YOWO icon indicating copy to clipboard operation
YOWO copied to clipboard

Is there anyway to test on unknown video?

Open zhaoleo1111 opened this issue 3 years ago • 7 comments

cau you give me a support for test on my own video?

zhaoleo1111 avatar Nov 29 '20 11:11 zhaoleo1111

Hi,I want it ,too. there is a project for me to adress it by using action localization.

GeLee-Q avatar Mar 11 '21 02:03 GeLee-Q

I will soon update the paper with AVA dataset results. The repo will also be updated accordingly. I will provide also a webcam demo.

okankop avatar Mar 12 '21 15:03 okankop

YOWO is extended for AVA dataset! Please check out the updated repo!

okankop avatar Mar 29 '21 17:03 okankop

@okankop Thanks for your great effort. Can I use test_video_ava.py for ucf24 or any other custom dataset?

MoaazAbdulrahman avatar Apr 06 '21 15:04 MoaazAbdulrahman

@MoaazAbdulrahman I have written test_video_ava.py for AVA dataset. For ucf24 dataset, you need to use YOWO model trained on ucf24 and modify the inference part according to ucf24. Because, ucf24 and ava are quite diferent as higlighted in Table 1 of updated_paper.

okankop avatar Apr 06 '21 16:04 okankop

@okankop Thank you. I just need to know if I need to preform any preprocessing to the input image other than resizing? I am working on building inference for ucf24 dataset.

MoaazAbdulrahman avatar Apr 27 '21 15:04 MoaazAbdulrahman

@MoaazAbdulrahman were you able to do that?

ronnie659 avatar Apr 29 '22 11:04 ronnie659