We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
某些图片在cpp的pse过程会卡住,没报错一直卡住,改成pypse就可以正常运行。pypse代码里有个bug,25行应该改成for i in range(label_values): 之前是for i in label_values:,label_values是个int
The text was updated successfully, but these errors were encountered:
找到问题了,是因为cpppse里面的结果矩阵类型是uint8所以只支持256个框以内的,我的图片框比较多,就会有问题, //初始化结果 auto res = py::array_t<int32_t>(pbuf_text.size); 改成int32就行了
Sorry, something went wrong.
只有我在改了后,出现段错误的情况么。 按楼上说的,改为int32_t之后,训练没问题,但是预测时候基本上所有图片都出现段错误的情况,改回去就好了。。。
pypse 怎么使用,我看 postprocessing init.py 使用的是 from .pse import pse_cpp, get_points, get_num, 这里应该是用到了 pse.so文件吧,如何直接运行 pypse 不用cpp的代码呢
No branches or pull requests
某些图片在cpp的pse过程会卡住,没报错一直卡住,改成pypse就可以正常运行。pypse代码里有个bug,25行应该改成for i in range(label_values): 之前是for i in label_values:,label_values是个int
The text was updated successfully, but these errors were encountered: