P
pytorch-image-models
huggingface/pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
★37.1kstars
Python
Apache-2.0
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?A , built with Python open-source project in the Models category, core strengths: augmix/convnext
Who made it?Maintained by huggingface team, 37.1K⭐ on GitHub, #27 out of 3201 in Models
Why does it exist?In the Models space, augmix workflows faced efficiency bottlenecks. pytorch-image-models was built by huggingface to address these convnext challenges.
What can it do?Key use cases: distributed-training, efficientnet, image-classification
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/huggingface/pytorch-image-models | 官网 https://huggingface.co/docs/timm
🔗 github.com/huggingface/pytorch-image-models | 官网 https://huggingface.co/docs/timm
Topics
augmixconvnextdistributed-trainingefficientnetimage-classificationimagenetmaxvitmixnetmobile-deep-learningmobilenet-v2mobilenetv3nfnetsnormalization-free-trainingoptimizerpretrained-modelspretrained-weightspytorchrandaugmentresnetvision-transformer-models