added a little helper function to vggish to get features from waveforms #31
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
|
NB: tests pass and coverage is good locally, i anticipate no problems even if travis takes forever. |
ejhumphrey
reviewed
Sep 19, 2018
|
|
||
| Returns | ||
| ------- | ||
| time_points : np.ndarray, len=n |
There was a problem hiding this comment.
per #29, we're making a conscious decision to converge to time_points then?
There was a problem hiding this comment.
I literally just copied over from the existing functions. If we rename, we should do it all at once, and i think it's independent of this pr.
ejhumphrey
reviewed
Sep 19, 2018
| The output features, with or without PCA compression and quantization. | ||
| ''' | ||
|
|
||
| import tensorflow as tf |
There was a problem hiding this comment.
what's the rationale for within-function importing here?
There was a problem hiding this comment.
tf import is heavy (sometimes); we shouldn't do it until called for.
If it's already been loaded elsewhere, then this is free.
ejhumphrey
approved these changes
Sep 19, 2018
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Outdated suggestions cannot be applied.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.
Now you can get features directly from waveforms by saying
with
compress=True(default), the outputs are whitened and quantized. Withcompress=Falsethey are left as is from the model.This should simplify doing one-off feature extraction in our notebook demos, even if it's less efficient than going through featurefy.