pytorch cifar
1.0.0
我正在 CIFAR10 数据集上使用 PyTorch。
# Start training with:
python main.py
# You can manually resume the training with:
python main.py --resume --lr=0.01
模型 | 附件。 |
---|---|
VGG16 | 92.64% |
残差网络18 | 93.02% |
残网50 | 93.62% |
残网101 | 93.75% |
RegNetX_200MF | 94.24% |
RegNetY_400MF | 94.29% |
移动网络V2 | 94.43% |
ResNeXt29(32x4d) | 94.73% |
ResNeXt29(2x64d) | 94.82% |
简单DLA | 94.89% |
密集网121 | 95.04% |
PreActResNet18 | 95.11% |
DPN92 | 95.16% |
DLA | 95.47% |