Train CIFAR10 with PyTorch

I'm playing with PyTorch on the CIFAR10 dataset.

Learning rate adjustment

I manually change the lr during training:

• 0.1 for epoch [0,150)
• 0.01 for epoch [150,250)
• 0.001 for epoch [250,350)

Resume the training with python main.py --resume --lr=0.01

cifar Accuracy

Model	cifar10	cifar100
VGG16	92.64
ResNet18	93.02	76.51
ResNet50	93.62
ResNet101	93.75
MobileNetV2	94.43
ResNeXt29(32x4d)	94.73
ResNeXt29(2x64d)	94.82
DenseNet121	95.04
PreActResNet18	95.11
DPN92	95.16

ImageNet Accuracy

Model	ImageNet Top1	ImageNet Top5	Tiny ImageNet Top1	Tiny ImageNet Top5
VGG16
ResNet18	64.33	85.73	47.23(64)/60.72(224)	71.84(64)/82.25(224)
ResNet50
ResNet101
MobileNetV2
ResNeXt29(32x4d)
ResNeXt29(2x64d)
DenseNet121
PreActResNet18
DPN92