Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
tjulitianyi 478058d398 | 1 year ago | |
---|---|---|
.. | ||
data | 1 year ago | |
imagecorruptions | 1 year ago | |
samples | 1 year ago | |
src | 1 year ago | |
README.md | 1 year ago | |
customize_service.py | 1 year ago | |
mindspore_hub_conf.py | 1 year ago | |
pascal2coco.py | 1 year ago | |
train.py | 1 year ago | |
train.sh | 1 year ago |
第三届华为云无人车挑战杯复赛Top1方案分享。本届无人车挑战杯大赛主要考核点有交通信号灯识别、车道线检测、斑马线检测、限速标志识别、施工标志识别、障碍物检测等,其中交通信号灯、斑马线、限速标志检测算法需要基于AI开发平台ModelArts开发。训练数据集包含红灯、绿灯、黄灯、人行横道、限速标志、解除限速标志六种类型图片,需使用ModelArts数据管理模块完成以上六种检测目标的标注。参赛者需基于MindSpore框架(使用其他框架提交的作品无效)建立目标检测模型
感谢以上作者的开源工作!!!
4张1080ti,batch_size(6x4)
训练集标签放在data/annotations_xml
下,训练集图片放在data/train
下
mkdir -p data/annotations
python pascal2coco.py
coco预训练模型下载完后放在weights文件夹下面
sh train.sh
生成的模型在weights文件夹下
测试图片放在samples文件夹下,推理结果在outputs文件夹下,该脚本可以本地运行,也可以直接用于部署Modelarts在线服务和批量服务
python customize_service.py
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》