Tobias Cornille commited on
Commit
d801a52
1 Parent(s): ff8c233

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -8,8 +8,8 @@ widget:
8
  - src: https://segmentsai-prod.s3.eu-west-2.amazonaws.com/assets/admin-tobias/439f6843-80c5-47ce-9b17-0b2a1d54dbeb.jpg
9
  example_title: Brugge
10
  ---
11
- # SegFormer (b0-sized) model fine-tuned on Segments.ai [`sidewalk-semantic`](https://huggingface.co/datasets/segments/sidewalk-semantic).
12
- SegFormer model fine-tuned on [Segments.ai](https://segments.ai) Sidewalk Semantic. 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).
13
  ## Model description
14
  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.
15
  ### How to use
 
8
  - src: https://segmentsai-prod.s3.eu-west-2.amazonaws.com/assets/admin-tobias/439f6843-80c5-47ce-9b17-0b2a1d54dbeb.jpg
9
  example_title: Brugge
10
  ---
11
+ # SegFormer (b0-sized) model fine-tuned on Segments.ai sidewalk-semantic.
12
+ SegFormer model fine-tuned on [Segments.ai](https://segments.ai) [`sidewalk-semantic`](https://huggingface.co/datasets/segments/sidewalk-semantic). 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).
13
  ## Model description
14
  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.
15
  ### How to use