Skip to content

对测试集数据的要求是什么,我用其他的图像测试出来都是一个蓝块,没有结果 #7

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

Open
hantong263 opened this issue Oct 13, 2020 · 6 comments

Comments

@hantong263
Copy link

No description provided.

@TachibanaYoshino
Copy link
Owner

Same as the training dataset type

@Sun-Xinnnnn
Copy link

Me too!!!do u solve this problem??

@Sun-Xinnnnn
Copy link

Same as the training dataset type

How can other datasets be adjusted to the same format as the training set?

@TachibanaYoshino
Copy link
Owner

Of course, you can adjust the palette and one-hot preprocessing of the dataset.

@Sun-Xinnnnn
Copy link

当然,您可以调整数据集的调色板和 one-hot 预处理。

非常感谢您的回复!!!我直接跑的预测,用您的模型,发现是蓝色的,是因为one-hot 预处理不对吗?

@TachibanaYoshino
Copy link
Owner

You need to make sure that your data is of the same category as my predefined category, and the palette is the same. For rivers and lakes, the processed colored semantic regions are blue. Please note that the output result of the network is the predicted segmentation map, and then according to the color of the palette corresponding to the fixed category number, the map of different color semantics is generated.

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