Closed cesc-park closed 8 years ago
@cesc-park I was wondering what is right and what is wrong. Did you closed this issue because the original code is right?
@carpedm20 Yep
softmax_cross_entropy_with_logits implicitly calculate log probability.
Tensorflow document "tf.nn.softmax_cross_entropy_with_logits(logits, labels, name=None) logits: Unscaled log probabilities."
Made me confusing.
Sorry!
Model output should be changed to log probability
to calculate
tf.nn.softmax_cross_entropy_with_logits(logpro, target)