Open GarrickLin opened 6 years ago
You can look at the tensorrt3.0 document.There is an introduction in the document.
Thanks for your contribution to TensorRT implementation @chenzhi1992 , I found that TensorRT3 already implemented createPReLU
INvPlugin * createPReLUPlugin(float negSlope); INvPlugin * createPReLUPlugin(const void * data, size_t length);
However it only supports channel_shared mode, so what we need to do is to extend it to cross_channel mode, is it right?
it it not a real PReLU as caffe, it is a leakyrelu
with constant neg-slop.
I found that PreluPlugin still need a constructor for nvinfer1::Weights to init prelu parameters