Source code were reused from here.
conda create -n torchenv python=3.6conda activate torchenvconda install pytorch torchvision torchaudio cudatoolkit=10.2 -c pytorch
# Start training with:
python main.py
# You can manually resume the training with:
python main.py --resume --lr=0.01
# You can switch between models by --netname:
python main.py --resume --lr=0.01 --netname {preactresnet18|vgg19|resnet18|lenet}
| 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% |
| SimpleDLA | 94.89% |
| DenseNet121 | 95.04% |
| PreActResNet18 | 95.11% |
| DPN92 | 95.16% |
| DLA | 95.47% |