Skip to content
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

Could you give some suggestions about how to train on my own dataset #22

Open
scut-salmon opened this issue Feb 11, 2018 · 5 comments
Open

Comments

@scut-salmon
Copy link

How can I obtain my own pickle files in VGG/models base on my dataset ?

@gooa1121
Copy link
Collaborator

Hi, I pushed some files to train new models on different dataset. You can take a look at the guide and try the files mentioned in it. Let me know if you have any error or problem when trying it.

@lc-git
Copy link

lc-git commented Mar 21, 2018

@gooa1121 Thank you for your work. When retraining the Gaussian and regression model, what labels do I need to use? The body parts mask? like background subtraction retraining?

@gooa1121
Copy link
Collaborator

Following the section 3.2.2 in the main paper, the label is the normalized displacement between the coordinate of the pixel and the center of the bounding box it belongs to. For the pixels not belonging to any bounding box, you can give it any number <= -1

@lc-git
Copy link

lc-git commented May 14, 2018

As you mentioned, label is the displacement between the pixel and the center so I think label has 2 channels. Why the shape of parts labels is (H, W, 5)? What does "5" mean? Thank you.

@gooa1121
Copy link
Collaborator

The first channel indicates foreground or background, 2nd and 3rd are the displacement to the center, 4th and 5th are the displacement to the right, bottom corner of the bounding box.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants