pytorch-classification

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

Features

• 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)

Install

• Install PyTorch

• Clone recursively

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

Training

Please see the Training recipes for how to train the models.

Results

CIFAR

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.

ImageNet

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

Pretrained models

Our trained models and training logs are downloadable at OneDrive.

Supported Architectures

CIFAR-10 / CIFAR-100

Since the size of images in CIFAR dataset is 32x32, popular network structures for ImageNet need some modifications to adapt this input size. The modified models is in the package models.cifar:

•  AlexNet

•  VGG (Imported from pytorch-cifar)

•  ResNet

•  Pre-act-ResNet

•  ResNeXt (Imported from ResNeXt.pytorch)

•  Wide Residual Networks (Imported from WideResNet-pytorch)

•  DenseNet

ImageNet

•  All models in torchvision.models (alexnet, vgg, resnet, densenet, inception_v3, squeezenet)

•  ResNeXt

•  Wide Residual Networks

Contribute

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).