About Convolutional Neural Networks in TensorFlow Week 4 loss: nan

nan loss, why did it happen, what went wrong?

Hello @M_Fathurrohman_Haris ,

Welcome to the community!!

Don’t attach screenshot here publicly on discourse as per the community guidelines. Send me your notebook via dm such that I can check where it went wrong. By clicking on the profile picture, you will see an option to message. There you can attach your notebook. Then we can discuss the issues here, under the topic you created.

With regards,
Nilosree Sengupta

Flat loss and accuracy curves almost always mean a mismatch between the loss function and the training data. If you’re using one of the cross entropy loss functions, check to see that it is the right one for the type of output you’re producing (binary or multiclass) and whether the training data has been represented as one-hot or not.


for some details