Repository files navigation

Classification on CIFAR-10/100 and ImageNet with PyTorch.

• Unified interface for different network architectures
• Multi-GPU support
• Training progress bar with rich info
• Training log and training curve visualization code (see./utils/logger.py)

• InstallPyTorch
• Clone recursively

  git clone --recursive https://github.com/bearpaw/pytorch-classification.git

Please see theTraining recipes for how to train the models.

Top1 error rate on the CIFAR-10/100 benchmarks are reported. You may get different results when training your models with different random seed.Note that the number of parameters are computed on the CIFAR-10 dataset.

Single-crop (224x224) validation error rate is reported.

Our trained models and training logs are downloadable atOneDrive.

Since the size of images in CIFAR dataset is32x32, popular network structures for ImageNet need some modifications to adapt this input size. The modified models is in the packagemodels.cifar:

• AlexNet
• VGG (Imported frompytorch-cifar)
• ResNet
• Pre-act-ResNet
• ResNeXt (Imported fromResNeXt.pytorch)
• Wide Residual Networks (Imported fromWideResNet-pytorch)
• DenseNet

• All models intorchvision.models (alexnet, vgg, resnet, densenet, inception_v3, squeezenet)
• ResNeXt
• Wide Residual Networks

Feel free to create a pull request if you find any bugs or you want to contribute (e.g., more datasets and more network structures).