-
Hi,
Is there any sensor which provides panoptic segmentation masks?
Thanks
-
Thanks for your great contributions to the community!! Thanks for your dataset and toolbox. I have several questions about the dataset.
The first one is about the instance id, do the instance id o…
-
According to [link1](https://github.com/facebookresearch/detectron2/blob/master/datasets/prepare_panoptic_fpn.py#L55), the code maps background pixels whose category are 0 to category 255. According …
-
Hi @MehmetAygun , thank you for your code and contribution to the community. It is a really interesting work.
I have run your training and testing code. It seems that the validation process takes q…
-
Hello, I am a beginner. I know how to use Instance Segmentation parameter “pred_masks” to cut image by mask for every instance. But Panoptic Segmentation doesn't have parameter like “pred_masks”.
…
-
## 📚 Documentation
* Link to the relevant documentation/comment:
https://detectron2.readthedocs.io/en/latest/tutorials/install.html#installation-inside-specific-environments
https://colab.resea…
-
MMDetection v2.12.0 will be released at the end of April.
We list our plan for v2.13.0, which will be released at the end of May.
The PRs from the communities will also be listed here.
Thus, devel…
-
When doing an evaluation on the test set, I got the following error. I don't have any clue about it.
```
2019-04-18 03:56:17,288 | upsnet_end2end_test.py | line 307: unified pano result:
Tracebac…
-
## 📚 Documentation
* Links to the relevant documentation/comment:
https://detectron2.readthedocs.io/en/latest/tutorials/datasets.html
panoptic_root, panoptic_json: Used by panoptic evaluation.
…
-
您好！想请问一下，如果我不是用AxialAttention作为backbone，而是仅仅用它作为一个attention机制的话，效果怎么样？此外，AxialAttention中的kernel size是不是取决于输入的feature map的尺寸，那么如果我在train和infer的时候输入尺寸不同，feature map尺寸也不同，是不是会出现问题呢？希望能够得到解答，非常感谢！