Repository files navigation

Status:Archive ( Final test withPyTorch 1.7 and no longer maintained, I would recommend you to usepycls powered byFAIR, which is a simple and flexible codebase for image classification )

This repository contains the pytorch code for multiple CNN architectures and improve methods based on the following papers,hope the implementation and results will helpful for your research!!

• Architecure
  • (lenet)LeNet-5, convolutional neural networks
  • (alexnet)ImageNet Classification with Deep Convolutional Neural Networks
  • (vgg)Very Deep Convolutional Networks for Large-Scale Image Recognition
  • (resnet)Deep Residual Learning for Image Recognition
  • (preresnet)Identity Mappings in Deep Residual Networks
  • (resnext)Aggregated Residual Transformations for Deep Neural Networks
  • (densenet)Densely Connected Convolutional Networks
  • (senet)Squeeze-and-Excitation Networks
  • (bam)BAM: Bottleneck Attention Module
  • (cbam)CBAM: Convolutional Block Attention Module
  • (genet)Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks
  • (sknet)SKNet: Selective Kernel Networks
• Regularization
  • (shake-shake)Shake-Shake regularization
  • (cutout)Improved Regularization of Convolutional Neural Networks with Cutout
  • (mixup)mixup: Beyond Empirical Risk Minimization
• Learning Rate Scheduler
  • (cos_lr)SGDR: Stochastic Gradient Descent with Warm Restarts
  • (htd_lr)Stochastic Gradient Descent with Hyperbolic-Tangent Decay on Classification

• Python (>=3.6)
• PyTorch (>=1.1.0)
• Tensorboard(>=1.4.0) (forvisualization)
• Other dependencies (pyyaml, easydict)

pip install -r requirements.txt

simply run the cmd for the training:

## 1 GPU for lenetCUDA_VISIBLE_DEVICES=0 python -u train.py --work-path ./experiments/cifar10/lenet## resume from ckptCUDA_VISIBLE_DEVICES=0 python -u train.py --work-path ./experiments/cifar10/lenet --resume## 2 GPUs for resnet1202CUDA_VISIBLE_DEVICES=0,1 python -u train.py --work-path ./experiments/cifar10/preresnet1202## 4 GPUs for densenet190bcCUDA_VISIBLE_DEVICES=0,1,2,3 python -u train.py --work-path ./experiments/cifar10/densenet190bc## 1 GPU for vgg19 inferenceCUDA_VISIBLE_DEVICES=0 python -u eval.py --work-path ./experiments/cifar10/vgg19

We use yaml fileconfig.yaml to save the parameters, check any files in./experimets for more details.
You can see the training curve via tensorboard,tensorboard --logdir path-to-event --port your-port.
The training log will be dumped via logging, checklog.txt in your work path.

PS: the default data augmentation methods areRandomCrop +RandomHorizontalFlip +Normalize,
and the√ means which additional method be used. 🍰

PS:shake_resnet26_2x64d achieved97.71% test accuracy withcutout andmixup!!
It's cool, right?

Provided codes were adapted from

• kuangliu/pytorch-cifar
• bearpaw/pytorch-classification
• timgaripov/swa
• xgastaldi/shake-shake
• uoguelph-mlrg/Cutout
• facebookresearch/mixup-cifar10
• BIGBALLON/cifar-10-cnn
• BayesWatch/pytorch-GENet
• Jongchan/attention-module
• pppLang/SKNet

Feel free to contact me if you have any suggestions or questions, issues are welcome,
create a PR if you find any bugs or you want to contribute. 😊

@misc{bigballon2019cifarzoo,  author = {Wei Li},  title = {CIFAR-ZOO: PyTorch implementation of CNNs for CIFAR dataset},  howpublished = {\url{https://github.com/BIGBALLON/CIFAR-ZOO}},  year = {2019}}