https://github.com/xiaochus/MobileNetV3

A Keras implementation of MobileNetV3.
https://github.com/xiaochus/MobileNetV3

image-classification keras mobilenetv3

Last synced: 3 days ago
JSON representation

A Keras implementation of MobileNetV3.

• Host: GitHub
• URL: https://github.com/xiaochus/MobileNetV3
• Owner: xiaochus
• License: mit
• Created: 2019-05-18T04:51:07.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2020-03-23T08:02:12.000Z (over 4 years ago)
• Last Synced: 2024-08-31T22:38:22.761Z (2 months ago)
• Topics: image-classification, keras, mobilenetv3
• Language: Python
• Size: 261 KB
• Stars: 237
• Watchers: 11
• Forks: 84
• Open Issues: 10
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-image-classification - unofficial-keras : https://github.com/xiaochus/MobileNetV3
• awesome-image-classification - unofficial-keras : https://github.com/xiaochus/MobileNetV3

README

        
# MobileNetV3

A Keras implementation of MobileNetV3 and Lite R-ASPP Semantic Segmentation (Under Development).

According to the paper: [Searching for MobileNetV3](https://arxiv.org/abs/1905.02244?context=cs)

## Requirement

- Python 3.6

- Tensorflow-gpu 1.10.0  

- Keras 2.2.4

## Train the model

 The ```config/config.json``` file provide a config for training.

### Train the classification

**The dataset folder structure is as follows:**

	| - data/

		| - train/

	  		| - class 0/

				| - image.jpg

					....

			| - class 1/

			  ....

			| - class n/

		| - validation/

	  		| - class 0/

			| - class 1/

			  ....

			| - class n/

**Run command below to train the model:**

```

python train_cls.py

```

## Acknowledgement

Thank [@fzyzcjy](https://github.com/fzyzcjy) for your help in this project.

## Reference

	@article{MobileNetv3,  

	  title={Searching for MobileNetV3},  

	  author={Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang Vijay Vasudevan, Quoc V. Le, Hartwig Adam},

	  journal={arXiv preprint arXiv:1905.02244},

	  year={2019}

	}

## Copyright

See [LICENSE](LICENSE) for details.