README.md
3.0 KB · 74 lines · markdown Raw
1 ---
2 license: other
3 tags:
4 - vision
5 - image-segmentation
6 datasets:
7 - scene_parse_150
8 widget:
9 - src: https://huggingface.co/datasets/hf-internal-testing/fixtures_ade20k/resolve/main/ADE_val_00000001.jpg
10 example_title: House
11 - src: https://huggingface.co/datasets/hf-internal-testing/fixtures_ade20k/resolve/main/ADE_val_00000002.jpg
12 example_title: Castle
13 ---
14
15 # SegFormer (b1-sized) model fine-tuned on ADE20k
16
17 SegFormer model fine-tuned on ADE20k at resolution 512x512. It was introduced in the paper [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://arxiv.org/abs/2105.15203) by Xie et al. and first released in [this repository](https://github.com/NVlabs/SegFormer).
18
19 Disclaimer: The team releasing SegFormer did not write a model card for this model so this model card has been written by the Hugging Face team.
20
21 ## Model description
22
23 SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmentation benchmarks such as ADE20K and Cityscapes. The hierarchical Transformer is first pre-trained on ImageNet-1k, after which a decode head is added and fine-tuned altogether on a downstream dataset.
24
25 ## Intended uses & limitations
26
27 You can use the raw model for semantic segmentation. See the [model hub](https://huggingface.co/models?other=segformer) to look for fine-tuned versions on a task that interests you.
28
29 ### How to use
30
31 Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes:
32
33 ```python
34 from transformers import SegformerFeatureExtractor, SegformerForSemanticSegmentation
35 from PIL import Image
36 import requests
37
38 feature_extractor = SegformerFeatureExtractor.from_pretrained("nvidia/segformer-b1-finetuned-ade-512-512")
39 model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b1-finetuned-ade-512-512")
40
41 url = "http://images.cocodataset.org/val2017/000000039769.jpg"
42 image = Image.open(requests.get(url, stream=True).raw)
43
44 inputs = feature_extractor(images=image, return_tensors="pt")
45 outputs = model(**inputs)
46 logits = outputs.logits # shape (batch_size, num_labels, height/4, width/4)
47 ```
48
49 For more code examples, we refer to the [documentation](https://huggingface.co/transformers/model_doc/segformer.html#).
50
51 ### BibTeX entry and citation info
52
53 ```bibtex
54 @article{DBLP:journals/corr/abs-2105-15203,
55 author = {Enze Xie and
56 Wenhai Wang and
57 Zhiding Yu and
58 Anima Anandkumar and
59 Jose M. Alvarez and
60 Ping Luo},
61 title = {SegFormer: Simple and Efficient Design for Semantic Segmentation with
62 Transformers},
63 journal = {CoRR},
64 volume = {abs/2105.15203},
65 year = {2021},
66 url = {https://arxiv.org/abs/2105.15203},
67 eprinttype = {arXiv},
68 eprint = {2105.15203},
69 timestamp = {Wed, 02 Jun 2021 11:46:42 +0200},
70 biburl = {https://dblp.org/rec/journals/corr/abs-2105-15203.bib},
71 bibsource = {dblp computer science bibliography, https://dblp.org}
72 }
73 ```
74