Skip to content
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

Add Shear augmentation. #3656

Merged
merged 25 commits into from
Sep 23, 2020
Merged

Add Shear augmentation. #3656

merged 25 commits into from
Sep 23, 2020

Conversation

v-qjqs
Copy link
Contributor

@v-qjqs v-qjqs commented Aug 31, 2020

This PR implements Shear augmentation, and clean up the irrelevant commits.

@v-qjqs v-qjqs mentioned this pull request Aug 31, 2020
@codecov
Copy link

codecov bot commented Aug 31, 2020

Codecov Report

Merging #3656 into master will increase coverage by 0.61%.
The diff coverage is 86.42%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master    #3656      +/-   ##
==========================================
+ Coverage   60.84%   61.45%   +0.61%     
==========================================
  Files         213      213              
  Lines       15135    15345     +210     
  Branches     2587     2608      +21     
==========================================
+ Hits         9209     9431     +222     
+ Misses       5459     5441      -18     
- Partials      467      473       +6     
Flag Coverage Δ
#unittests 61.45% <86.42%> (+0.61%) ⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files Coverage Δ
mmdet/models/dense_heads/rpn_test_mixin.py 83.87% <0.00%> (ø)
mmdet/core/mask/structures.py 90.12% <76.66%> (-1.18%) ⬇️
mmdet/datasets/pipelines/auto_augment.py 91.05% <89.52%> (+43.68%) ⬆️
mmdet/__init__.py 94.11% <100.00%> (ø)
mmdet/datasets/pipelines/__init__.py 100.00% <100.00%> (ø)
mmdet/models/roi_heads/mask_heads/fcn_mask_head.py 74.67% <100.00%> (+0.16%) ⬆️
mmdet/models/roi_heads/mask_heads/maskiou_head.py 97.84% <100.00%> (+0.04%) ⬆️
mmdet/datasets/custom.py 51.42% <0.00%> (ø)
mmdet/models/losses/mse_loss.py 100.00% <0.00%> (ø)
mmdet/models/losses/smooth_l1_loss.py 100.00% <0.00%> (ø)
... and 34 more

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update a10d24d...d7d6da3. Read the comment docs.

@v-qjqs v-qjqs requested a review from ZwwWayne August 31, 2020 02:48
_MAX_LEVEL = 10


def level_to_value(level, max_value):
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Will this method be used by multiple transforms?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yeah, it will be used for another aug like translate, rotate, etc.

return (level / _MAX_LEVEL) * max_value


def random_negative(value, random_negative_prob):
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

and this

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yeah, it will be used for another aug like translate, rotate, etc.

@hellock hellock merged commit 868f7e5 into open-mmlab:master Sep 23, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants