Detach sample and log_prob from neural net #17
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
janfb
approved these changes
Mar 30, 2021
pyknos/mdn/mdn.py
Outdated
| Return the log-probability of `inputs` under a MoG with specified parameters. | ||
|
|
||
| Unlike the `log_prob()` method, this method is fully detached from the neural | ||
| network and is a `staticmethod`. |
There was a problem hiding this comment.
would remove the "and is a static method", this is clear from the code, no?
Instead I would add why this is useful, e.g., add sth like "can be used independent of the neural net in case the MoG parameters are already known"?
| """ | ||
| Return samples of a MoG with specified parameters. | ||
|
|
||
| Unlike the `sample()` method, this method is fully detached from the neural |
There was a problem hiding this comment.
same addition as for the log_prob_mog docstring.
michaeldeistler
force-pushed
the
refactor-mdn
branch
from
4011b8f
to
8db4601
Compare
|
Totally agree with both comments, thanks! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR provides methods that allow to
sample()andlog_prob()from a MoG when already knowing the precision and means. It's a simple refactor, but it will save us a lot of code repetition here.