zuppif commited on
Commit
16ebe37
1 Parent(s): 9375d07

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +64 -0
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - vision
5
+ - image-segmentatiom
6
+
7
+ datasets:
8
+ - ade-20k
9
+
10
+ widget:
11
+ - src: https://huggingface.co/datasets/hf-internal-testing/fixtures_ade20k/resolve/main/ADE_val_00000001.jpg
12
+ example_title: House
13
+ - src: https://huggingface.co/datasets/hf-internal-testing/fixtures_ade20k/resolve/main/ADE_val_00000002.jpg
14
+ example_title: Castle
15
+
16
+ ---
17
+
18
+ # Mask
19
+
20
+ Mask model trained on ade-20k. 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).
21
+
22
+ 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.
23
+
24
+ ## Model description
25
+
26
+ MaskFormer addresses semantic segmentation with a mask classification paradigm instead.
27
+
28
+ ![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/maskformer_architecture.png)
29
+
30
+ ## Intended uses & limitations
31
+
32
+ You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=maskformer) to look for
33
+ fine-tuned versions on a task that interests you.
34
+
35
+ ### How to use
36
+
37
+ Here is how to use this model:
38
+
39
+ ```python
40
+ >>> from transformers import MaskFormerFeatureExtractor, MaskFormerForInstanceSegmentation
41
+ >>> from PIL import Image
42
+ >>> import requests
43
+
44
+ >>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
45
+ >>> image = Image.open(requests.get(url, stream=True).raw)
46
+ >>> feature_extractor = MaskFormerFeatureExtractor.from_pretrained("facebook/maskformer-swin-base-ade")
47
+ >>> inputs = feature_extractor(images=image, return_tensors="pt")
48
+
49
+ >>> model = MaskFormerForInstanceSegmentation.from_pretrained("facebook/maskformer-swin-base-ade")
50
+ >>> outputs = model(**inputs)
51
+ >>> # model predicts class_queries_logits of shape `(batch_size, num_queries)`
52
+ >>> # and masks_queries_logits of shape `(batch_size, num_queries, height, width)`
53
+ >>> class_queries_logits = outputs.class_queries_logits
54
+ >>> masks_queries_logits = outputs.masks_queries_logits
55
+
56
+ >>> # you can pass them to feature_extractor for postprocessing
57
+ >>> output = feature_extractor.post_process_segmentation(outputs)
58
+ >>> output = feature_extractor.post_process_semantic_segmentation(outputs)
59
+ >>> output = feature_extractor.post_process_panoptic_segmentation(outputs)
60
+ ```
61
+
62
+
63
+
64
+ For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/maskformer).