Andrea Balzano comments

Repositories
Issues
Comments

Results 3 comments of


                                            Andrea Balzano

nan cost

hello, i write here because i encountered a problem with nan cost as well. I am using Neon 2.0 for python 2.7 on Ubuntu 16.04 using GTX1080 backend. in my...

nan cost

i was able to fix the issue by dropping the learning rate of 2 order of magnitude, the issue was apparently due to an infinite cost caused by a prediction...

input shape for inference with new data

i am experimenting using tensorflow serving, i have added the functions spectrogram and spectrogram_from_file to the preprocessing steps. however i am getting this output, shape: (231, 161) dtype: float64 this...