Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

gopro dataset #70

Open
Original-2 opened this issue Jul 21, 2023 · 5 comments
Open

gopro dataset #70

Original-2 opened this issue Jul 21, 2023 · 5 comments

Comments

@Original-2
Copy link

When downloading the dataset, it cannot be extracted as it is a damaged archive.

I have tested this on 2 devices across 3 networks and 2 operating systems.

@shacharp
Copy link

Try downloading from https://www.kaggle.com/datasets/darthvader4067/gopro

@wu-771190343
Copy link

May I ask if it is necessary to modify the image size in the dataset? The image size of the dataset I downloaded is 1280 * 720, which is a multiple of 256 * 256 and does not meet the requirements

@shacharp
Copy link

shacharp commented Aug 1, 2024

May I ask if it is necessary to modify the image size in the dataset? The image size of the dataset I downloaded is 1280 * 720, which is a multiple of 256 * 256 and does not meet the requirements

What requirement?
The code works with this DB without any modifications to the DB, if that's the question

@wu-771190343
Copy link

Due to the failure of the dataset link provided on GitHub to redirect, we downloaded an 8GB dataset from the GoPro official website. When training, prompt "File"/home/shaohua/200g/code/UFormer/train/../model. py ", line 969, in forwardx = x.view(B, H, W, C)Runtime Error: Shape '[4, 991, 991, 32]' is invalid for input of size 125829120 '. I think this may be due to differences in dataset size

@shacharp
Copy link

shacharp commented Aug 4, 2024

You can find the DB in here also:
https://github.com/swz30/MPRNet/tree/main/Deblurring/Datasets

I'm running this code on that DB without any code modifications regarding the dataset.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants