Skip to content
This repository has been archived by the owner on Jun 25, 2024. It is now read-only.

A question about PriorBox layer in ssd_layers.py #45

Open
PKUWison opened this issue Mar 1, 2017 · 3 comments
Open

A question about PriorBox layer in ssd_layers.py #45

PKUWison opened this issue Mar 1, 2017 · 3 comments

Comments

@PKUWison
Copy link

PKUWison commented Mar 1, 2017

I want to ask two questions about the PriorBox layer in your work. What's the meaning of min_szie and max_size? Maybe there are some relationships between these parameters and S__min, S__max in paper. Really hope you can give me replies. Thank you! @rykov8

@rykov8
Copy link
Owner

rykov8 commented Mar 7, 2017

@PKUWison they should be related to s_min and s_max, but in the original implementation they are just hard-coded. I think, that the authors experimented with these values, and in the paper they provide only some of the heuristics.

@PKUWison
Copy link
Author

Really thanks for your answers. I have another question, I want to run the SSD model on a public dataset. But the labels of the dataset are saved in .mat file. I don't know how to transfer the .mat file to the .XML file. And I don't know whether the .XML file has any rigid requirements or not. Thanks in advance. @rykov8

@rykov8
Copy link
Owner

rykov8 commented Mar 10, 2017

@PKUWison you could use loadmat fucntion from scipy. Actually, you don't need to convert annotations to xml, I use a little bit more convenient (at least for me) format. It was described several times in issues, e.g. in #15

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

No branches or pull requests

2 participants