aaron-xichen/pytorch-playground resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2716 stars · 619 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A PyTorch playground providing pretrained models and dataset loaders for popular benchmarks like MNIST, SVHN, CIFAR10/100, STL10, and ImageNet architectures (AlexNet, VGG, ResNet, Inception, SqueezeNet). It also includes a demo for quantizing models to lower bit-widths using linear, minmax, and non-linear methods.

Use cases

• learn pytorch with pretrained models on mnist and cifar
• download pretrained models for image classification benchmarks
• quantize a model to 8-bit or lower precision
• train an mlp on mnist as a pytorch beginner
• evaluate quantization accuracy tradeoffs on standard datasets
• set up a quick imagenet validation pipeline

When to choose

• you are a pytorch beginner wanting ready-made models and dataset loaders
• you need pretrained checkpoints for small vision benchmarks
• you want to experiment with low-bit quantization methods

When to avoid

• you need production-grade training frameworks or modern architectures like transformers
• you require actively maintained code with recent pytorch compatibility
• you work outside image classification domains

Facets

learning-resource · maturity maintenance

machine-learning deep-learning benchmarking data-science deep-learning machine-learning computer-vision tutorials python cross-platform pytorch pretrained-models quantization image-classification mnist cifar tutorial model-zoo gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="aaron-xichen/pytorch-playground")