Dinesh Acharya comments

Repositories
Issues
Comments

Results 2 comments of


                                            Dinesh Acharya

the loss tend to be nan

The gradient computation of tensorflow eigen decomposition is most likely producing NaNs. The proposed technique tensorflow_patch.txt worked previously on a different system (with occasional failures). Recently I tried it on...

the loss tend to be nan

However, if you cannot get the numbers in the paper by using pretrained models, I would try following data: https://drive.google.com/open?id=1eh93I0ndg6X-liUJDYpWveIShLd0ao_x and make sure following versions are used: scikit-learn==0.18.1 tensorflow==1.2.0 numpy==1.14.4...