A reverse image search engine powered by elastic search and tensorflow
Explore the docs »

View Demo · Report Bug · Request Feature

Fork from sethuiyer/Image-to-Image-search.

• Anaconda
• Keras with Tensorflow Backend (Python 3.6)
• Elastic Search and elasticsearch-py (Elastic Search 6.0)

For more, check out requirements.txt

• Flickr-8k LSTM weights (flickr8k_cnn_lstm_v1.p)

Download this and paste it inside models folder.

• Install elasticsearch and always check if elastic search process is running before launching server.py or index_database.py.

• Instead of using the upload functionality, paste all your images inside static/img folder followed by python index_database.py to index all those images.

• If you want to delete the indexed images, do sh delete_index.sh

See the open issues for a list of proposed features (and known issues).

Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

Distributed under the MIT License. See LICENSE for more information.

• sethuiyer/Image-to-Image-search

• Sis

笔者所有文章遵循知识共享 署名 - 非商业性使用 - 禁止演绎 4.0 国际许可协议，欢迎转载，尊重版权。如果觉得本系列对你有所帮助，欢迎给我家布丁买点狗粮(支付宝扫码)~

您还可以前往 NGTE Books 主页浏览包含知识体系、编程语言、软件工程、模式与架构、Web 与大前端、服务端开发实践与工程架构、分布式基础架构、人工智能与深度学习、产品运营与创业等多类目的书籍列表：