Many thanks for kuangliu/pytorch-cifar, akamaster/pytorch_resnet_cifar10, HtutLynn in kuangliu/issues/45 !
- Python 3.6+
- PyTorch 1.0+
| Model | Acc. |
|---|---|
| VGG16 | 92.64% |
| ResNet18 | 93.02% |
| ResNet50 | 93.62% |
| ResNet101 | 93.75% |
| RegNetX_200MF | 94.24% |
| RegNetY_400MF | 94.29% |
| MobileNetV2 | 94.43% |
| ResNeXt29(32x4d) | 94.73% |
| ResNeXt29(2x64d) | 94.82% |
| DenseNet121 | 95.04% |
| PreActResNet18 | 95.11% |
| DPN92 | 95.16% |
- [Add resnet 20,32,56,110,1202]
- [Auto learning rate adjustment]
- [Save log]
- [Save to tensorboard]
- [Select network in arguments]
- [Support more datasets]
$ python main.py$ python main.py --resume --checkpoint '/path/to/your/checkpoint'