-
Notifications
You must be signed in to change notification settings - Fork 9
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
problem with videos names #5
Comments
Even when I changed the names in KoNViD-1k_data.mat, I faced probelms when excuting extracted_SlowFast_features_VQA.py, |
Please use the KoNViD-1k videos downloaded from the link https://drive.google.com/file/d/1p-6FJR6pPa9Fh-Va995t0Ycb1Dq9hBJG/view?usp=sharing. |
Thanks for your answer, but if I need to train on other data sets, how do I go about it? |
The video names in other datasets match the video names in the corresponding datasets that are downloaded in public. |
Thanks for your answer, but I would like to train your model on other datasets, for example LIVE-VQC, I only found custom scripts for konvid, LSVQ and YouTube UGC. |
For LIVE-VQC, you can write your custom script. It is easy and you only need to provide the video names and the corresponding MOSs. |
Thank you ^^ |
I tried to train my owen model, but it's a bit confusing, even train.py is customized for the existing dataset , how to change it please to train on any database? |
I'm sorry, the file in the link doesn't exist anymore, can you share it again, thanks! |
Hello, I want to train your model on the KonViD-1k database, I used your script extract_frame_konvid1k.py, however, I think the KoNViD-1k_data.mat file contains different names of the dataset, ('8171831850_cut_centercrop_960x540_8s.mp4').
The text was updated successfully, but these errors were encountered: