extract_feaures

[Nirvana-feng]

Hello, I want to ask if you want to extract and save video frames locally in advance. I tried to extract and save the video frame to the local, but the following error occurred when running It should be that I didn't read the image, so first ask me what I should do to extract features. This is the video frame I extracted The underlined part is the name of the video

[atelili]

Hello, can you send me arguments used with features_extraction.py ?

[Nirvana-feng]

The underlined part is the file path of the video

[atelili]

The problem in the path of videos that's why the script can't read them, can you please send me your csv file konvid.csv ?

[Nirvana-feng]

This is a csv file

[atelili]

you have to add the extension for all videos (.mp4) in the csv file.

[Nirvana-feng]

Okay, thank you I'll try

[atelili]

You're welcome, please close this issue if that works.

[Nirvana-feng]

It's still not possible. Is it my file address

[atelili]

The problem in your csv file, or in your folder path, the script cannot read the path of your videos, in fact, it takes the path, in your case: F:\data\koNViD_1k and add '/' + the name of the video, so it has to be like this: F:\data\koNViD_1k\16515618.mp4.

[Nirvana-feng]

When I set flag=0, the program starts running. When flag=1, the same error as before will be reported. Is it because the file path should be changed to the video frame saving path when flag=1

[atelili]

Ok, if you use it on videos, the flag should remain 0. This is mentioned in the help when you type extract_features.py -h . I will close this issue, don't hesitate to contact me if you have any problems. Kind regards,

[Nirvana-feng]

Okay Thank you