I use this URL (https://github.com/dusty-nv/jetson-inference/blob/master/docs/pytorch-collect.md) to go to the training step. I corrected the dropout network parameters of googlenet-1378be20.pth. When I got to the step of converting onnx, I found that the .pth network parameters were still the same. How can I solve this problem?
Would you mind to run the .pth with pyTorch interface directly?
Please help to check if the dropout layer is added correctly or not.