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

How to split the 50% uncompressed videos and 50% compressed videos in training dataset? #7

Closed
StevenTony611 opened this issue Sep 7, 2022 · 3 comments

Comments

@StevenTony611
Copy link

In the paper, we got the training dataset split two parts: 50% uncompressed videos and 50% compressed videos, but we can't find how to split the training dataset. It's so confusing!

@ericzw
Copy link
Member

ericzw commented Sep 7, 2022

please see the function

def folder_change1(folder): if 'X4' in folder: if np.random.uniform() > 0.5: pass else: crf_folder_choice = random.choice([0,15,25,35]) folder = folder.replace('X4_start1', CRF_FOLDER[crf_folder_choice]) elif 'sequences_BD' in folder: if np.random.uniform() > 0.5: pass else: crf_folder_choice = random.choice([0,15,25,35]) folder = folder.replace('sequences_BD', VIMO[crf_folder_choice]) else: raise ValueError('please check dataset: {}'.format(folder)) return folder

in https://github.com/researchmm/FTVSR/blob/main/mmedit/datasets/base_sr_dataset.py

@ericzw
Copy link
Member

ericzw commented Sep 7, 2022

@StevenTony611
Copy link
Author

We find this function now and thank you very much! Good job!

@ericzw ericzw closed this as completed Sep 11, 2022
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

2 participants