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过程出错 #15

Open
clearliu777 opened this issue Feb 8, 2021 · 10 comments
Open

train过程出错 #15

clearliu777 opened this issue Feb 8, 2021 · 10 comments

Comments

@clearliu777
Copy link

File "D:/untitled2/Segmentation/unet_mobile/train.py", line 42, in generate_arrays_from_file
one_hot_label = np.eye(NCLASSES)[np.array(label, np.int16)]
IndexError: index 128 is out of bounds for axis 0 with size 2

做的是2分类 但是这个地方显示128是为什么呀 求up主指导

@bubbliiiing
Copy link
Owner

数据集格式错了

@Echanted-168
Copy link

你好 up主 我的错误和上边的错误是一样的 数据集格式的错误具体是指的是什么错误那 您能不能详细阐述一下那
因为我用到别的数据集都是公开的数据集 用的camvid数据集 需要把数据集格式怎么转换那 先行谢谢

@Echanted-168
Copy link

File "D:/untitled2/Segmentation/unet_mobile/train.py", line 42, in generate_arrays_from_file
one_hot_label = np.eye(NCLASSES)[np.array(label, np.int16)]
IndexError: index 128 is out of bounds for axis 0 with size 2

做的是2分类 但是这个地方显示128是为什么呀 求up主指导

你好 请问你是怎么解决这个 问题的那

@bubbliiiing
Copy link
Owner

你看看你的数据集是什么格式,要求三个通道的值都是这个像素点的种类

@Echanted-168
Copy link

好的 up主 谢谢先

@Echanted-168
Copy link

你好 up主 我看您的标注的图片位深度都是24,我用的图片的标注格式位深度也是24,报的那个错误是和图片的位深度有关嘛??
看您的重置版本的voc数据集标注的格式位深度是8,老版本的voc数据集位深度是24,这个位深度和训练时候报的那个错误有关嘛?

@bubbliiiing
Copy link
Owner

你是像素点的值错了。

@bubbliiiing
Copy link
Owner

我看错误是这样的

@Echanted-168
Copy link

好的 up主

@bubbliiiing
Copy link
Owner

好的加油

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