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

The result of tf_nndistance.nn_distance is zero #3

Open
Shaofei-Li opened this issue Sep 24, 2020 · 4 comments
Open

The result of tf_nndistance.nn_distance is zero #3

Shaofei-Li opened this issue Sep 24, 2020 · 4 comments

Comments

@Shaofei-Li
Copy link

When I "make -f makefile_10.0 clean" and "make -f makefile_10.0", I can use the tf_nndistance.nn_distance function ,but no matter what two sets of point clouds I enter, the returned distance and idx are zero. How can I use the function correctly?Thanks

@Shaofei-Li
Copy link
Author

I have found that if I use placehoulder and feed the value to run ,and I will get zero ,but if I use array and transform it to tensor and run ,the result will be right.

@renmaqilong
Copy link

make: makefile_10.0: 没有那个文件或目录
make: *** 没有规则可以创建目标“makefile_10.0”。 stop

@renmaqilong
Copy link

image
The loss is very low at the beginning of the training process. Is this all right?

@renmaqilong
Copy link

@LSFMESSI The loss is very low at the beginning of the training process. Is this all right?

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

2 participants