Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/kuangliu/pytorch-cifar
95.47% on CIFAR10 with PyTorch
https://github.com/kuangliu/pytorch-cifar
pytorch
Last synced: 29 days ago
JSON representation
95.47% on CIFAR10 with PyTorch
- Host: GitHub
- URL: https://github.com/kuangliu/pytorch-cifar
- Owner: kuangliu
- License: mit
- Created: 2017-01-21T05:43:20.000Z (almost 8 years ago)
- Default Branch: master
- Last Pushed: 2023-02-24T10:06:53.000Z (over 1 year ago)
- Last Synced: 2024-10-01T21:42:43.811Z (about 1 month ago)
- Topics: pytorch
- Language: Python
- Homepage:
- Size: 83 KB
- Stars: 5,932
- Watchers: 85
- Forks: 2,136
- Open Issues: 107
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Train CIFAR10 with PyTorch
I'm playing with [PyTorch](http://pytorch.org/) on the CIFAR10 dataset.
## Prerequisites
- Python 3.6+
- PyTorch 1.0+
## Training
```
# Start training with:
python main.py
# You can manually resume the training with:
python main.py --resume --lr=0.01
```
## Accuracy
| Model | Acc. |
| ----------------- | ----------- |
| [VGG16](https://arxiv.org/abs/1409.1556) | 92.64% |
| [ResNet18](https://arxiv.org/abs/1512.03385) | 93.02% |
| [ResNet50](https://arxiv.org/abs/1512.03385) | 93.62% |
| [ResNet101](https://arxiv.org/abs/1512.03385) | 93.75% |
| [RegNetX_200MF](https://arxiv.org/abs/2003.13678) | 94.24% |
| [RegNetY_400MF](https://arxiv.org/abs/2003.13678) | 94.29% |
| [MobileNetV2](https://arxiv.org/abs/1801.04381) | 94.43% |
| [ResNeXt29(32x4d)](https://arxiv.org/abs/1611.05431) | 94.73% |
| [ResNeXt29(2x64d)](https://arxiv.org/abs/1611.05431) | 94.82% |
| [SimpleDLA](https://arxiv.org/abs/1707.064) | 94.89% |
| [DenseNet121](https://arxiv.org/abs/1608.06993) | 95.04% |
| [PreActResNet18](https://arxiv.org/abs/1603.05027) | 95.11% |
| [DPN92](https://arxiv.org/abs/1707.01629) | 95.16% |
| [DLA](https://arxiv.org/pdf/1707.06484.pdf) | 95.47% |