Add down_sampling.py for generating LQ image from GT image. #222
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
…required in LIIF.
innerlee
reviewed
Mar 13, 2021
| Args: | ||
| scale_min (int): The minimum of upsampling scale. Default: 1. | ||
| scale_max (int): The maximum of upsampling scale. Default: 4. | ||
| inp_size (int): The input size, i.e. cropped lr patch size. |
innerlee
reviewed
Mar 13, 2021
|
|
||
| Args: | ||
| scale_min (int): The minimum of upsampling scale. Default: 1. | ||
| scale_max (int): The maximum of upsampling scale. Default: 4. |
There was a problem hiding this comment.
is this min to max range inclusive or exclusive
innerlee
reviewed
Mar 13, 2021
|
|
||
| Args: | ||
| results (dict): A dict containing the necessary information and | ||
| data for augmentation. |
There was a problem hiding this comment.
Clearly specify which keys are required, which are modified
innerlee
reviewed
Mar 13, 2021
| if isinstance(size, int): | ||
| size = (size, size) | ||
| if isinstance(img, np.ndarray): | ||
| return np.asarray(Image.fromarray(img).resize(size, Image.BICUBIC)) |
There was a problem hiding this comment.
- Will cv2.resize or mmcv.imresize work here?
- Is the PIL image a hard requirement
innerlee
reviewed
Mar 13, 2021
| if isinstance(size, int): | ||
| size = (size, size) | ||
| if isinstance(img, np.ndarray): | ||
| return np.asarray(Image.fromarray(img).resize(size, Image.BICUBIC)) |
There was a problem hiding this comment.
- Will cv2.resize or mmcv.imresize work here?
- Is the PIL image a hard requirement?
Codecov Report
@@ Coverage Diff @@
## master #222 +/- ##
==========================================
- Coverage 81.71% 81.69% -0.02%
==========================================
Files 148 149 +1
Lines 7055 7102 +47
Branches 1047 1052 +5
==========================================
+ Hits 5765 5802 +37
- Misses 1171 1179 +8
- Partials 119 121 +2
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
innerlee
reviewed
Mar 14, 2021
| Scale will be in the range of [scale_min, scale_max). | ||
| """ | ||
|
|
||
| def __init__(self, scale_min=1, scale_max=4, patch_size=None): |
There was a problem hiding this comment.
add interpolation and backend here, and pass them to resize_fn
innerlee
reviewed
Mar 14, 2021
| modified 'gt', supplement 'lq' and 'scale' to keys. | ||
| """ | ||
| img = results['gt'] | ||
| scale = random.uniform(self.scale_min, self.scale_max) |
innerlee
reviewed
Mar 14, 2021
|
|
||
|
|
||
| @PIPELINES.register_module() | ||
| class DownSampling: |
There was a problem hiding this comment.
DownSampling -> RandomDownSampling
innerlee
reviewed
Mar 14, 2021
| """Generate LQ image from GT (and crop). | ||
|
|
||
| Args: | ||
| scale_min (int): The minimum of upsampling scale, inclusive. |
innerlee
reviewed
Mar 14, 2021
|
|
||
| @PIPELINES.register_module() | ||
| class DownSampling: | ||
| """Generate LQ image from GT (and crop). |
There was a problem hiding this comment.
Give a detailed description here. e.g. it randomly pick a scale
innerlee
reviewed
Mar 14, 2021
| if isinstance(size, int): | ||
| size = (size, size) | ||
| if isinstance(img, np.ndarray): | ||
| return imresize(img, size, interpolation='bicubic', backend='pillow') |
There was a problem hiding this comment.
do not hardcode bicubic here
innerlee
reviewed
Mar 14, 2021
| return imresize(img, size, interpolation='bicubic', backend='pillow') | ||
| elif isinstance(img, torch.Tensor): | ||
| image = imresize( | ||
| img.numpy(), size, interpolation='bicubic', backend='pillow') |
innerlee
approved these changes
Mar 15, 2021
Yshuo-Li
added a commit
to Yshuo-Li/mmediting
that referenced
this pull request
Jul 15, 2022
…ab#222) * Add down_sampling.py for generating LQ image from GT image, which is required in LIIF. * Add '__repr__' and test_down_sampling.py. * Add docstring, rename parameter and change the function of resize. * Fine-tuning code and docstring of RandomDownSampling class. * Remove hardcode of bicubic and pillow. Co-authored-by: 李尹硕 <SENSETIME\[email protected]>
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.
Add down_sampling.py for generating LQ image from GT image, which is required in Learning Continuous Image Representation with Local Implicit Image Function