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

训练没有归一化,预测却有归一化,是不是有问题? #26

Closed
seven-linglx opened this issue Dec 21, 2021 · 2 comments
Closed

Comments

@seven-linglx
Copy link

训练时候加载数据是dataloader.py 222行,是没有对图片做mean和std归一化的,但预测时predict.py -> centernet.py -> util/util.py -> preprocess_input里却对图片做了mean、std归一化,这应该有问题吧?

@bubbliiiing
Copy link
Owner

120行
image = np.transpose(preprocess_input(image), (2, 0, 1))

@seven-linglx
Copy link
Author

seven-linglx commented Dec 23, 2021

120行 image = np.transpose(preprocess_input(image), (2, 0, 1))

确实,是我没看清。
对图片的处理统一放在get_random_data函数里是不是会更好些。

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