-
Notifications
You must be signed in to change notification settings - Fork 9
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
Evaluation on YUD #7
Comments
Hi, Fkluger, Yancong |
Thanks for taking the time! I am in a bit of a rush. If you could look into it within the next two weeks I would really appreciate it. I have now tried using the mappings from NYU, with the following config file:
and run the evaluation script with the SU3 checkpoint:
This works, but the results are worse than in your paper:
I have also tried using the correct focal length (
Is there anything I am missing? Thanks again! |
I will have to look into the details because there is some rescaling (in terms of image dimensions and focal length) when doing SU3-YUD (if I recall correctly). Say train on SU3 and then test on YUD:
I will try to find out the scripts. it seems they are not included in the initial repo. But unfortunately, I can not make any promises. |
Thanks, that's a good pointer. I have now tried the following: First, resize the images before feeding them into the network:
After prediction, de-normalize the VPs using SU3's focal length, then correct the aspect ratio, and finally normalize the VPs again:
This gives me these results:
Even a bit better than the paper for AA@3 and AA@5, but slightly worse for AA@10 |
Glad you made it work. As you probably have figured out, the scaling/mapping thing is somehow resolution-dependent, which is unfortunately a drawback of this solution. #7 (comment) |
feel free to reopen if you have further questions. |
Hi,
I am trying to reproduce your results on the YUD dataset, but I am unable to get it running.
In your paper, you say that you used a network trained on SU3 for the evaluation on YUD.
However, the
config/yud.yaml
file appears to assume a network trained on NYU instead.I changed it to match
su3.yaml
instead, but now I get this error:Sounds like there is a problem due to image size mismatch between YUD and SU3, but I don't know the root cause.
Could you kindly help me get this running?
Oh and I may have found a bug in the YUD dataloader. It expects the name of the file with the VP labels to contain the value of
C.io.num_nodes
:VanishingPoint_HoughTransform_GaussianSphere/vpd/datasets.py
Line 292 in 4b743cf
Meanwhile, the pre-processing script does not include this value in the file name:
VanishingPoint_HoughTransform_GaussianSphere/dataset/yud_process.py
Line 215 in 4b743cf
The dataloader then naturally throws an error because it can't find the npz file.
The text was updated successfully, but these errors were encountered: