hpc203 / YOLOP-opencv-dnn

使用OpenCV部署全景驾驶感知网络YOLOP,可同时处理交通目标检测、可驾驶区域分割、车道线检测,三项视觉感知任务,包含C++和Python两种版本的程序实现。本套程序只依赖opencv库就可以运行, 从而彻底摆脱对任何深度学习框架的依赖。

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

OpenCV minimum version

Takugo opened this issue · comments

Hi there,
Thanks for your guys awesome tasks.
But I met an issue while compiling through opencv. Which version your team using to build this repo?

opencv/modules/dnn/src/onnx/onnx_importer.cpp:555: error: (-215:Assertion failed) blob.type() == 5 in function 'populateNet'

Hi there, Thanks for your guys awesome tasks. But I met an issue while compiling through opencv. Which version your team using to build this repo?

opencv/modules/dnn/src/onnx/onnx_importer.cpp:555: error: (-215:Assertion failed) blob.type() == 5 in function 'populateNet'

升级opencv再试一下

commented

4.5.4.60测试没问题

4.5.4.60报错如下:

line 68, in postprocess
i = i[0]
IndexError: invalid index to scalar variable.

1.建议使用opencv-python==4.5.4.60
2.如果报错如下:
line 68, in postprocess
i = i[0]
IndexError: invalid index to scalar variable.

请直接注释掉line68