WeiJin_MUST

How can I get the electrical data which has been disaggreted by NILMTK-contrib

1

Hi, appliance load disaggregation is the first step of my research project. So, I need to get the data from nilmtk as the input data of the next experiment. I...

提个问题，大佬有做增量学习这块吗？

1

Incremental learning 应该是Open Wold问题中的一个子模块，想知道作者是如何进行增量学习的

Thank you for your nice paper. But I don't know how to conduct incremental object detection. - According to the open world setting. When the model labels sufficient unknown classes,...

Not able to load: datasets/VOC2007/Annotations/006423.xml. Continuing without aboarting...

2

Hi guys！ Have you encountered this problem before? How did you solve it? My environment is Python 3.8+torch1.10+cuda113；reliability == 0.5.6 Thank you!

How to solve this problem in Task 1 ?

Hi Joseph, thank you for your great work! Here, I have a question about how to localize the unknown instance. We know that unknown candidate proposals are from top-k region...

Hi, I find that there are two datasets on Waymo official website, the motion dataset and the perception dataset. And I can not find raw dataset. Which one should I...

我的一些理解

1

说一下我的理解和问题： 1. 做不了细分类的原因是，训练阶段的mini-batch是只获取IoU0.5以上的框，目的就是对已知instance建模。因此整个模型就没有考虑到unknown instance。只是在test的时候，或者说，相当于后处理方法，给目标一个分数来判断是否是已知或者未知，这也是为什么文中会说：“Furthermore, since background proposals usually overwhelm the mini-batch, we sample the same number of foreground and background proposals, enabling our model to recall unknown objects from the...

关于评估VOC_COCO_20_40_test的问题

4

 你好，我在用你们训练好的模型评估VOC_COCO_20_40_test时，mAP特别低，其他指标都很正常。  然后在评估20_60时mAP又下降到13，是怎么回事呢？ 只有在VOC评估中达到了80.02%，希望得到回复，谢谢！ VOC_COCO_20_40 的意思是指20个VOC类(20)和20个VOC类+20个非VOC类(40)吗？