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
老师你好,我在训练[deep-hough-transform]这个方法的时候,使用SEL数据集训练,实验结果与论文结果相符,但是在可视化霍夫前后的特征图时,发现经过网络训练,霍夫前有直线的位置是较暗的,霍夫之后的特征图中霍夫变换焦点打分在应有直线的位置,亮度是更低的。在经过最后的卷积才反变为较亮的目标直线点位置(这似乎不太符合霍夫变换的逻辑,与原逻辑相反)。 请问这是什么原因?如何验证DHT模块中cuda反传代码的正确与否呢?下面是对0432.jpg这张图中间特征层可视化的结果。从上到下分别是1.检测图,2.DHT前,3.DHT后,4.DHT后并且经过卷积以后
The text was updated successfully, but these errors were encountered:
dht借助于deep cnn的feature表达,其原始语义与hough空间的不一定相同,属于预期现象,因为是端到端训练,模型会优化中间空间的表达以更适应当前任务。
cuda反传代码可以自己通过导函数的定义来验证。
Sorry, something went wrong.
No branches or pull requests
老师你好,我在训练[deep-hough-transform]这个方法的时候,使用SEL数据集训练,实验结果与论文结果相符,但是在可视化霍夫前后的特征图时,发现经过网络训练,霍夫前有直线的位置是较暗的,霍夫之后的特征图中霍夫变换焦点打分在应有直线的位置,亮度是更低的。在经过最后的卷积才反变为较亮的目标直线点位置(这似乎不太符合霍夫变换的逻辑,与原逻辑相反)。
请问这是什么原因?如何验证DHT模块中cuda反传代码的正确与否呢?下面是对0432.jpg这张图中间特征层可视化的结果。从上到下分别是1.检测图,2.DHT前,3.DHT后,4.DHT后并且经过卷积以后
The text was updated successfully, but these errors were encountered: