New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Not using mne epochs for windowing #515
Not using mne epochs for windowing #515
Conversation
db0a4d1
to
f9480e8
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks nice! A few comments.
f9480e8
to
0bf207c
Compare
0bf207c
to
51fbb44
Compare
Still a lot of code duplication and code simplification to do, will tackle that next |
Codecov Report
@@ Coverage Diff @@
## master #515 +/- ##
==========================================
- Coverage 84.55% 83.70% -0.86%
==========================================
Files 63 63
Lines 4676 4812 +136
==========================================
+ Hits 3954 4028 +74
- Misses 722 784 +62 |
…decode-1 into windower-without-epochs
yes, brackets on new lines makes more happy 😁 |
Hey @robintibor! From the CI it looks like it is finished, is there something missing in the PR? |
So still need to reenable the outcommented test or remove it, and possibly rename dataset classes, but might do renaming of dataset classes in separate PR |
Trying to get at it today |
So this would be ready from my side now I think @bruAristimunha feel free to merge. See also new issues I created #543 and #544 |
Amazing @robintibor 🚀!!! Thank you so much for the code and review, @robintibor, @tomMoral and @sliwy =) |
Not calling
mne.Epochs
construction anymore during windowing,using directly the computed crop indices on the mne raw.For now, in same
WindowsDataset
class as before, potentially splitting the class into two later.