JDet¶

Introduction¶

JDet is a object detection benchmark based on Jittor.

Install¶

JDet environment requirements:

System: Linux(e.g. Ubuntu/CentOS/Arch), macOS, or Windows Subsystem of Linux (WSL)
Python version >= 3.7
CPU compiler (require at least one of the following)
- g++ (>=5.4.0)
- clang (>=8.0)
GPU compiler (optional)
- nvcc (>=10.0 for g++ or >=10.2 for clang)
GPU library: cudnn-dev (recommend tar file installation, reference link)

Step 1: Install the requirements

git clone https://github.com/Jittor/JDet
cd JDet
python -m pip install -r requirements.txt

If you have any installation problems for Jittor, please refer to Jittor

Step 2: Install JDet

cd JDet
# suggest this 
python setup.py develop
# or
python setup.py install

If you don’t have permission for install,please add --user.

Or use PYTHONPATH You can add export PYTHONPATH=$PYTHONPATH:{you_own_path}/JDet/python into .bashrc

source .bashrc

Getting Started¶

Data¶

DOTA Dataset documents are avaliable in the dota.md

FAIR Dataset documents are avaliable in the fair.md

Config¶

Config documents are avaliable in the config.md

Train¶

python tools/run_net.py --config-file=configs/s2anet_r50_fpn_1x_dota.py --task=train

Test¶

If you want to test the downloaded trained models, please set resume_path={you_checkpointspath} in the last line of the config file.

python tools/run_net.py --config-file=configs/s2anet_r50_fpn_1x_dota.py --task=test

Build a New Project¶

In this document, we will introduce how to build a new project(model) with JDet. We need to install JDet first, and build a new project by:

mkdir $PROJECT_PATH$
cd $PROJECT_PATH$
cp $JDet_PATH$/tools/run_net.py ./
mkdir configs

Then we can build and edit configs/base.py like $JDet_PATH$/configs/retinanet.py. If we need to use a new layer, we can define this layer at $PROJECT_PATH$/layers.py and import layers.py in $PROJECT_PATH$/run_net.py, then we can use this layer in config files. Then we can train/test this model by:

python run_net.py --config-file=configs/base.py --task=train
python run_net.py --config-file=configs/base.py --task=test

Models¶

Models	Dataset	Sub_Image_Size/Overlap	Train Aug	Test Aug	Optim	Lr schd	mAP	Paper	Config	Download
S2ANet-R50-FPN	DOTA1.0	1024/200	flip	-	SGD	1x	74.11	arxiv	config	model
S2ANet-R50-FPN	DOTA1.0	1024/200	flip+ra90+bc	-	SGD	1x	76.40	arxiv	config	model
S2ANet-R50-FPN	DOTA1.0	1024/200	flip+ra90+bc+ms	ms	SGD	1x	79.72	arxiv	config	model
S2ANet-R101-FPN	DOTA1.0	1024/200	Flip	-	SGD	1x	74.28	arxiv	config	model
Gliding-R50-FPN	DOTA1.0	1024/200	flip+ms	ms	SGD	1x	67.42	arxiv	config	model
Gliding-R101-FPN	DOTA1.0	1024/200	flip+ms+ra90+bc	ms	SGD	1x	69.53	arxiv	config	model
RetinaNet-R50-FPN	DOTA1.0	600/150	-	-	SGD	-	62.503	arxiv	config	model pretrained

Notice:

ms: multiscale
flip: random flip
ra: rotate aug
ra90: rotate aug with angle 90,180,270
1x : 12 epochs
bc: balance category

Plan¶

:heavy_check_mark:Supported :clock3:Doing :heavy_plus_sign:TODO

:heavy_check_mark: S2ANet
:heavy_check_mark: Gliding
:heavy_check_mark: RetinaNet
:heavy_check_mark: Faster R-CNN
:heavy_check_mark: SSD
:heavy_check_mark: ROI Transformer
:clock3: ReDet
:clock3: YOLOv5
:clock3: R3Det
:clock3: Cascade R-CNN
:heavy_plus_sign: CSL
:heavy_plus_sign: DCL
:heavy_plus_sign: GWD
:heavy_plus_sign: KLD
:heavy_plus_sign: …

Contact Us¶

Website: http://cg.cs.tsinghua.edu.cn/jittor/

Email: jittor@qq.com

File an issue: https://github.com/Jittor/jittor/issues

QQ Group: 761222083

The Team¶

JDet is currently maintained by the Tsinghua CSCG Group. If you are also interested in JDet and want to improve it, Please join us!

Citation¶

@article{hu2020jittor,
  title={Jittor: a novel deep learning framework with meta-operators and unified graph execution},
  author={Hu, Shi-Min and Liang, Dun and Yang, Guo-Ye and Yang, Guo-Wei and Zhou, Wen-Yang},
  journal={Science China Information Sciences},
  volume={63},
  number={222103},
  pages={1--21},
  year={2020}
}