-
Notifications
You must be signed in to change notification settings - Fork 19
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 get train, valid, test #10
Comments
Same problem, please tell me where can get these files. |
I have a question about the annotation file which localed in ./datasets/annotations_all/msrvtt_caption/train.jsonl, in video_downstream_datasets.py it need a key name's "golden_captions" which is not exist in my jsonl file. Am i get the wrong annotation file? |
please tell me where can get these files. |
Can you please tell me where to get these files? |
It's easy, you just need to look at the number of captions corresponding to a video_id, if it corresponds to only one sentence then the key is caption, if it corresponds to multiple sentences then the key is golden_captions. |
I have created an annotated file of the MSVD dataset that you are free to use, |
thank you,best,
…------------------ 原始邮件 ------------------
发件人: ***@***.***>;
发送时间: 2024年12月5日(星期四) 晚上7:03
收件人: ***@***.***>;
抄送: ***@***.***>; ***@***.***>;
主题: Re: [X-PLUG/mPLUG-2] how to get train, valid, test (Issue #10)
I have created an annotated file of the MSVD dataset that you are free to use, not provided here as the original MSVD video can be downloaded at https://www.cs.utexas.edu/~ml/clamp/videoDescription/.
Uploading annotations_all.zip…
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
You're welcome, bro. |
train_file: 'datasets/annotations_all/msrvtt_caption/train.jsonl'
test_file: 'datasets/annotations_all/msrvtt_caption/test.jsonl'
video_root: "datasets/MSRVTT/data/MSRVTT/videos/all"
i get YouTubeClips, AllVideoDescriptions.txt at https://www.cs.utexas.edu/users/ml/clamp/videoDescription/ (Videos, annotation)
and get splits from https://github.com/albanie/collaborative-experts/blob/master/misc/datasets/msvd/README.md
The text was updated successfully, but these errors were encountered: