[Feature] Add Rgb2Gray transform #227
Merged
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
Codecov Report
@@ Coverage Diff @@
## master #227 +/- ##
==========================================
+ Coverage 84.26% 84.35% +0.09%
==========================================
Files 90 90
Lines 4315 4340 +25
Branches 684 687 +3
==========================================
+ Hits 3636 3661 +25
Misses 537 537
Partials 142 142
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
xvjiarui
reviewed
Nov 7, 2020
Comment on lines
211
to
212
| # print(results) | ||
| print(results, results['img'].shape) |
|
|
||
| This transform calculate the weighted mean of input image channels with | ||
| ``weights`` and then expand the channels to ``out_channels``. When | ||
| ``out_channels`` equals 0, the number of output channels is the same as |
| @@ -463,6 +465,61 @@ def __repr__(self): | |||
| return self.__class__.__name__ + f'(crop_size={self.crop_size})' | |||
|
|
|||
|
|
|||
| @PIPELINES.register_module() | |||
| class Rgb2Gray(object): | |||
| Default: (0.299, 0.587, 0.114). | ||
| """ | ||
|
|
||
| def __init__(self, out_channels, weights=(0.299, 0.587, 0.114)): |
There was a problem hiding this comment.
Why using weighted sum instead of direct mmcv.rgb2gray.
There was a problem hiding this comment.
By this method, we can use the weights defined by us instead of fixed weights.
xvjiarui
reviewed
Nov 9, 2020
| assert len(img.shape) == 3 | ||
| assert img.shape[2] == len(self.weights) | ||
| weights = np.array(self.weights).reshape((1, 1, -1)) | ||
| img = (img * weights).sum(2) |
There was a problem hiding this comment.
We may use keep_dim=True. In this way, we don't need to expand dim.
|
Task linked: CU-fjrgpn Data preprocessing |
xvjiarui
approved these changes
Nov 9, 2020
bowenroom
pushed a commit
to bowenroom/mmsegmentation
that referenced
this pull request
Feb 25, 2022
* add transformer Rgb2Gray * restore * fix self.weights * restore * fix code * restore * fix syntax error * restore
aravind-h-v
pushed a commit
to aravind-h-v/mmsegmentation
that referenced
this pull request
Mar 27, 2023
…ab#227) add add_noise method in more schedulers
wjkim81
pushed a commit
to wjkim81/mmsegmentation
that referenced
this pull request
Dec 3, 2023
wipe out the extra gpu memony cost by set the default map_location as 'cpu'
sibozhang
pushed a commit
to sibozhang/mmsegmentation
that referenced
this pull request
Mar 22, 2024
* init commit * fix download annotations * parse hvu tags * add downloading & trimming scripts * add file list generation * finish hvu datatools * resolve comments * init commit * fix download annotations * parse hvu tags * add downloading & trimming scripts * add file list generation * finish hvu datatools * resolve comments * update changelog * Update data_preparation.md Co-authored-by: Jintao Lin <528557675@qq.com>
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.
No description provided.