François Chollet
François Chollet
> PS: I know is not the most proper place to say that, but if you don't mind I'd love to thank you for (among other things) your wonderful book...
> Do you know where you obtained the resnet 50 weights I ported them from the original Caffe implementation IIRC. > Another solution would be to translate the ones from...
This just refers to the dataset as far as I can tell. Seems fine to port them.
> Basically for the same weights and the same inputs, PyTorch and TensorFlow do not give the same outputs... This may be related to padding defaults. See if you can...
I am slightly concerned that the need for manual insertion of padding operations is making the model slower, while not being necessary (it's only needed in order to be able...
> Maybe since I cannot train the model straight away (and I would need to validate the training procedure with someone), it's okay to integrate the models as is and...
> I have to say I hadn't thought about the possibility to use TPUs on Colab. It's true that it might be enough. I believe it is. Happy to help...
Note that placing files in git history can be expensive. It's often a good idea to upload files as "release artifacts" of a new GitHub release of the project.
> Up. I'd be happy to push a PR and fix some code if someone would direct me towards the right direction. I would recommend simply adding a `convert_to_tensor` call...
Thanks for the PR! @rchao what do you think about this change?