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
[Feature] Register torchvision transforms into mmcls #1265
[Feature] Register torchvision transforms into mmcls #1265
Conversation
Codecov ReportPatch coverage has no change and project coverage change:
Additional details and impacted files@@ Coverage Diff @@
## dev #1265 +/- ##
==========================================
+ Coverage 84.37% 85.22% +0.85%
==========================================
Files 142 229 +87
Lines 9925 17311 +7386
Branches 1621 2715 +1094
==========================================
+ Hits 8374 14753 +6379
- Misses 1277 2056 +779
- Partials 274 502 +228
Flags with carried forward coverage won't be shown. Click here to find out more. see 371 files with indirect coverage changes Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. ☔ View full report in Codecov by Sentry. |
f162ab1
to
b4e24a1
Compare
* add stochastic depth decay rule to drop path rate * add default value * update * pass ut * update * pass ut * remove np
d81e078
to
0b818d6
Compare
Motivation
Register torchvision transforms into mmcls
Modification
NumpyToPIL
andPILToNumpy
;Use cases
1. Use some vision Augs Surrounded by
NumpyToPIL
and'PILToNumpy
(Recommendation)Surrounded by
dict(type='NumpyToPIL', to_rgb=True),
anddict(type='PILToNumpy', to_bgr=True),
2. Use vision Augs and ToTensor&Normalize
Make sure have coverted to RGB-Numpy format;
dict(type='NumpyToPIL', to_rgb=True)
3. USe Augs but no ToTensor&Normalize
Checklist
Before PR:
After PR: