https://github.com/imvision12/segformer-tf
A Keras 3 Implementation of "SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers"
https://github.com/imvision12/segformer-tf
image-segmentation segformer segmentation semantic-segmentation tensorflow transformer
Last synced: about 1 month ago
JSON representation
A Keras 3 Implementation of "SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers"
- Host: GitHub
- URL: https://github.com/imvision12/segformer-tf
- Owner: IMvision12
- Created: 2023-01-31T11:51:07.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-03-01T16:27:41.000Z (about 1 year ago)
- Last Synced: 2025-03-24T23:06:18.486Z (about 2 months ago)
- Topics: image-segmentation, segformer, segmentation, semantic-segmentation, tensorflow, transformer
- Language: Jupyter Notebook
- Homepage:
- Size: 6.18 MB
- Stars: 10
- Watchers: 1
- Forks: 9
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# SegFormer-tf
This repository is about an implementation of the research paper "SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers"
SegFormer is a Transformer-based framework for semantic segmentation that unifies Transformers with lightweight multilayer perceptron (MLP) decoders.
#### Model Architecture :
#### Detailed overview of MiT :
# Usage:
Clone Github Repo:
```bash
$ git clone https://github.com/IMvision12/SegFormer-tf
$ cd SegFormer-tf
```
Then import model
```py
import tensorflow as tf
from models import SegFormer_B3
model = SegFormer_B3(input_shape = (224, 224, 3), num_classes = 19)
print(model.summary())
```
# References
[1] SegFormer paper: https://arxiv.org/pdf/2105.15203
[2] Official SegFormer Repo: https://github.com/NVlabs/SegFormer