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

inputs = tf.placeholder(name='img_inputs', shape=[None, *args.image_size, 3], dtype=tf.float32) #66

Open
Casi11as opened this issue Jun 11, 2020 · 6 comments

Comments

@Casi11as
Copy link

Casi11as commented Jun 11, 2020

No description provided.

@Casi11as Casi11as reopened this Jun 11, 2020
@Casi11as
Copy link
Author

暴力解决法,直接把*args.image改成112,112

@LeiiY
Copy link

LeiiY commented Nov 11, 2021

@Casi11as 你好,我这边是这样的,
image
然后卡在这一步
image
请问你的shape参数也是?吗?为什么我这里不行呢

@Casi11as
Copy link
Author

@Casi11as 你好,我这边是这样的, image 然后卡在这一步 image 请问你的shape参数也是?吗?为什么我这里不行呢

你是这一步报的错吗?shape里第一个维度 ? 代表batch_size,在送入数据之前是?没错的

@LeiiY
Copy link

LeiiY commented Nov 11, 2021

@Casi11as 我是在红线这一行 直接退出程序了,不反馈信息
image

@Casi11as
Copy link
Author

@Casi11as 我是在红线这一行 直接退出程序了,不反馈信息 image

怎么可能不显示任何信息,你不会是因为加了断点开的调试所以在这停了吧

@LeiiY
Copy link

LeiiY commented Nov 11, 2021

不是,我是因为启动训练脚本过一会就报错进程已退出,然后一点点打断点到这里,这一步走不通,不确定是不是数据的问题,所以我在重新生成tfrecord,因此现在没法演示,生成完我明天给你演示一下,感谢回复。

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