Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
langdu c2253970f2 | 2 years ago | |
---|---|---|
configs | 2 years ago | |
deploy | 2 years ago | |
images | 2 years ago | |
log | 2 years ago | |
paddleseg | 2 years ago | |
test_tipc | 2 years ago | |
tools | 2 years ago | |
LICENSE | 2 years ago | |
README.md | 2 years ago | |
export.py | 2 years ago | |
predict.py | 2 years ago | |
requirements.txt | 2 years ago | |
train.py | 2 years ago | |
val.py | 2 years ago |
本项目基于paddlepaddle框架复现了DMNet语义分割模型,DMNet提出动态滤波器,核心在于DCM模块,该模块利用池化和卷积生成动态卷积核,与特征图进行卷积。
论文:
项目参考:
在CityScapes val数据集的测试效果如下表。
NetWork | steps | opt | image_size | batch_size | dataset | memory | card | mIou | config | weight | log |
---|---|---|---|---|---|---|---|---|---|---|---|
DMNet | 80K | SGD | 1024x512 | 8 | CityScapes | 32G | 4 | 79.88 | dmnet_cityscapes_1024x512_80k.yml | weight | log |
硬件: Tesla V100 * 4
框架:
# clone this repo
git clone https://github.com/justld/DMNet_paddle.git
cd DMNet_paddle
安装第三方库
pip install -r requirements.txt
单卡训练:
python train.py --config configs/dmnet_cityscapes_1024x512_80k.yml --do_eval --use_vdl --log_iter 100 --save_interval 1000 --save_dir output
多卡训练:
python -m paddle.distributed.launch train.py --config configs/dmnet_cityscapes_1024x512_80k.yml --do_eval --use_vdl --log_iter 100 --save_interval 1000 --save_dir output
output目录下包含已经训练好的模型参数以及对应的日志文件。
python val.py --config configs/dmnet_cityscapes_1024x512_80k.yml --model_path
output目录下包含已经训练好的模型参数以及对应的日志文件。
bash test_tipc/prepare.sh ./test_tipc/configs/dmnet_small/train_infer_python.txt 'lite_train_lite_infer'
bash test_tipc/test_train_inference_python.sh ./test_tipc/configs/dmnet_small/train_infer_python.txt 'lite_train_lite_infer'
代码结构
├─configs
├─images
├─output
├─paddleseg
│ export.py
│ predict.py
│ README.md
│ README_CN.md
│ requirements.txt
│ setup.py
│ train.py
│ val.py
说明
1、本项目在Aistudio平台,使用Tesla V100 * 4 脚本任务训练100K 79.88%。
2、本项目基于PaddleSeg开发。
DMNet转为静态图模式,需要固定输入尺寸,具体参考这里。
相关信息:
信息 | 描述 |
---|---|
作者 | 郎督 |
日期 | 2021年11月 |
框架版本 | PaddlePaddle==2.2.0 |
应用场景 | 语义分割 |
硬件支持 | GPU、CPU |
在线体验 | notebook, Script |
paddle复现DMNET
Python Java Shell Text C++ other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》