apple-aiml-research/ml-cvnets

Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.

Scenic: A Jax Library for Computer Vision Research and Beyond

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

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

OpenMMLab Computer Vision Foundation

A CV toolkit for my papers.

CoreNet: A library for training deep neural networks

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

OpenMMLab Pre-training Toolbox and Benchmark