This repo contains the code for reproducing object detection results of our FocalNets. It is based on DINO.
Please follow DINO's instruction for installation.
python -m torch.distributed.launch --nproc_per_node={ngpus} main.py --config_file config/DINO/DINO_4scale_focalnet_fl3.py --coco_path {coco_path} --output_dir {output_dir}
python -m torch.distributed.launch --nproc_per_node={ngpus} main.py --config_file config/DINO/DINO_5scale_focalnet_fl4.py --coco_path {coco_path} --output_dir {output_dir}
FocalNet-DINO pretrained with Object365:
Backbone Method Pretrained Data COCO minival mAP (w/o tta) Download Swin-L DINO Object365 63.1 - FocalNet-L DINO Object365 63.5 in21k ckpt/o365 ckpt/coco ckptThanks to the authors of DINO, the DINO models trained with FocalNets as the backbones can be found here:
FocalNet-L + DINO: DINO + FocalNet-L
All pretrained models on imagenet-1k or imagenet-21k are provided in:
Focal Modulation Networks: Focal Modulation Networks Model Zoo.
If you find this repo useful to your project, please consider to cite it with following bib:
@misc{yang2022focalnet,
author = {Yang, Jianwei and Li, Chunyuan and Dai, Xiyang and Yuan, Lu and Gao, Jianfeng},
title = {Focal Modulation Networks},
publisher = {arXiv},
year = {2022},
}
and also:
@misc{zhang2022dino,
title={DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection},
author={Hao Zhang and Feng Li and Shilong Liu and Lei Zhang and Hang Su and Jun Zhu and Lionel M. Ni and Heung-Yeung Shum},
year={2022},
eprint={2203.03605},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4