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

Unable to reproduce the results of semantic segmentation on S3DIS #24

Open
jelenab98 opened this issue Feb 16, 2023 · 2 comments
Open

Comments

@jelenab98
Copy link

Hi,
we are having some problems reproducing the results of semantic segmentation on S3DIS from the article.

For the repsurf model (all hyperparameters set as instructed in article), we got mIoU of 70% while your article reports mIoU of 74%. We would like to inspect the training logs so could you possibly provide training logs of repsurf for 6-fold validation?

Another problem is related to the PointNet++ model. You reported mIoU of 58% in your paper. Did you measure it with the PointNet++ implementation from this repo or some other implementation? We ran the 6-fold validation of the PointNet++ implementation from this repo and got mIoU of 69%. Do you know what can be the possible cause of this?

@helen1c
Copy link

helen1c commented Feb 27, 2023

I obtained similar results as @jelenab98, @hancyran could you please publish 6-fold validation results for RepSurf and PointNet++?

@chenys0425
Copy link

嗨,我们在文章中重现 S3DIS 上的语义分割结果时遇到了一些问题。

对于 repsurf 模型(按照文章中的说明设置所有超参数),我们得到的 mIoU 为 70%,而您的文章报告的 mIoU 为 74%。我们想检查训练日志,所以你能提供 repsurf 的训练日志进行 6 倍验证吗?

另一个问题与 PointNet++ 模型有关。您在论文中报告了 58% 的 mIoU。您是否使用此存储库或其他实现中的 PointNet++ 实现来衡量它?我们从这个存储库中对 PointNet++ 实现进行了 6 倍验证,得到了 69% 的 mIoU。你知道造成这种情况的可能原因是什么吗?

Hi, we are having some problems reproducing the results of semantic segmentation on S3DIS from the article.

For the repsurf model (all hyperparameters set as instructed in article), we got mIoU of 70% while your article reports mIoU of 74%. We would like to inspect the training logs so could you possibly provide training logs of repsurf for 6-fold validation?

Another problem is related to the PointNet++ model. You reported mIoU of 58% in your paper. Did you measure it with the PointNet++ implementation from this repo or some other implementation? We ran the 6-fold validation of the PointNet++ implementation from this repo and got mIoU of 69%. Do you know what can be the possible cause of this?

Hello, do you have the code for performing 6-fold validation on the S3DIS dataset?If possible, can you send it to me for learning?

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