I use this URL (jetson-inference/pytorch-collect.md at master · dusty-nv/jetson-inference · GitHub) 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?
Hi,
Would you mind to run the .pth with pyTorch interface directly?
Please help to check if the dropout layer is added correctly or not.
Thanks.