shooker531 comments

Repositories
Issues
Comments

Results 2 comments of


                                            shooker531

Low accuracy in notebook and py

Did you ever get to the bottom of this? I'm currently having the same issue.

Low accuracy in notebook and py

I think I've found the issue. The cost should be `tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=model, labels=y))` rather than `tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=y))`. That seems to have got the accuracy to a good level for me.