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

关于车道线的评估方式 #148

Open
q36101 opened this issue Jun 2, 2023 · 9 comments
Open

关于车道线的评估方式 #148

q36101 opened this issue Jun 2, 2023 · 9 comments
Labels
lane detection question Further information is requested

Comments

@q36101
Copy link

q36101 commented Jun 2, 2023

请问tusimple、culane和llamas dataset,在评估f1-score时,是使用instance(多类别)还是binary(二分类)的结果?在测试llamas时,因为车道线断断续续,我的instance测试效果很差,与其他论文f1-score=80-90差太多。

@voldemortX
Copy link
Owner

@q36101 你说的多类别指的是区分实线虚线吗?

@q36101
Copy link
Author

q36101 commented Jun 2, 2023 via email

@voldemortX
Copy link
Owner

我指的多类别是llamas dataset 的label ,将每一条车道线视为一类(跟tusimple一样),而不考虑实线和虚线。
但是如果有区分实线和虚线的方法我也想知道。

Zhengyang Feng @.***> 於 2023年6月2日 週五 下午5:04寫道:

@q36101 https://github.com/q36101 你说的多类别指的是区分实线虚线吗?


Reply to this email directly, view it on GitHub
#148 (comment),
or unsubscribe
https://github.com/notifications/unsubscribe-auth/AZA5HJAO7BGO5XLOAAYCWU3XJGUCNANCNFSM6AAAAAAYYATKXY
.
You are receiving this because you were mentioned.Message ID:
@.***>

根据你的描述,各个数据集的评测都不是多分类的吧

@q36101
Copy link
Author

q36101 commented Jun 2, 2023 via email

@voldemortX
Copy link
Owner

@q36101 好像我理解错你的定义了。所有的评测都是instance为单位的,计算预测线(转化为点集合)和GT线(转化为点集合)之间的某种几何距离判定正确性。或者以点为单位计算acc(tusimple)。

@q36101
Copy link
Author

q36101 commented Jun 2, 2023 via email

@voldemortX
Copy link
Owner

voldemortX commented Jun 2, 2023

应该理解为类似目标检测的评测,而不是分割。单位是instance。

你可以看llamas的python代码理解一下。

@voldemortX voldemortX added question Further information is requested lane detection labels Jun 5, 2023
@q36101
Copy link
Author

q36101 commented Jun 10, 2023

您好,請問一般我們評估tusimple、culane和llamas dataset時,如何將車道標記的預測圖像轉換為車道標記所在的車道坐標列表,並將其保存為 JSON 文件?是網路生成的嗎,抑或是不同dataset有不同的生成方式。

@voldemortX
Copy link
Owner

@q36101 不同算法有不同的输出格式(分割图,曲线表达式,点序列),根据数据集评测脚本的要求(如y坐标每10pixel采样一个x坐标),自行转换结果格式。你说的json文件是tusimple的格式吧,其他数据集是txt文件。你可以在这里找到转换的逻辑。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
lane detection question Further information is requested
Projects
None yet
Development

No branches or pull requests

2 participants