Repository files navigation

This project provides an implementation for "End-to-End Object Detection with Fully Convolutional Network" on PyTorch.

Experiments in the paper were conducted on the internal framework, thus we reimplement them oncvpods and report details as below.

• cvpods
• scipy >= 1.5.4

• install cvpods locally (requires cuda to compile)

python3 -m pip install'git+https://github.com/Megvii-BaseDetection/cvpods.git'# (add --user if you don't have permission)# Or, to install it from a local clone:git clone https://github.com/Megvii-BaseDetection/cvpods.gitpython3 -m pip install -e cvpods# Or,pip install -r requirements.txtpython3 setup.py build develop

• prepare datasets

cd /path/to/cvpodscd datasetsln -s /path/to/your/coco/dataset coco

• Train & Test

git clone https://github.com/Megvii-BaseDetection/DeFCN.gitcd DeFCN/playground/detection/coco/poto.res50.fpn.coco.800size.3x_ms# for example# Trainpods_train --num-gpus 8# Testpods_test --num-gpus 8 \    MODEL.WEIGHTS /path/to/your/save_dir/ckpt.pth# optional    OUTPUT_DIR /path/to/your/save_dir# optional# Multi node training## sudo apt install net-tools ifconfigpods_train --num-gpus 8 --num-machines N --machine-rank 0/1/.../N-1 --dist-url"tcp://MASTER_IP:port"

* We adopt a one-to-one assignment in POTO and a one-to-many assignment in the auxiliary loss, respectively.

• 2x + ms schedule is adopted in the paper, but we adopt3x + ms schedule here to achieve higher performance.
• It's normal to observe ~0.3AP noise in POTO.

* We adopt a one-to-one assignment in POTO and a one-to-many assignment in the auxiliary loss, respectively.

• It's normal to observe ~0.3AP noise in POTO, and ~1.0mMR noise in all methods.

* We adopt a one-to-one assignment in POTO and a one-to-many assignment in the auxiliary loss, respectively.

• Forone-to-one assignment, more training iters lead to higher performance.
• Theargmax (also known as top-1) operation is indeed the approximate solution of bipartite matching in dense prediction methods.
• It seems harmless to remove GN in 3DMF, which also leads to higher inference speed.

This repo is developed based on cvpods. Please checkcvpods for more details and features.

This repo is released under the Apache 2.0 license. Please see the LICENSE file for more information.

If you use this work in your research or wish to refer to the baseline results published here, please use the following BibTeX entries:

@article{wang2020end,  title   =  {End-to-End Object Detection with Fully Convolutional Network},  author  =  {Wang, Jianfeng and Song, Lin and Li, Zeming and Sun, Hongbin and Sun, Jian and Zheng, Nanning},  journal =  {arXiv preprint arXiv:2012.03544},  year    =  {2020}}

Any pull requests or issues about the implementation are welcome. If you have any issue about the library (e.g. installation, environments), please refer tocvpods.