TensorTest

[Potential NAN bug] Loss may become NAN during training

1

Hello~ Thank you very much for sharing the code! I try to use my own data set ( with the same shape as mnist) in code. After some iterations, it...

I found that there may be a potential NAN bug in the code if we use tf.log(pred) when the pred contains 0. I described in detail in the issue #383...

Hello~ Thank you very much for sharing the code! I try to use my own data set ( with the same shape as mnist) in code. After some iterations, it...

Hello~ Thank you very much for sharing the code! I try to use my own dataset ( with the same shape as mnist) in code. After some iterations, it is...