We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
When I load the UBody dataset, I found the number of images(train 71299) is much less than the paper's show number(>1051K).
Could you tell me the right number of the images? @linjing7
Thanks a lot.
This is the screenshot of my output of the number of images:
This is the paper's show out number of the images:
The text was updated successfully, but these errors were encountered:
inter_scene_test_list.npy. train: 60971
60971+71299 << 1051K
Sorry, something went wrong.
Hi, in our dataloader, we sample an image every 10 frames. You can set cfg.train_sample_interval to a smaller number and you will get more images.
cfg.train_sample_interval
OSX/data/UBody/UBody.py
Line 88 in 118cf97
No branches or pull requests
When I load the UBody dataset, I found the number of images(train 71299) is much less than the paper's show number(>1051K).
Could you tell me the right number of the images? @linjing7
Thanks a lot.
This is the screenshot of my output of the number of images:
This is the paper's show out number of the images:
The text was updated successfully, but these errors were encountered: