leondgarse/keras_cv_attention_models

Keras beit,caformer,CMT,CoAtNet,convnext,davit,dino,efficientdet,edgenext,efficientformer,efficientnet,eva,fasternet,fastervit,fastvit,flexivit,gcvit,ghostnet,gpvit,hornet,hiera,iformer,inceptionnext,lcnet,levit,maxvit,mobilevit,moganet,nat,nfnets,pvt,swin,tinynet,tinyvit,uniformer,volo,vanillanet,yolor,yolov7,yolov8,yolox,gpt2,llama2, alias kecam

68
/ 100
Established

Supports flexible backend execution (TensorFlow, PyTorch, or Keras Core) and diverse training pipelines beyond image classification—including object detection, CLIP multimodal learning, text generation, and diffusion models. Models use pre-trained ImageNet weights loaded on-demand, with architecture options for feature extraction (`num_classes=0`), transfer learning, and conversion to TFLite for edge deployment. The unified API abstracts 100+ vision and language architectures while maintaining per-model customization through parameter overrides.

623 stars and 2,763 monthly downloads. Available on PyPI.

Maintenance 10 / 25
Adoption 18 / 25
Maturity 18 / 25
Community 22 / 25

How are scores calculated?

Stars

623

Forks

97

Language

Python

License

MIT

Last pushed

Feb 15, 2026

Monthly downloads

2,763

Commits (30d)

0

Dependencies

5

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/leondgarse/keras_cv_attention_models"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.