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

40000轮visualization/eval效果不一致 #28

Open
KevinSONG729 opened this issue May 22, 2024 · 0 comments
Open

40000轮visualization/eval效果不一致 #28

KevinSONG729 opened this issue May 22, 2024 · 0 comments

Comments

@KevinSONG729
Copy link

KevinSONG729 commented May 22, 2024

您好,我在复现代码过程中遇到了下述问题:
我使用kitti_mot数据集中的0002场景(所有图片)进行训练,并在40000轮训练结束后,运行了evaluate.py代码:
python train.py --config xxx/kitti_reconstruction.yaml source_path=xxx model_path=xxx start_frame=0 end_frame=232
python evaluate.py --config xxx/kitti_reconstruction.yaml source_path=xxx model_path=xxx start_frame=0 end_frame=232
yaml文件配置保持原始设置。但是发现训练过程中输出的visualization文件夹中的图片以及训练结束后eval文件夹中的图片,和使用evaluation.py输出的图片效果不一致,后者在非天空的区域明显变暗:
visiualization/40000_148.png:
image
训练结束时自动eval的结果187.png:
image
手动运行evaluate.py的结果187.png(40000iter):
image
手动运行evaluate.py的结果187.png(7000iter):
image
发现7000iter时evaluation.py的运行结果比较合理,可是40000iter的evaluation.py输出结果与训练阶段的输出结果出现了明显的不一致。因此想要请问下,出现上述问题是否是哪里的配置不当导致的,如何修复该错误?非常期待您的回复!

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

1 participant