how to understand the loss function corner case for 0 and 255
weixsong opened this issue · 3 comments
weixsong commented
Hi,
In the loss function, the code give a special value to value 0 and 255:
# log probability for edge case of 0 (before scaling)
log_cdf_plus = plus_in - tf.nn.softplus(plus_in)
# log probability for edge case of 255 (before scaling)
log_one_minus_cdf_min = -tf.nn.softplus(min_in)
I could not understand these code, how could me understand it?
npuichigo commented
weixsong commented
@npuichigo , thanks very much. I got it.