pytorch cifar
1.0.0
Estoy jugando con PyTorch en el conjunto de datos CIFAR10.
# Start training with:
python main.py
# You can manually resume the training with:
python main.py --resume --lr=0.01
| Modelo | Acc. |
|---|---|
| VGG16 | 92,64% |
| ResNet18 | 93,02% |
| ResNet50 | 93,62% |
| ResNet101 | 93,75% |
| RegNetX_200MF | 94,24% |
| RegNetY_400MF | 94,29% |
| MóvilNetV2 | 94,43% |
| ResNeXt29(32x4d) | 94,73% |
| ResNeXt29(2x64d) | 94,82% |
| DLA simple | 94,89% |
| DensoNet121 | 95,04% |
| PreActResNet18 | 95,11% |
| DPN92 | 95,16% |
| DLA | 95,47% |
