search

PKUZHOU / MTCNN_FaceDetection_TensorRT

MTCNN C++ implementation with NVIDIA TensorRT Inference accelerator SDK
202 stars 57 forks source link

Prelu replacement - "Weights for scale layer" doesn't exists #10

Open ramanathan831 opened 5 years ago

ramanathan831 commented 5 years ago

Hi, Was the model trained on relu+scale combination or it was trained on prelu and you just replace the prelu with equivalent operations only in the prototxt file. I have a model which was trained on prelu, but replacing it with relu+scale combination in the prototxt gives me a "Weights for scale layer" doesn't exists on Tensorrt. Any idea how to solve the issue?

PKUZHOU commented 5 years ago

it was trained on prelu, in fact the model prototxt and weight are borrowed from the official repo of MTCNN. If you replace with relu+scale, you should also modify the model weight to match your prototxt