Skip to content
Branch: master
Find file History
lyttonhao and facebook-github-bot add download links for pretrained tridentnet models
Summary:
* Upload tridentnet models to D2 model zoo in S3 Storage
* Add download links for pretrained tridentnet models
* Update the results of tridentnet to make consistent with downloaded models

Reviewed By: ppwwyyxx

Differential Revision: D18346588

fbshipit-source-id: 938c49c9004ba5f08f870608325354b49d458ea0
Latest commit cb69ea1 Nov 9, 2019
Permalink
Type Name Latest commit message Commit time
..
Failed to load latest commit information.
configs add download links for pretrained tridentnet models Nov 9, 2019
tridentnet Spelling (#47) Oct 13, 2019
README.md add download links for pretrained tridentnet models Nov 9, 2019
train_net.py Initial commit Oct 10, 2019

README.md

TridentNet in Detectron2

Scale-Aware Trident Networks for Object Detection

Yanghao Li*, Yuntao Chen*, Naiyan Wang, Zhaoxiang Zhang

[TridentNet] [arXiv] [BibTeX]

In this repository, we implement TridentNet-Fast in Detectron2. Trident Network (TridentNet) aims to generate scale-specific feature maps with a uniform representational power. We construct a parallel multi-branch architecture in which each branch shares the same transformation parameters but with different receptive fields. TridentNet-Fast is a fast approximation version of TridentNet that could achieve significant improvements without any additional parameters and computational cost.

Training

To train a model, run

python /path/to/detectron2/projects/TridentNet/train_net.py --config-file <config.yaml>

For example, to launch end-to-end TridentNet training with ResNet-50 backbone on 8 GPUs, one should execute:

python /path/to/detectron2/projects/TridentNet/train_net.py --config-file configs/tridentnet_fast_R_50_C4_1x.yaml --num-gpus 8

Evaluation

Model evaluation can be done similarly:

python /path/to/detectron2/projects/TridentNet/train_net.py --config-file configs/tridentnet_fast_R_50_C4_1x.yaml --eval-only MODEL.WEIGHTS model.pth

Results on MS-COCO in Detectron2

Model Backbone Head lr sched AP AP50 AP75 APs APm APl download
Faster R50-C4 C5-512ROI 1X 35.7 56.1 38.0 19.2 40.9 48.7 model | metrics
TridentFast R50-C4 C5-128ROI 1X 38.0 58.1 40.8 19.5 42.2 54.6 model | metrics
Faster R50-C4 C5-512ROI 3X 38.4 58.7 41.3 20.7 42.7 53.1 model | metrics
TridentFast R50-C4 C5-128ROI 3X 40.6 60.8 43.6 23.4 44.7 57.1 model | metrics
Faster R101-C4 C5-512ROI 3X 41.1 61.4 44.0 22.2 45.5 55.9 model | metrics
TridentFast R101-C4 C5-128ROI 3X 43.6 63.4 47.0 24.3 47.8 60.0 model | metrics

Citing TridentNet

If you use TridentNet, please use the following BibTeX entry.

@InProceedings{li2019scale,
  title={Scale-Aware Trident Networks for Object Detection},
  author={Li, Yanghao and Chen, Yuntao and Wang, Naiyan and Zhang, Zhaoxiang},
  journal={The International Conference on Computer Vision (ICCV)},
  year={2019}
}
You can’t perform that action at this time.