projects/conditional_detr/README.md

Conditional DETR for Fast Training Convergence

Depu Meng, Xiaokang Chen, Zejia Fan, Gang Zeng, Houqiang Li, Yuhui Yuan, Lei Sun, Jingdong Wang

[arXiv] [BibTeX]

Pretrained Weights

Here we provide the pretrained Conditional-DETR weights based on detrex.

Name	Backbone	Pretrain	Epochs	box AP	download
Conditional-DETR-R50	R-50	IN1k	50	41.6	model

Converted Weights

Name	Backbone	Pretrain	Epochs	box AP	download
Conditional-DETR-R50	R-50	IN1k	50	41.0	model
Conditional-DETR-R50-DC5	R-50-DC5	IN1k	50	43.8	model
Conditional-DETR-R101	R-101	IN1k	50	43.0	model
Conditional-DETR-R101-DC5	R-101-DC5	IN1k	50	45.1	model

Note: Here we borrowed the pretrained weight from ConditionalDETR official repo. And our detrex training results will be released in the future version.

Training

All configs can be trained with:

cd detrex
python tools/train_net.py --config-file projects/conditional_detr/configs/path/to/config.py --num-gpus 8

By default, we use 8 GPUs with total batch size as 16 for training.

Evaluation

Model evaluation can be done as follows:

cd detrex
python tools/train_net.py --config-file projects/conditional_detr/configs/path/to/config.py --eval-only train.init_checkpoint=/path/to/model_checkpoint

Citing Conditional-DETR

If you find our work helpful for your research, please consider citing the following BibTeX entry.

@inproceedings{meng2021-CondDETR,
  title       = {Conditional DETR for Fast Training Convergence},
  author      = {Meng, Depu and Chen, Xiaokang and Fan, Zejia and Zeng, Gang and Li, Houqiang and Yuan, Yuhui and Sun, Lei and Wang, Jingdong},
  booktitle   = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
  year        = {2021}
}