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

Performance issue of images in Val set of Cityscapes #30

Open
scyyx1 opened this issue Apr 26, 2022 · 5 comments
Open

Performance issue of images in Val set of Cityscapes #30

scyyx1 opened this issue Apr 26, 2022 · 5 comments

Comments

@scyyx1
Copy link

scyyx1 commented Apr 26, 2022

Hi,

I have used your provided pretrained model of DDRNet23 slim on Cityscapes dataset. However, for the validation set, I have only reached 41.49% mIoU instead of 77.8%. Did I forget to tune any parameters?

@sithu31296
Copy link
Owner

The mIoU results are from official papers and pretrained weights from official repo. I haven't tested each of them with my codebase. Though evaluation image size should be 1024x2048 for DDRNet. And I don't remember are there any more parameters you need to change.
The results are only included for comparability of different models. Still 41.49 is too low.

@scyyx1
Copy link
Author

scyyx1 commented Apr 26, 2022

I have tried both your provided one "ddrnet_23slim_city.pth" and the one in the official paper. They produced the same results, which are 41.49%. I've also tried to set the image to different size. For image size of [2048, 1024], I get lower accuracy, while if I change it to [1024, 2048], I received the same result.

@sithu31296
Copy link
Owner

Hello, sorry for late. I will evaluate the model and see if there is an issue with my implementation.

@scl666
Copy link

scl666 commented Sep 26, 2022

我已经尝试了您提供的“ddrnet_23slim_city.pth”和官方文件中的那个。他们产生了相同的结果,为41.49%。我还尝试将图像设置为不同的大小。对于[2048,1024]的图像大小,我得到的精度较低,而如果我将其更改为[1024,2048],我会收到相同的结果。

你好,方便提供cityscapes数据集的DDR23slim的预训练权重吗?邮箱2358919283@qq.com

@scl666
Copy link

scl666 commented Sep 30, 2022

您好,很抱歉迟到了。我将评估模型,看看我的实现是否存在问题。

你好,请问我在使用DDR模型遇到这个错误‘RuntimeError: transform: failed to synchronize: cudaErrorIllegalAddress: an illegal memory access’,请教一下遇到这样子错误吗?网上搜有说pytorch版本,还有标注文件 / 标签 等没有设置正确
以及网络模型、训练数据(图片和标签)没有放置到GPU上,我感觉这些都没有问题啊。期待您的回复

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

3 participants