LutaoChu 21d2f0ce8e | 2 years ago | |
---|---|---|
.. | ||
README.md | 2 years ago | |
analyze_infer_models_log.py | 2 years ago | |
fcn_hrnetw18_small_v1_humanseg_192x192_mini_supervisely.yml | 2 years ago | |
hrnetw18_small_v1_params.txt | 2 years ago | |
prepare.sh | 2 years ago | |
test_infer_models.sh | 2 years ago | |
test_model.sh | 2 years ago |
test_model.sh和params.txt文件配合使用,完成分割模型从训练到预测的流程测试。
pip3 install -r ../requirements.txt
git clone https://github.com/LDOUBLEV/AutoLog
cd AutoLog
pip3 install -r requirements.txt
python3 setup.py bdist_wheel
pip3 install ./dist/auto_log-1.0.0-py3-none-any.whl
cd ../
tests/
├── hrnetw18_small_v1_params.txt # 测试分割模型的参数配置文件
└── fcn_hrnetw18_small_v1_humanseg_192x192_mini_supervisely.yml # 测试分割模型的config配置文件
└── prepare.sh # 完成test_model.sh运行所需要的数据和模型下载
└── test_model.sh # 测试主程序
test_model.sh包含四种运行模式,每种模式的运行数据不同,分别用于测试速度和精度,分别是:
bash test/prepare.sh ./tests/hrnetw18_small_v1_params.txt 'lite_train_infer'
bash tests/test_model.sh ./tests/hrnetw18_small_v1_params.txt 'lite_train_infer'
bash tests/prepare.sh ./tests/hrnetw18_small_v1_params.txt 'whole_infer'
bash tests/test_model.sh ./tests/hrnetw18_small_v1_params.txt 'whole_infer'
bash tests/prepare.sh ./tests/hrnetw18_small_v1_params.txt 'infer'
# 用法1:
bash tests/test_model.sh ./tests/hrnetw18_small_v1_params.txt 'infer'
# 用法2: 指定GPU卡预测,第三个传入参数为GPU卡号
bash tests/test_model.sh ./tests/hrnetw18_small_v1_params.txt 'infer' '1'
bash tests/prepare.sh ./tests/hrnetw18_small_v1_params.txt 'whole_train_infer'
bash tests/test_model.sh ./tests/hrnetw18_small_v1_params.txt 'whole_train_infer'
最终在tests/output
目录下生成.log后缀的日志文件
飞桨高性能图像分割开发套件,端到端完成从训练到部署的全流程图像分割应用。
https://github.com/PaddlePaddle/PaddleSeg
Python Markdown Text Shell Java 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》