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

train自己的数据报错 #14

Open
huang6886 opened this issue May 16, 2019 · 15 comments
Open

train自己的数据报错 #14

huang6886 opened this issue May 16, 2019 · 15 comments

Comments

@huang6886
Copy link

大神您好,想针对自己的问题做个尝试,有两个问题想请教您,关于MPII标注的数据结构,是否就是 picturename minbox.x minbox.y maxbox.x maxbox.y point1.x point1.y ........
另外,我自己尝试运行trainMobileCPM,发现缺少了‘import dataset.datagen_para_branch as paral’,添加后出现RuntimeError :
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.
@huang6886
Copy link
Author

初步定位是datagen_para_branch.py下面的 self.manager = Manager()所产生的,实在能力有限,只能求大神来解答

@mpskex
Copy link
Owner

mpskex commented May 16, 2019 via email

@mpskex
Copy link
Owner

mpskex commented May 16, 2019 via email

@huang6886
Copy link
Author

您好,关于Manager()的实现,我看到直接指向了SyncManager,SyncManager内部感觉都是对register的操作啊,没有看到wrapper,不知道是不是自己是在太弱了,还望指导。

@mpskex
Copy link
Owner

mpskex commented May 17, 2019 via email

@huang6886
Copy link
Author

谢谢指导,可惜在下还是愚钝,没有搞明白您的意思。我的理解是您在main中调用了datagen_para_branch这个文件里的DataGenParaWrapper类,您是说这个类不需要调用么?我试了删除了,发现报如下ERROR:
File "D:\TF\Convolutional-Pose-Machine-tf-master\datagen.py", line 459, in generator
return self._aux_generator(*args, **kwargs)
TypeError: _aux_generator() got an unexpected keyword argument 'norm'

@mpskex
Copy link
Owner

mpskex commented May 17, 2019 via email

@huang6886
Copy link
Author

谢谢指导,不过发现去掉了就出现了如下错误,似乎和另一个未解决的问题一致了。
return self._aux_generator(*args, **kwargs)
TypeError: _aux_generator() got an unexpected keyword argument 'norm'

@mpskex
Copy link
Owner

mpskex commented May 20, 2019 via email

@huang6886
Copy link
Author

谢谢你,有一个关于模型的问题,想向您请教下,主要是关于点的遮蔽的问题的,目前遮蔽点的标注一般是[-1,-1]吧,我理解是这个数值直接用于训练(heatmap为空),后面的输出也是根据输出对应处的heatmap来求取点的坐标吧?应该没有一个专门的输出处表征该点是否遮挡吧?另外,您blog里说的节点间的关系,我理解CPM的级联利用的还是从粗到细的过程加速模型传播速度吧,是不是并没有真正利用节点之间的关系呢?

@mpskex
Copy link
Owner

mpskex commented May 27, 2019 via email

@huigoing
Copy link

你好,请问dataset.txt文件是怎么生成的,用的是mpii数据集还是coco2017数据集?

@mpskex
Copy link
Owner

mpskex commented Aug 11, 2019 via email

@huigoing
Copy link

huigoing commented Aug 11, 2019 via email

@mpskex
Copy link
Owner

mpskex commented Dec 18, 2019

输出的格式就在dataset mpii里,但是代码我现在没有。可以使用hdf5来读写mat,然后mpii的存储方式可能有点奇怪,但是mpii的官网有matlab代码。可以使用那个代码转换成dataset mpii接受的格式。

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

3 participants