hyo37009 commited on
Commit
0c73a31
·
1 Parent(s): e926fec
Files changed (2) hide show
  1. 1212.md +75 -0
  2. README.md +8 -75
1212.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ tags:
4
+ - vision
5
+ - image-segmentation
6
+ datasets:
7
+ - cityscapes
8
+ widget:
9
+ - src: https://cdn-media.huggingface.co/Inference-API/Sample-results-on-the-Cityscapes-dataset-The-above-images-show-how-our-method-can-handle.png
10
+ example_title: road
11
+ ---
12
+
13
+ # SegFormer (b5-sized) model fine-tuned on CityScapes
14
+
15
+ SegFormer model fine-tuned on CityScapes at resolution 640x1280. 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).
16
+
17
+ 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.
18
+
19
+ ## Model description
20
+
21
+ 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.
22
+
23
+ ## Intended uses & limitations
24
+
25
+ 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.
26
+
27
+ ### How to use
28
+
29
+ Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes:
30
+
31
+ ```python
32
+ from transformers import SegformerFeatureExtractor, SegformerForSemanticSegmentation
33
+ from PIL import Image
34
+ import requests
35
+
36
+ feature_extractor = SegformerFeatureExtractor.from_pretrained("nvidia/segformer-b0-finetuned-cityscapes-640-1280")
37
+ model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-cityscapes-640-1280")
38
+
39
+ url = "http://images.cocodataset.org/val2017/000000039769.jpg"
40
+ image = Image.open(requests.get(url, stream=True).raw)
41
+
42
+ inputs = feature_extractor(images=image, return_tensors="pt")
43
+ outputs = model(**inputs)
44
+ logits = outputs.logits # shape (batch_size, num_labels, height/4, width/4)
45
+ ```
46
+
47
+ For more code examples, we refer to the [documentation](https://huggingface.co/transformers/model_doc/segformer.html#).
48
+
49
+ ### License
50
+
51
+ The license for this model can be found [here](https://github.com/NVlabs/SegFormer/blob/master/LICENSE).
52
+
53
+ ### BibTeX entry and citation info
54
+
55
+ ```bibtex
56
+ @article{DBLP:journals/corr/abs-2105-15203,
57
+ author = {Enze Xie and
58
+ Wenhai Wang and
59
+ Zhiding Yu and
60
+ Anima Anandkumar and
61
+ Jose M. Alvarez and
62
+ Ping Luo},
63
+ title = {SegFormer: Simple and Efficient Design for Semantic Segmentation with
64
+ Transformers},
65
+ journal = {CoRR},
66
+ volume = {abs/2105.15203},
67
+ year = {2021},
68
+ url = {https://arxiv.org/abs/2105.15203},
69
+ eprinttype = {arXiv},
70
+ eprint = {2105.15203},
71
+ timestamp = {Wed, 02 Jun 2021 11:46:42 +0200},
72
+ biburl = {https://dblp.org/rec/journals/corr/abs-2105-15203.bib},
73
+ bibsource = {dblp computer science bibliography, https://dblp.org}
74
+ }
75
+ ```
README.md CHANGED
@@ -1,75 +1,8 @@
1
- ---
2
- license: other
3
- tags:
4
- - vision
5
- - image-segmentation
6
- datasets:
7
- - cityscapes
8
- widget:
9
- - src: https://cdn-media.huggingface.co/Inference-API/Sample-results-on-the-Cityscapes-dataset-The-above-images-show-how-our-method-can-handle.png
10
- example_title: road
11
- ---
12
-
13
- # SegFormer (b5-sized) model fine-tuned on CityScapes
14
-
15
- SegFormer model fine-tuned on CityScapes at resolution 640x1280. 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).
16
-
17
- 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.
18
-
19
- ## Model description
20
-
21
- 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.
22
-
23
- ## Intended uses & limitations
24
-
25
- 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.
26
-
27
- ### How to use
28
-
29
- Here is how to use this model to classify an image of the COCO 2017 dataset into one of the 1,000 ImageNet classes:
30
-
31
- ```python
32
- from transformers import SegformerFeatureExtractor, SegformerForSemanticSegmentation
33
- from PIL import Image
34
- import requests
35
-
36
- feature_extractor = SegformerFeatureExtractor.from_pretrained("nvidia/segformer-b0-finetuned-cityscapes-640-1280")
37
- model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-cityscapes-640-1280")
38
-
39
- url = "http://images.cocodataset.org/val2017/000000039769.jpg"
40
- image = Image.open(requests.get(url, stream=True).raw)
41
-
42
- inputs = feature_extractor(images=image, return_tensors="pt")
43
- outputs = model(**inputs)
44
- logits = outputs.logits # shape (batch_size, num_labels, height/4, width/4)
45
- ```
46
-
47
- For more code examples, we refer to the [documentation](https://huggingface.co/transformers/model_doc/segformer.html#).
48
-
49
- ### License
50
-
51
- The license for this model can be found [here](https://github.com/NVlabs/SegFormer/blob/master/LICENSE).
52
-
53
- ### BibTeX entry and citation info
54
-
55
- ```bibtex
56
- @article{DBLP:journals/corr/abs-2105-15203,
57
- author = {Enze Xie and
58
- Wenhai Wang and
59
- Zhiding Yu and
60
- Anima Anandkumar and
61
- Jose M. Alvarez and
62
- Ping Luo},
63
- title = {SegFormer: Simple and Efficient Design for Semantic Segmentation with
64
- Transformers},
65
- journal = {CoRR},
66
- volume = {abs/2105.15203},
67
- year = {2021},
68
- url = {https://arxiv.org/abs/2105.15203},
69
- eprinttype = {arXiv},
70
- eprint = {2105.15203},
71
- timestamp = {Wed, 02 Jun 2021 11:46:42 +0200},
72
- biburl = {https://dblp.org/rec/journals/corr/abs-2105-15203.bib},
73
- bibsource = {dblp computer science bibliography, https://dblp.org}
74
- }
75
- ```
 
1
+ title: Myseg
2
+ emoji: ☃️
3
+ colorFrom: blue
4
+ colorTo: gray
5
+ sdk: gradio
6
+ sdk_version: 3.44.4
7
+ app_file: app.py
8
+ pinned: false