Description
Hello. I am new to using tensorrt to accelerate neural networks. I have a question that I could not find an answer to. Maybe someone can give me the answer.
Question : is whether tensorrt supports sets the new value for the learned param of the layer. The solution I am working with has weights that need to be set (the weights are derived from another neural network). Is it possible to do this in tensorrt (analogous to cv::dnn::Net::setParam function from OpenCV).
Maybe someone has a minimal example of how to do it?