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

rpn层输出的proposals中带有nan值问题 #11

Open
Julius-ZCJ opened this issue Jun 18, 2020 · 2 comments
Open

rpn层输出的proposals中带有nan值问题 #11

Julius-ZCJ opened this issue Jun 18, 2020 · 2 comments

Comments

@Julius-ZCJ
Copy link

我在运行train_model.py文件时,我发现他会自动中断,而且没有任何提示。通过debug我发现实在
proposals = self.rpn_head.get_proposals(rpn_probs, rpn_deltas, img_metas) 这行代码中输出的proposals 带有nan值,导致在roi_align.py中使用tf.image.crop_and_resize可能里面出错了,导致程序退出了,想问下作者有碰到这种情况么,我要怎么解决呢

@Julius-ZCJ
Copy link
Author

我已经看到评论有人提到这个问题了,不好意思,刚刚没看到

现在我有发下你发布在百度云盘的权重加载不进去,报错:
ValueError: Layer #0 (named "res_net") expects 0 weight(s), but the saved weights have 624 element(s).
也是和这个评论说的一样么?
#4

@Viredery
Copy link
Owner

关于第一个问题,和#4是一样的,你更新成目前最新的代码后应该没问题了,你试下。如果有问题可以再提一下

第二个权重问题。你需要先跑一下网络来进行网络的初始构造。你看下我每个jupyter文件里面加载权重之前,都有一行代码执行了一遍网络的前向传播

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

2 participants