Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/margaretmz/segmentation-style-transfer
A background stylizer Android app chaining 2 ML models: segmentation & style transfer.
https://github.com/margaretmz/segmentation-style-transfer
Last synced: about 8 hours ago
JSON representation
A background stylizer Android app chaining 2 ML models: segmentation & style transfer.
- Host: GitHub
- URL: https://github.com/margaretmz/segmentation-style-transfer
- Owner: margaretmz
- License: apache-2.0
- Created: 2020-06-28T01:56:42.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2021-01-20T19:27:52.000Z (almost 4 years ago)
- Last Synced: 2024-05-01T14:03:56.362Z (6 months ago)
- Language: Kotlin
- Homepage:
- Size: 53 MB
- Stars: 57
- Watchers: 7
- Forks: 8
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Background Stylizer - with Segmentation & Style Transfer
This is the GitHub repo for an end-to-end tutorial from TFLite model conversion, to model deployment on an Android and iOS. This project received the [#TFCommunitySpotlight award](https://twitter.com/TensorFlow/status/1351590466068783105) for its creativity and real-world user scenarios. This is one of the [End-to-End TensorFlow Lite Tutorials](https://github.com/ml-gde/e2e-tflite-tutorials). See the full list of TensorFlow Lite samples and learning resources on [awesome-tflite](https://github.com/margaretmz/awesome-tflite).
Links to the multi-part tutorial blog posts on Medium:
1. [Project Intro](https://medium.com/@margaretmz/image-background-stylizer-part-1-project-intro-d68c4547e7e3), [Margaret Maynard-Reid](https://twitter.com/margaretmz)
2. [TensorFlow Lite models](https://medium.com/@spsayakpaul/e614af91944d), [Sayak Paul](https://twitter.com/RisingSayak)
3. [Android implementation](https://farmaker47.medium.com/android-part-of-create-artistic-effect-by-stylizing-an-image-segment-2a646da2d39a), [George Soloupis](https://www.linkedin.com/in/george-soloupis/)
4. iOS implementation, Patrick Haralabidis (coming soon)
This project combines multiple CV models to create visually appealing demo that run in real time on device. For example, [segmentation plus style transfer]; or segmentation plus background removal ([1](https://ai.googleblog.com/2018/03/mobile-real-time-video-segmentation.html) | [2](https://twitter.com/jason_mayes/status/1229547600895823873))
Demo created by [Sayak Paul](https://github.com/sayakpaul) ([Colab Notebook](https://colab.research.google.com/github/sayakpaul/Adventures-in-TensorFlow-Lite/blob/master/Semantic_Segmentation_%2B_Background_Removal_%2B_Style_Transfer.ipynb))
Demo created by [Khanh LeViet](https://github.com/khanhlvg) ([Colab Notebook](https://colab.research.google.com/drive/1KZpmuwBfLZM_0mzUyX2W-xcNq26jCNtn))
## Acknowledgement
We would like to thank the TensorFlow Lite team and the ML GDEs Google Developers Expert Program for their collaboration and continuous support. This project is also a great showcase of community collabration by members of diverse geographic areas (U.S., India, Greece and Austrialia), expertise and background.
