16(**kwargs)

VGG 16-layer model (configuration “D”)

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

kpick.classifier.cifar_classification_models.vgg.vgg16_bn(**kwargs): VGG 16-layer model (configuration “D”) with batch normalization

kpick.classifier.cifar_classification_models.vgg.vgg19(**kwargs)

VGG 19-layer model (configuration “E”)

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

kpick.classifier.cifar_classification_models.vgg.vgg19_bn(**kwargs): VGG 19-layer model (configuration ‘E’) with batch normalization

kpick.classifier.cifar_classification_models.wrn module

kpick.classifier.cifar_classification_models.wrn.wrn(**kwargs): Constructs a Wide Residual Networks.