pytorch cifar
1.0.0
Я играю с PyTorch в наборе данных CIFAR10.
# Start training with:
python main.py
# You can manually resume the training with:
python main.py --resume --lr=0.01
Модель | Акк. |
---|---|
ВГГ16 | 92,64% |
Реснет18 | 93,02% |
Реснет50 | 93,62% |
Реснет101 | 93,75% |
RegNetX_200MF | 94,24% |
RegNetY_400MF | 94,29% |
МобилНетВ2 | 94,43% |
ResNeXt29(32x4d) | 94,73% |
ResNeXt29(2x64d) | 94,82% |
SimpleDLA | 94,89% |
DenseNet121 | 95,04% |
PreActResNet18 | 95,11% |
ДПН92 | 95,16% |
ДЛА | 95,47% |