kasteric

Performance gap between this version and Co-Detr in mmdetection v3

3

I wonder why there is a performance gap between Co-detr and its version in mmdetection v3, I have used the same training data to train on both repo, and I...

The user-unfriendly implementation of CoDINO head

3

This code makes the inference format of output become a class, rather than a list of tensors, which may cause errors when trying to convert the model to onnx, even...

inference得到了莫名奇妙的背景框。。

3

我用cascadercnn训练都至少可以区分前景和背景，用dino训练也不会出现莫名奇妙的invalid的框，但是用co-dino大尺度训练，出现了把背景预测为前景的例子，好神奇。。

1) git clone https://github.com/open-mmlab/mmcv 2) pip3 install -e . -v 3) 测试是否安装成功 -> 失败，报错： python3 .dev_scripts/check_installation.py Traceback (most recent call last): File ".dev_scripts/check_installation.py", line 4, in from mmcv.ops import box_iou_rotated...

visual prompt的效果有点差，不如t-rex2

4

I have tested t-rex2 on visually-prompted detection by giving some examples of document boxes, and it worked out fine. But I tried this demo, it did not work, no boxes...

Can PartSLIP++ perform well on PartNet?

3

Hi, thanks for your inspiring work! I notice that the point clouds in training set and testing set are both collected from Part-Mobility dataset, whose point clouds have dense number...