Skip to content

Issues: PeizeSun/SparseR-CNN

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.

Sign up for GitHub

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

38 Open 63 Closed
38 Open 63 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

I am just start to learn, I found that the default configuration of Sparse R-CNN had better AP results than Faster R-CNN. However, with the detection results, I noticed that Sparse R-CNN had lower confidence scores for its detections. Why is that the case? im little confused
#113 opened May 20, 2024 by ZhangShutongo
请问怎么使用预训练权重，从头开始训练的准确率比较低
#112 opened Mar 19, 2024 by WinnieMs
How to visualize the activation maps of dynamic head in Sparse R-CNN？
#111 opened Oct 31, 2023 by Nanakl
Initialization box selection
#110 opened Sep 11, 2023 by YH-2023
Some questions about positional encoding, in the Table 10
#109 opened Aug 12, 2023 by AlterRay
The results were not reproduced on CrowdHuman dataset
#108 opened Jun 8, 2023 by a1b2c3s4d4
1
"Dataset 'CrowdHuman_train' is not registered
#107 opened Jun 27, 2022 by Aliweka2020
3
KeyError: 1, when using only 1 class dataset to evaluation
#106 opened May 24, 2022 by YipChakwai
AssertionError: Attribute 'thing_classes' in the metadata of 'coco_2017_train' cannot be set to a different value! question Further information is requested
#102 opened Jan 28, 2022 by Aruen24
2
How can I use a custom dataset?
#99 opened Nov 26, 2021 by JEO-96
2
我把从coco数据集换成了自己的数据集，但是出现了错误，我应该修改你的代码中的哪几个部分的代码
#98 opened Nov 11, 2021 by libingDY
5
How to install the Sparse R-CNN(it seems amusing)?
#97 opened Oct 4, 2021 by xiaomin0416
1
How to do use test time augmentation?
#95 opened Sep 6, 2021 by bravezzzzzz
1
Does anything changes in detectron2？
#93 opened Jul 12, 2021 by kuiran
1
Resume started from zero again!
#91 opened Jul 4, 2021 by zobeirraisi
3
How the feature re-use is performed
#90 opened Jun 9, 2021 by XuyangBai
1
'assert (boxes1[:, 2:] >= boxes1[:, :2]).all()' happened when training
#89 opened May 25, 2021 by Swall0w
4
how to use plot function?
#87 opened May 22, 2021 by Yixiang-Wu
1
Question about the Iterative architecture
#84 opened May 10, 2021 by GuangxingHan
2
About the loss format
#83 opened Apr 27, 2021 by FL77N
4
train w/o pre-trained backbone
#82 opened Apr 22, 2021 by StarsMyDestination
3
question about pred_bboxes.detach() in DynamicHead.forward()
#81 opened Apr 20, 2021 by burningisnaive
2
the learning rate adjustment when training with one gpu or two gpus
#80 opened Apr 1, 2021 by Young0111
5
Question regarding proposal feature
#77 opened Mar 10, 2021 by abeyang00
4
Hi,Have you verified the model to ONNX, i meet some bugs to onnx.
#75 opened Mar 5, 2021 by csliuchang
2
ProTip! Type g i on any issue or pull request to go back to the issue listing page.