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.

Sign up for GitHub

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

Jump to bottom

怎么定位模型训练结果有误的原因？ #13

Open

guitLearn opened this issue Jun 8, 2024 · 0 comments

guitLearn commented Jun 8, 2024

首先感谢您提供了这个超棒的方案。我在根据https://github.com/ekzhang/semantic-segmentation.git这个进行模型训练时遇到训练结果一直有较大误差的问题。能否提供下什么建议或思路？谢谢。
下面是我的模型训练结果：
validating[Iter: 1 / 1]
IoU:
Id label iU_1.0 TP FP FN Precision Recall

0 background 99.02 98.40 0.00 0.01 1.00 0.99
1 left_line 0.00 0.00 inf nan 0.00 nan
2 right_line 46.21 0.50 0.53 0.64 0.66 0.61
Mean: 48.41

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment