praeclarumjj3 commited on
Commit
a63b561
1 Parent(s): e2947fb

Add documentation

Browse files
Files changed (1) hide show
  1. README.md +63 -0
README.md CHANGED
@@ -13,3 +13,66 @@ widget:
13
  - src: https://huggingface.co/datasets/shi-labs/oneformer_demo/blob/main/demo.jpeg
14
  example_title: Corgi
15
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  - src: https://huggingface.co/datasets/shi-labs/oneformer_demo/blob/main/demo.jpeg
14
  example_title: Corgi
15
  ---
16
+
17
+ # OneFormer
18
+
19
+ OneFormer model trained on the COCO dataset (large-sized version, Dinat backbone). It was introduced in the paper [OneFormer: One Transformer to Rule Universal Image Segmentation](https://arxiv.org/abs/2211.06220) by Jain et al. and first released in [this repository](https://github.com/SHI-Labs/OneFormer).
20
+
21
+ ![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/oneformer_teaser.png)
22
+
23
+ ## Model description
24
+
25
+ OneFormer is the first multi-task universal image segmentation framework based on transformers. OneFormer needs to be trained only once with a single universal architecture, a single model, and on a single dataset, to outperform existing frameworks across semantic, instance, and panoptic segmentation tasks. OneFormer uses a task token to condition the model on the task in focus, making the architecture task-guided for training, and task-dynamic for inference, all with a single model.
26
+
27
+ ![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/oneformer_architecture.png)
28
+
29
+ ## Intended uses & limitations
30
+
31
+ You can use this particular checkpoint for semantic, instance and panoptic segmentation. See the [model hub](https://huggingface.co/models?search=oneformer) to look for other fine-tuned versions on a different dataset.
32
+
33
+ ### How to use
34
+
35
+ Here is how to use this model:
36
+
37
+ ```python
38
+ from transformers import OneFormerFeatureExtractor, OneFormerForUniversalSegmentation
39
+ from PIL import Image
40
+ import requests
41
+ url = "https://huggingface.co/datasets/shi-labs/oneformer_demo/blob/main/coco.jpeg"
42
+ image = Image.open(requests.get(url, stream=True).raw)
43
+
44
+ # Loading a single model for all three tasks
45
+ feature_extractor = OneFormerFeatureExtractor.from_pretrained("shi-labs/oneformer_coco_dinat_large")
46
+ model = OneFormerForUniversalSegmentation.from_pretrained("shi-labs/oneformer_coco_dinat_large")
47
+
48
+ # Semantic Segmentation
49
+ semantic_inputs = feature_extractor(images=image, ["semantic"] return_tensors="pt")
50
+ semantic_outputs = model(**semantic_inputs)
51
+ # pass through feature_extractor for postprocessing
52
+ predicted_semantic_map = feature_extractor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
53
+
54
+ # Instance Segmentation
55
+ instance_inputs = feature_extractor(images=image, ["instance"] return_tensors="pt")
56
+ instance_outputs = model(**instance_inputs)
57
+ # pass through feature_extractor for postprocessing
58
+ predicted_instance_map = feature_extractor.post_process_instance_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]
59
+
60
+ # Panoptic Segmentation
61
+ panoptic_inputs = feature_extractor(images=image, ["panoptic"] return_tensors="pt")
62
+ panoptic_outputs = model(**panoptic_inputs)
63
+ # pass through feature_extractor for postprocessing
64
+ predicted_semantic_map = feature_extractor.post_process_panoptic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]["segmentation"]
65
+ ```
66
+
67
+ For more examples, please refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/oneformer).
68
+
69
+ ### Citation
70
+
71
+ ```bibtex
72
+ @article{jain2022oneformer,
73
+ title={{OneFormer: One Transformer to Rule Universal Image Segmentation}},
74
+ author={Jitesh Jain and Jiachen Li and MangTik Chiu and Ali Hassani and Nikita Orlov and Humphrey Shi},
75
+ journal={arXiv},
76
+ year={2022}
77
+ }
78
+ ```