tensorflow methods
what is tf.cast() and tf.nn.softmax_cross_entropy_with_logits() pls explain this in detail
1 answers ( 0 marked as helpful)
Hi Ashutosh,
First of all, I'd like to point out how amazing the TensorFlow documentation is that you can find here: https://www.tensorflow.org/
More specifically,
Explanation on tf.cast() could be found here: https://www.tensorflow.org/api_docs/python/tf/cast
In layman's terms, to cast means to 'force a different variable type'. For instance, if you have the number '3', you can cast it to be the string 3 (from number it becomes text).
On the other hand, tf.nn.softmax_cross_entropy_with_logits() is available here: https://www.tensorflow.org/api_docs/python/tf/nn/softmax_cross_entropy_with_logits
Combines the softmax activation with the cross entropy loss.
Best,
Iliya