facebook
/
maskformer-swin-large-coco
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
Niels Rogge 2022-11-10 10:06:13 +00:00 committed by huggingface-web
parent cf0d6d85c4
commit 8c011b6777
1 changed files with 30 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
README.md
View File

@ -1,27 +1,32 @@
--- ---
license: apache-2.0 license: other
tags: tags:
- vision - vision
- image-segmentation - image-segmentation
datasets: datasets:
- coco - coco
widget:
- src: http://images.cocodataset.org/val2017/000000039769.jpg
example_title: Cats
- src: http://images.cocodataset.org/val2017/000000039770.jpg
example_title: Castle
--- ---
# Mask # MaskFormer
Mask model trained on coco. It was introduced in the paper [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278) and first released in [this repository](https://github.com/facebookresearch/MaskFormer/blob/da3e60d85fdeedcb31476b5edd7d328826ce56cc/mask_former/modeling/criterion.py#L169). MaskFormer model trained on COCO panoptic segmentation (large-sized version, Swin backbone). It was introduced in the paper [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278) and first released in [this repository](https://github.com/facebookresearch/MaskFormer/blob/da3e60d85fdeedcb31476b5edd7d328826ce56cc/mask_former/modeling/criterion.py#L169).
Disclaimer: The team releasing Mask did not write a model card for this model so this model card has been written by the Hugging Face team. Disclaimer: The team releasing MaskFormer did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description ## Model description
MaskFormer addresses semantic segmentation with a mask classification paradigm instead. MaskFormer addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation.
![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/maskformer_architecture.png) ![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/maskformer_architecture.png)
## Intended uses & limitations ## Intended uses & limitations
You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=maskformer) to look for You can use this particular checkpoint for semantic segmentation. See the [model hub](https://huggingface.co/models?search=maskformer) to look for other
fine-tuned versions on a task that interests you. fine-tuned versions on a task that interests you.
### How to use ### How to use
@ -29,28 +34,28 @@ fine-tuned versions on a task that interests you.
Here is how to use this model: Here is how to use this model:
```python ```python
>>> from transformers import MaskFormerFeatureExtractor, MaskFormerForInstanceSegmentation from transformers import MaskFormerFeatureExtractor, MaskFormerForInstanceSegmentation
>>> from PIL import Image from PIL import Image
>>> import requests import requests
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg" # load MaskFormer fine-tuned on COCO panoptic segmentation
>>> image = Image.open(requests.get(url, stream=True).raw) feature_extractor = MaskFormerFeatureExtractor.from_pretrained("facebook/maskformer-swin-large-coco")
>>> feature_extractor = MaskFormerFeatureExtractor.from_pretrained("facebook/maskformer-swin-base-ade") model = MaskFormerForInstanceSegmentation.from_pretrained("facebook/maskformer-swin-large-coco")
>>> inputs = feature_extractor(images=image, return_tensors="pt")
>>> model = MaskFormerForInstanceSegmentation.from_pretrained("facebook/maskformer-swin-base-ade") url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> outputs = model(**inputs) image = Image.open(requests.get(url, stream=True).raw)
>>> # model predicts class_queries_logits of shape `(batch_size, num_queries)` inputs = feature_extractor(images=image, return_tensors="pt")
>>> # and masks_queries_logits of shape `(batch_size, num_queries, height, width)`
>>> class_queries_logits = outputs.class_queries_logits
>>> masks_queries_logits = outputs.masks_queries_logits
>>> # you can pass them to feature_extractor for postprocessing outputs = model(**inputs)
>>> output = feature_extractor.post_process_segmentation(outputs) # model predicts class_queries_logits of shape `(batch_size, num_queries)`
>>> output = feature_extractor.post_process_semantic_segmentation(outputs) # and masks_queries_logits of shape `(batch_size, num_queries, height, width)`
>>> output = feature_extractor.post_process_panoptic_segmentation(outputs) class_queries_logits = outputs.class_queries_logits
masks_queries_logits = outputs.masks_queries_logits
# you can pass them to feature_extractor for postprocessing
result = feature_extractor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
# we refer to the demo notebooks for visualization (see "Resources" section in the MaskFormer docs)
predicted_panoptic_map = result["segmentation"]
``` ```
For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/maskformer). For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/maskformer).