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

你好请问为什么会出现类似的问题 #18

Open
ruiqiyan opened this issue Aug 31, 2023 · 6 comments
Open

你好请问为什么会出现类似的问题 #18

ruiqiyan opened this issue Aug 31, 2023 · 6 comments

Comments

@ruiqiyan
Copy link

Failed to import tensorflow.
INFO - 2023-08-31 20:37:59,198 - test_pcn - Length of test dataset:1200
Loaded compiled 3D CUDA chamfer distance
INFO - 2023-08-31 20:38:05,548 - test_pcn - PointAttN's previous weights loaded.
INFO - 2023-08-31 20:38:05,550 - test_pcn - Testing...
INFO - 2023-08-31 20:38:38,501 - test_pcn - test [0/37]
Traceback (most recent call last):
File "test_pcn.py", line 108, in
test()
File "test_pcn.py", line 70, in test
if not os.path.isdir(os.path.join(os.path.dirname(args.load_model), 'all', str(label[j]))):
IndexError: tuple index out of range

@ruiqiyan
Copy link
Author

是由于我没有安装tensorflow吗

@WangJun-ZJUT
Copy link
Collaborator

您好!这个问题是超出索引造成的,请检查一下返回的lable是否正常。

@ruiqiyan
Copy link
Author

ruiqiyan commented Sep 1, 2023

您提供的预训练模型与yaml文件里的num_points: 2048并不相符。应该改为num_points: 16384

@ruiqiyan

This comment was marked as outdated.

@ruiqiyan
Copy link
Author

ruiqiyan commented Sep 2, 2023

您提供的预训练模型与yaml文件里的num_points: 2048并不相符。应该改为num_points: 16384

但是当我要生成点云结果把 save_vis 改为True时又会发生超出索引的报错

@WangJun-ZJUT
Copy link
Collaborator

您好,源码中生成点云的数量是根据yaml文件中的dataset自动变化的,与num_points参数无关。详见models/PointAttN.py

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