Help convert a VGG 16 model from keras to pytorch
higherdefender opened this issue · comments
Hello! I’m very new to machine learning and I’m trying to convert a trained VGG-16 based model (with a modified fc layer) from keras to pytorch. Can MMdnn help with this? If yes, how should I go about it? I tried for some time to create some commands myself but none worked.
If not, is there any other way I can copy weights from keras VGG to pytorch VGG? Can someone guide me as I really feel out of my depths here?
Thank you really for your help!
Yes, that's what mmdnn does. Maybe you should look at intros in our repo.
Just to hijack this thread! I have also done this (@higherdefender if you didnt manage i can advise)
however, I get different outputs from the keras network and the torch network. Is this normal?
No the predictions differ between the two models on the same data (with same normalisation). Not only are the probabilities different but the argmax too. I can see that the convolutional layers have the same weights, however the fully connected are different which i find strange - maybe i'm missing something.