weiaicunzai/pytorch-cifar100 resource

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

4776 stars · 1206 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A PyTorch practice repository implementing dozens of classic CNN architectures (ResNet, DenseNet, VGG, GoogLeNet, Inception variants, Xception, MobileNet, ShuffleNet, SENet, and more) for training and evaluating on the CIFAR-100 dataset. It includes training and testing scripts with GPU support, warmup options, and TensorBoard logging.

Use cases

• train resnet on cifar100 in pytorch
• compare cnn architectures on cifar100
• learn how to implement classic vision models from scratch
• benchmark mobilenet vs shufflenet accuracy
• pytorch image classification training script example
• study inception and xception implementations

When to choose

• you want ready-to-run PyTorch implementations of many classic CNN architectures on CIFAR-100
• you are learning deep learning and want reference code for papers like ResNet or DenseNet
• you need a simple baseline for image classification experiments

When to avoid

• you need production-grade training pipelines with distributed training or mixed precision
• you want pretrained ImageNet weights or transfer learning tooling
• you need a maintained library with a license, tests, and package releases

Facets

learning-resource · maturity maintenance

deep-learning machine-learning image-processing computer-vision benchmarking deep-learning computer-vision image-processing machine-learning tutorials python cross-platform pytorch cifar100 image-classification cnn-architectures resnet densenet mobilenet educational gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="weiaicunzai/pytorch-cifar100")