[add] A PairRandomCrop for both input and target.#221
Closed
Time1ess wants to merge 5 commits intopytorch:masterfrom
Closed
[add] A PairRandomCrop for both input and target.#221Time1ess wants to merge 5 commits intopytorch:masterfrom
Time1ess wants to merge 5 commits intopytorch:masterfrom
Conversation
When we crop images in Semantic Segmentation and other related work, we want to crop both input image and its target image, however, RandomCrop generates a new random positon each time being called, PairRandomCrop instead, will use the same position twice.
Member
|
Hi, |
Contributor
|
Hi, this functionality can now be achieved in your own dataset using the new functional interface in from torchvision.transforms import crop, RandomCrop
class MyDataset(Dataset):
def __init__(self, crop_size):
super(Dataset, self).__init__()
self.crop_size = crop_size
def __getitem__(self, idx):
img = self.get_img(idx)
target = self.get_target(idx)
i, j, h, w = RandomCrop.get_params(img, self.crop_size)
img = crop(img, i, j, h, w)
target = crop(img, i, j, h, w)
return img, target |
rajveerb
pushed a commit
to rajveerb/vision
that referenced
this pull request
Nov 30, 2023
* adding code for data generation * fix imports in run_expansion * more fixes, and added readme * More fixes
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
RandomCrop does not support crop both image and target at same position, each time we call RandomCrop it will generate a new position which is not what we want.
This PairRandomCrop will remember the crop position of the image and use this same position to crop the target(vice versa).
It follows this idea:
A dict is used to remember the crop position of the image, key is the os.getpid() and value is the position.
So each time we crop a image, PairRandomCrop will generate a new position, when it comes to the target, it will pop and reuse the position.