Using float("-inf") #5

jacobjinkelly · 2018-06-21T01:30:22Z

ptr_decoder.py uses negative infinity (i.e. logarithm of 0). It is unclear if this is best practice or if there is a better way to model the log probability of probability 0.

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Using float("-inf") #5

Using float("-inf") #5

jacobjinkelly commented Jun 21, 2018 •

edited

Loading

Using float("-inf") #5

Using float("-inf") #5

Comments

jacobjinkelly commented Jun 21, 2018 • edited Loading

jacobjinkelly commented Jun 21, 2018 •

edited

Loading