Run panoptic segmentation about detr HOT 13 CLOSED

Hi,

Thanks for the message!

We are planning on releasing a colab notebook illustrating how to perform predictions with detr_panoptic, and we will also include torchhub models for it. It should be available sometime next week.

from detr.

Hi all, the panoptic notebook is now available here https://colab.research.google.com/github/facebookresearch/detr/blob/colab/notebooks/DETR_panoptic.ipynb
cc @shidilrzf
Let me know what you think.

from detr.

Thank you this is super helpful!

I had to upgrade pyyaml for whatever reason.
Just run:
pip3 install pyyaml -U
if you run into the same error.

from detr.

I made simple demo using DETR and panoptic segmentation here:

https://youtu.be/CJj6V1eafVs

Each class has predefined color (to prevend color blinking on video).

from detr.

Awesome, thanks for the info!

from detr.

Thanks a lot! That really helped.
I had some problems with metadata to be able to use detecton2 Visualizer. The category-id reported in the "segment_info" was different than the one used in detectron2.

from detr.

Thanks a lot! That really helped.
I had some problems with metadata to be able to use detecton2 Visualizer. The category-id reported in the "segment_info" was different than the one used in detectron2.

Yes indeed, Detectron2 does a remapping to ensure contiguous IDs, which we don't. Did the Notebook clarify that part for you?

from detr.

Thanks a lot! That really helped.
I had some problems with metadata to be able to use detecton2 Visualizer. The category-id reported in the "segment_info" was different than the one used in detectron2.

Yes indeed, Detectron2 does a remapping to ensure contiguous IDs, which we don't. Did the Notebook clarify that part for you?

Yes, thanks a lot ;)

from detr.

I believe the issue at hand was addressed, as such I'm closing this. Feel free to ask if you have further questions.

from detr.

Is it possible to train panoptic segmentation on my dataset, which is not in COCO format? @alcinos

from detr.

@NIkimih We currently only support COCO format. You'll need to convert your dataset, see https://cocodataset.org/#format-data for information on what is expected. You essentially need three things: the images, some jsons (for train and val) describing the segments (class, associated bounding box, id), and a specially formatted png encoding per-pixel segment ids (the color correspond to the id, as described in the link)

from detr.

@NIkimih We currently only support COCO format. You'll need to convert your dataset, see https://cocodataset.org/#format-data for information on what is expected. You essentially need three things: the images, some jsons (for train and val) describing the segments (class, associated bounding box, id), and a specially formatted png encoding per-pixel segment ids (the color correspond to the id, as described in the link)

Thanks for the quick response

from detr.

Hii, can someone explain me how areas is calculate in panoptic segmentation ouput? Thanks in advance

segments_info = [{'area': 2712.0,
  'category_id': 0,
  'id': 1,
  'instance_id': 0,
  'isthing': True,
  'score': 0.9890128374099731},

from detr.