PKUZHOU/MTCNN_FaceDetection_TensorRT

could not parse layer type PReLU?

rencheng123456 opened this issue · 4 comments

rencheng123456 commented

Thanks your codes.
after cmake and make ,then i run it , the result are as follows:
Beging parsing Pnet model...
could not parse layer type PReLU
End parsing Pnet model
Segmentation fault (core dumped)

I use tensorrt2.1,cudnn7.0,cuda 8.0,opencv2.4.13.
Could you tell me how to solver this problem?

PKUZHOU commented

@rencheng123456 Tensorrt don't support PReLU, I have trained a model without PReLU and has the similar performance. This project isn't finished because I am faced some problem to solve, So you can't run it properly now. I will try to finish it and provide the models latter, Thanks for your interest!

bawdy commented

Any updates on this? I'm currently facing the same issue.

PKUZHOU commented

Sorry I misplaced the prototxt, the proper one is updated

dexception commented

@PKUZHOU
Any guidance on how to train ?