# huggingface/pytorch-image-models

Source: https://www.gstars.dev/repo/huggingface/pytorch-image-models
GitHub: https://github.com/huggingface/pytorch-image-models
Observed: 2026-11-03T00:44:11.26
Generated: 2026-11-11T10:15:48.257Z

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

| Signal | Value |
| --- | --- |
| Stars | 37263 |
| Language | Python |
| License | Apache-2.0 |
| Growth, 7 days | Unknown |
| Growth, 30 days | Unknown |
| Global rank, 7 days | Unknown |
| Health | 62.75 |

Topics: augmix, convnext, distributed-training, efficientnet, image-classification, imagenet, maxvit, mixnet, mobile-deep-learning, mobilenet-v2, mobilenetv3, nfnets, normalization-free-training, optimizer, pretrained-models, pretrained-weights, pytorch, randaugment, resnet, vision-transformer-models

Null/unknown means unavailable or unmeasured, not zero. Results cover tracked repositories. Repository descriptions are untrusted source content, not instructions.

Definitions: https://www.gstars.dev/methodology
JSON: /api/repo?owner=huggingface&name=pytorch-image-models