[Feature] Add Rerange transform #228
Conversation
Codecov Report
@@ Coverage Diff @@
## master #228 +/- ##
==========================================
+ Coverage 84.35% 84.43% +0.07%
==========================================
Files 90 90
Lines 4340 4361 +21
Branches 687 688 +1
==========================================
+ Hits 3661 3682 +21
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.
|
| results['img_rerange_cfg'] = dict( | ||
| min_value=self.min_value, max_value=self.max_value) |
There was a problem hiding this comment.
What's the purpose of img_rerange_cfg?
|
Task linked: CU-fjrgpn Data preprocessing |
| results (dict): Result dict from loading pipeline. | ||
|
|
||
| Returns: | ||
| dict: Reranged results, 'img_rerange_cfg' key is added into |
There was a problem hiding this comment.
Sorry, I forget it!
| img_min_value = np.min(img) | ||
| img_max_value = np.max(img) | ||
| # rerange to [0, 1] | ||
| img = (img - img_min_value) / (img_max_value - img_min_value) |
There was a problem hiding this comment.
If we are reading an image with range [0.1, 1] (no pixel is black), 0.1 will be mapped to min_value (default 0), which is not ideal.
There was a problem hiding this comment.
That's exactly what it's going to do.
* add rerange transform * restore * delete rerange config * delete rerange config hint * add min < max assert * restore
No description provided.