-
Notifications
You must be signed in to change notification settings - Fork 107
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
The pretrained model of ShapeNet55 #119
Comments
@wangxue7558 Hello, I have the same question, did you reach to any answer!? |
@mostafa501 Hello, I think because the PCN dataset and the ShapeNet55 dataset are built differently, you can focus on the following, one is built from a different perspective, the other is built by cropping. I guess it's because of the dataset that the demo/ is so different. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hello author, when I used the pretrained model you provided for verification, I found that for /demo, ShapeNet55_models effect is very poor, even worse than PCN_models effect, I tried many methods have not solved. I want to know if the ShapeNet55 pretrained model you provided is the best? Secondly, if the input point cloud needs to be normalized to the interval of [-1,1] and do other work?
The text was updated successfully, but these errors were encountered: