MTCNN_FaceDetection_TensorRT icon indicating copy to clipboard operation
MTCNN_FaceDetection_TensorRT copied to clipboard

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

Open ramanathan831 opened this issue 5 years ago • 1 comments

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?

ramanathan831 avatar Jul 10 '19 16:07 ramanathan831

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

PKUZHOU avatar Jul 22 '19 15:07 PKUZHOU