Support resize data augmentation according to original image size #291
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
…g_scale=None and retio_range is tuple)
Codecov Report
@@ Coverage Diff @@
## master #291 +/- ##
==========================================
+ Coverage 84.68% 84.88% +0.19%
==========================================
Files 90 90
Lines 4414 4425 +11
Branches 705 710 +5
==========================================
+ Hits 3738 3756 +18
+ Misses 536 531 -5
+ Partials 140 138 -2
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
xvjiarui
reviewed
Dec 9, 2020
xvjiarui
reviewed
Dec 9, 2020
Comment on lines
21
to
22
| and multiply it with the image scale. When img_scale is None, img_scale is | ||
| the shape of image in results (img_scale = results['img'].shape[:2]). |
There was a problem hiding this comment.
Suggested change
| and multiply it with the image scale. When img_scale is None, img_scale is | |
| the shape of image in results (img_scale = results['img'].shape[:2]). | |
| and multiply it with the image scale. When img_scale is None, the image is resized based on the original size. |
xvjiarui
reviewed
Dec 10, 2020
xvjiarui
reviewed
Dec 10, 2020
Comment on lines
105
to
109
| if self.img_scale is None and mmcv.is_list_of(self.img_ratios, float): | ||
| img_scale = results['img'].shape[:2] | ||
| self.img_scale = [(int(img_scale[0] * ratio), | ||
| int(img_scale[1] * ratio)) | ||
| for ratio in self.img_ratios] |
There was a problem hiding this comment.
self.img_scale is set after first __call__, so for the second image, it won't set again.
There was a problem hiding this comment.
fixed it and please check it again!
xvjiarui
reviewed
Dec 10, 2020
xvjiarui
approved these changes
Dec 14, 2020
|
Task linked: CU-herb9d Resize data aug |
bowenroom
pushed a commit
to bowenroom/mmsegmentation
that referenced
this pull request
Feb 25, 2022
…en-mmlab#291) * Support resize data augmentation according to original image size (img_scale=None and retio_range is tuple) * fix docstring * fix bug * add unittest * img_scale=None in TTA * fix bug * add unittest * fix typos * fix bug
wjkim81
pushed a commit
to wjkim81/mmsegmentation
that referenced
this pull request
Dec 3, 2023
* udp for bottom_up paradigm in 'switch' method * fix some code style, pylint problems * fix two code style, pylint problems * fix some code style, pylint problems * fix some code style, pylint problems * UDP for top-down paradigm * fix code style problems * fix some code style problems * fix some code style problems * fix some code style and explanation problems * fix some code style problems * simplify the implementation of 'pose_dark' and fix its usage error in top-down paradigm. * fix some code style problems * fix the conflict * fix the code style problems in JointsMSELoss_Combined and fix the testing problem by setting the default kpd as '0.0546875'. * fix some code style problems * fix some code style problems * fix some code style problems * fix some code style problems * fix some code style problems * add a config for unbiased data processing with GaussianHeatmap target in top-down paradigm and hrnet structure for bottom-up paradigm
sibozhang
pushed a commit
to sibozhang/mmsegmentation
that referenced
this pull request
Mar 22, 2024
* [Feature] Add motion decoder. * Fix the bad double loop with numpy broadcast and slice. * Remove FFMpegDecodeMotionVector and fix review issues. Minor. * Minor. * Minor fix. * Minor fix and change changelog. * Minor fix for pyint. * Rename the field mvs. Minor fix changelog. * More unittest. * Revised according to review. Fix typo. * Minor fix. * parse vectors to staticmethod.. fix.
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.
Support resize data augmentation according to original image size (img_scale=None and ratio_range is tuple).