-
## SQ, CQ and Registrar contain `NonNull` which point to the same value.
https://github.com/ringbahn/iou/blob/045f8d44c235e35b3731625356a11e6ee05966f9/src/submission_queue.rs#L47-L50
https://git…
-
Hi!
Why isn't negative sampling used during the training of ssd detector?
```
self._target_generator = SSDTargetGenerator(
iou_thresh=iou_thresh, stds=box_norm, negative_mining_ratio=-…
-
Hi,
I have a three specific questions w.r.t. the available **validation_metric_type**s: 'voc', 'coco' and 'coco_voc'
1. For 'voc', some microsoft documentation refers to the VOC site: http://ho…
-
thanks for your great work!But i meet a problem and i want to get your help!When i change the backbone from densenet121.features to vovnet57 or resnet50.My testing results are really bad which almost …
-
The IoU function seems to be (I + I)/(I +U) in mmdet3d_plugin/models/detectors/petr3d_seg.py, but not I/U that we common used.
This may lead to higher IoU value than that calculated by normal Io…
-
### Prerequisite
- [X] I have searched [Issues](https://github.com/open-mmlab/mmrotate/issues) and [Discussions](https://github.com/open-mmlab/mmrotate/discussions) but cannot get the expected help.
…
-
When I train p5, IOU will appear in the third row of every four rows: 0.000000 iou_loss = 0.000000, as shown in Figure 1
 < 0.3:” 就是负样本，但是这个判断某些情况下我认为是有问题的，例如随机生成的crop_box的面积大于最大单个人脸面积的3.3倍时，这个判断条件会满足，我认为这个这个负样本包含有完整的人脸，不是有效的负样本。你怎么看待这种情况？我觉得要解决这个问题，应该限制crop_box的面积大小或者判断overlap部分与人脸b…
-
Can evaluation scripts be provided on different datasets to validate the quantitative results provided in the paper？
-
Hello, I tried to run a few algorithms under that repository, but the performance of retinanet and fcos is better than sm(iou_thrs=[0.25, 0.5, 0.75]), I don't know if there is a problem with my config…