We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
网络结构是ENet, 我使用TUSimple训练集训练了25个epoch, Best val_loss = 0.055766,比log文件夹中原有的best model的验证损失更小, 但是instance_output结果如图2(效果不如示例图1) 这是为什么呢,谢谢。
The text was updated successfully, but these errors were encountered:
你现在的输出只是ENet Discriminative loss一侧的输出结果,这些是我已经复现了的内容,并不是最终实例输出。 在你现在的输出上,还需要做匹配和串线,最简单的方法是:把语义分割的mask匹配到实例分割的结果里,只保留mask=1的区域,然后无监督划分实例类别。也可以参考LaneNet作者的方法来处理。
Sorry, something went wrong.
我明白了,就是用语义二分的结果把mask=1的保留出来,再用类似原文中mean shift的聚类方法得到多个实例。
没错。
No branches or pull requests
网络结构是ENet,
我使用TUSimple训练集训练了25个epoch,
Best val_loss = 0.055766,比log文件夹中原有的best model的验证损失更小,
但是instance_output结果如图2(效果不如示例图1)
这是为什么呢,谢谢。
The text was updated successfully, but these errors were encountered: