Hi @ariseff , thanks for sharing the awesome code repo! :)
Your code works well, but I cannot understand why we need to do sampling from a multinomial distribution?
Can we replace it with argmax or just with no-sampling?
|
class_ind = tf.to_int32(tf.multinomial(tf.log(probs), 1)[0][0]) |
Hi @ariseff , thanks for sharing the awesome code repo! :)
Your code works well, but I cannot understand why we need to do sampling from a multinomial distribution?
Can we replace it with argmax or just with no-sampling?
overcoming-catastrophic/model.py
Line 54 in cab6d86