riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-03 03:31:05 +06:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

update maskformer docs (#18423)

Browse Source 
* update maskformer docs

* fix typo
This commit is contained in:
Alara Dirik 2022-08-02 18:43:58 +03:00 committed by GitHub
parent 0b8c1b6994
commit 8ae7784256
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/en/model_doc/maskformer.mdx
View File

@ -33,7 +33,7 @@ Tips:
`get_num_masks` function inside in the `MaskFormerLoss` class of `modeling_maskformer.py`. When training on multiple nodes, this should be
set to the average number of target masks across all nodes, as can be seen in the original implementation [here](https://github.com/facebookresearch/MaskFormer/blob/da3e60d85fdeedcb31476b5edd7d328826ce56cc/mask_former/modeling/criterion.py#L169).
- One can use [`MaskFormerFeatureExtractor`] to prepare images for the model and optional targets for the model.
- To get the final segmentation, depending on the task, you can call [`~MaskFormerFeatureExtractor.post_process_semantic_segmentation`] or [`~MaskFormerFeatureExtractor.post_process_panoptic_segmentation`]. Both tasks can be solved using [`MaskFormerForInstanceSegmentation`] output, the latter needs an additional `is_thing_map` to know which instances must be merged together..
- To get the final segmentation, depending on the task, you can call [`~MaskFormerFeatureExtractor.post_process_semantic_segmentation`] or [`~MaskFormerFeatureExtractor.post_process_panoptic_segmentation`]. Both tasks can be solved using [`MaskFormerForInstanceSegmentation`] output, panoptic segmentation accepts an optional `label_ids_to_fuse` argument to fuse instances of the target object/s (e.g. sky) together.
The figure below illustrates the architecture of MaskFormer. Taken from the [original paper](https://arxiv.org/abs/2107.06278).