JDet
Introduction
JDet is Object Detection Framework 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/li-xl/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
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 | Train Aug | Test Aug | Optim | Lr schd | mAP | Paper | Config | Download |
|---|---|---|---|---|---|---|---|---|---|
| S2ANet-R50-FPN | DOTA1.0 | flip | - | SGD | 1x | 74.11 | arxiv | config | model |
| S2ANet-R50-FPN | DOTA1.0 | flip+ra90+bc | - | SGD | 1x | 76.40 | arxiv | config | model |
| S2ANet-R50-FPN | DOTA1.0 | flip+ra90+bc+ms | ms | SGD | 1x | 79.72 | arxiv | config | model |
| S2ANet-R101-FPN | DOTA1.0 | Flip | - | SGD | 1x | 74.28 | arxiv | config | model |
| Gliding-R50-FPN | DOTA1.0 | flip+ms | ms | SGD | 1x | 67.42 | arxiv | config | model |
| Gliding-R101-FPN | DOTA1.0 | flip+ms+ra90+bc | ms | SGD | 1x | 69.53 | arxiv | config | model |
| RetinaNet-R50-FPN | DOTA1.0 | - | - | 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
-
✔️ S2ANet -
✔️ Gliding -
✔️ RetinaNet -
✔️ Faster R-CNN -
🕒 SSD -
🕒 ReDet -
🕒 YOLOv5 -
🕒 R3Det -
🕒 Cascade R-CNN -
🕒 ROI Transformer -
➕ CSL -
➕ DCL -
➕ GWD -
➕ KLD -
➕ ...
Contact Us
Website: http://cg.cs.tsinghua.edu.cn/jittor/
Email: [email protected]
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}
}
547 Jan 3, 2023
48 Dec 26, 2022
10 Jul 2, 2022
3 Jan 20, 2022
41 Nov 23, 2022
5 Dec 10, 2022
3 Jan 26, 2022
305 Dec 16, 2022
2.2k Jan 8, 2023
443 Dec 6, 2022
254 Dec 16, 2022
1.6k Jan 4, 2023
1 Dec 29, 2021
44 Dec 9, 2022
13 Aug 18, 2022
65 Dec 22, 2022
1 Nov 22, 2021
365 Jan 9, 2023