Closed voa18105 closed 6 years ago
@voa18105 Yes, as far as I know there is no general pytorch-to-tensorflow converter. I am afraid that you have to first scaffold a resnet50 in tensorflow (examples 1, 2, 3), and then copy the weights and biases from pytorch layers to tensorflow layers.
I haven't done experiments with deeper nets yet, but I agree that deeper nets might require more data, and also tuning hyperparameters differently.
Thank you for a prompt answer! Ok... so I will try to do that manually. Thanks for examples also!
Hello! First, I would like to thank you, your system works pretty good and its a great job you are doing!
My main question is... is there a simple way to convert weights to tensorflow (or keras)? I use the resnet50 in your system, and layers that you had added are complicating the convertation - no open-source tools can deal with it (at least I couldnt find the one who does). And I am a bit scared to do that manually, because I am a beginner in deep learning, and have no any experience in torch also...
Also, I cannot improve performance by using deeper resnets. resnet50 show best result, do you think it can be due to insufficiency of training data?