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

正样本对构建问题 #3

Open
realfzyyyyy opened this issue Aug 16, 2023 · 1 comment
Open

正样本对构建问题 #3

realfzyyyyy opened this issue Aug 16, 2023 · 1 comment

Comments

@realfzyyyyy
Copy link

作者您好:
复现代码的过程中,遇到了一些问题,希望能得到您的解答。main.py文件里面的正样本对构建有出入,正负样本是一样的图片吗?并且data_loader_train在dataloader那边是可以取到数据的,然后到了训练的时候,图像数据就是空的,标签数据还在。
50a0ab0653cdbd9654a358512aa02d4并报错
4b5256704a8f5d9e58d82eb4ef3cb96
拿data_loader_val的数据集去train,虽然跑不通,后面有维度问题,但是标签和这个img里面的内容是有的。具体的维度问题是:正常val时,数据维度是[B,3,448,448],但拿val的数据train时,经过这段代码
88ceebebe9f751ec227bf5bc7037e8f
维度会变为[B*3,448,448]。期待您的回复,谢谢!

@Markin-Wang
Copy link
Owner

Markin-Wang commented Aug 18, 2023

Hi, 谢谢你对我们工作的兴趣,正负样本不是同样的图片,具体请参见我们的论文。你提到的关于train的问题,经过重新检查代码,我们发现在我们重构代码准备发布的时候,我们将data/build.py MyTransform类中根据模型的mode来生成模型输入的args.model参数判断做了重命名(full_b --> full),而训练脚本文件中还是full_b, 我已更改相关脚本文件和代码,重新pull应该可以正常训练,如果还无法训练欢迎留言。

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