đ SegFormer (b5-sized) Model
A SegFormer (b5-sized) model fine-tuned on the sidewalk-semantic dataset for image segmentation.
đ Quick Start
This SegFormer model is fine-tuned on SegmentsAI's sidewalk-semantic
dataset. It was introduced in the paper SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers by Xie et al. and first released in this repository.
⨠Features
- Hierarchical Transformer Encoder: SegFormer consists of a hierarchical Transformer encoder and a lightweight all - MLP decode head, which can achieve great results on semantic segmentation benchmarks such as ADE20K and Cityscapes.
- Pre - training and Fine - tuning: The hierarchical Transformer is first pre - trained on ImageNet - 1k, and then a decode head is added and fine - tuned altogether on a downstream dataset.
đģ Usage Examples
Basic Usage
from transformers import SegformerFeatureExtractor, SegformerForImageClassification
from PIL import Image
import requests
url = "https://segmentsai-prod.s3.eu-west-2.amazonaws.com/assets/admin-tobias/439f6843-80c5-47ce-9b17-0b2a1d54dbeb.jpg"
image = Image.open(requests.get(url, stream=True).raw)
feature_extractor = SegformerFeatureExtractor.from_pretrained("zoheb/mit-b5-finetuned-sidewalk-semantic")
model = SegformerForImageClassification.from_pretrained("zoheb/mit-b5-finetuned-sidewalk-semantic")
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits
predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])
Advanced Usage
You can go through its detailed notebook here. For more code examples, refer to the documentation.
đ Documentation
Model description
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.
đ License
The license for this model can be found here.
BibTeX entry and citation info
@article{DBLP:journals/corr/abs-2105-15203,
author = {Enze Xie and
Wenhai Wang and
Zhiding Yu and
Anima Anandkumar and
Jose M. Alvarez and
Ping Luo},
title = {SegFormer: Simple and Efficient Design for Semantic Segmentation with
Transformers},
journal = {CoRR},
volume = {abs/2105.15203},
year = {2021},
url = {https://arxiv.org/abs/2105.15203},
eprinttype = {arXiv},
eprint = {2105.15203},
timestamp = {Wed, 02 Jun 2021 11:46:42 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2105-15203.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
Information Table
Property |
Details |
Tags |
vision, image - segmentation |
Datasets |
segments/sidewalk - semantic |
Finetuned From |
nvidia/mit - b5 |
Widget Example |
Brugge |