-
Notifications
You must be signed in to change notification settings - Fork 143
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
Code of GCN-S part #2
Comments
@LZDSJTU We will try to release as much code as possible before the conference. |
Thank you for your contribution. Additionally, could you provide the list for splitting MS-Celeb-1M dataset? |
@LZDSJTU The list has been uploaded to GoogleDrive and OneDrive. You can also find it in README of the |
Hello, I saw you evaluated your method with YTF dataset, I wonder how to generate this dataset? |
@jxyecn We use the frames extracted by YTF dataset. Checkout the second or third download link in YTB official page. Particularly, as stated in experimental settings, we use 14,653 frames for training and 140,629 frames for testing. The related data and pretrained model have been uploaded to GoogleDrive and OneDrive to reproduce the result. You can also find it in README of the |
@yl-1993 Thanks for your reply |
@CaiQiuYu GCN-S is devised to improve the precision of the proposals. Since the precision of clustering results after GCN-D is over 95, there is no much space for improvement. In ablation study, we show that GCN-S can be used as an independent module to combine with other methods. |
Is there any news about publishing the training code? |
Hi @yl-1993 , is there any plan of releasing the code of the GCN-S ? |
@AruniRC Thanks for checking our progress. Since the difference between GCN-S and GCN-D is not very significant, the priority of cleaning GCN-S is lower than our other projects currently. Actually, the model of GCN-S is available at dsgcn model. By setting the |
Hi @yl-1993 , is there any plan of releasing the code of the GCN-S ? |
@zsz00 Thanks for checking. I'm busy preparing a submission and currently may not have much time for this project. For those who want to have a try, I provide a code snippet for GCN-S. The snippet can not run directly, but includes the data processing and loss function used in GCN-S. |
Thanks for your reply |
Hi all, GCN-S will be available after PR #31 is merged. |
@yl-1993 Hello, I would like to ask some questions about testing GCN-S with my own dataset which has no id labels. There's something wrong when I run "test_cluster_seg_ms1m.py", it occurred an error that "TypeError: 'NoneType' object is not subscriptable " in cluster_seg_processor.py. Here the 'NoneType' object refers to dataset.idx2lb |
@linjiawen2019 Thanks for reporting! We will fix it through PR #44. |
Thank u so much!! Really helpful to me |
@linjiawen2019 The PR is merged. Feel free to have a try. |
Hello, I saw that you will open the training code in late May. I want to ask if you will open the code of GCN-S part at that time. Thank you.
The text was updated successfully, but these errors were encountered: