DevMesh

Selfie2Anime with TFLite

Sayak Paul

Sayak Paul

Kolkata, West Bengal

0 0
  • 0 Collaborators

The project demonstrates an end-to-end use case for deploying a deep learning model (that turns a selfie into an anime) in form of an Android application. This is a joint work with Margaret Maynard-Reid. ...learn more

Project status: Published/In Market

Artificial Intelligence

Intel Technologies
Intel Python

Code Samples [1]

Overview / Usage

The project demonstrates a workflow on how to convert a TF 1.x model to TensorFlow Lite (TFLite) and then deploy it to an Android app for transforming a selfie image to a plausible anime.

Methodology / Approach

We used a Generative Adversarial Network (GAN) model proposed in this paper Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation (also known as U-GAT-IT). The paper provides two generators: one that converts a selfie to anime-style image and the other one from anime to selfie. Here we only implemented the Selfie2Anime model since it better resembles the real-world scenario.

Technologies Used

  • TensorFlow

  • TensorFlow Lite

  • Android Studio

Repository

https://github.com/margaretmz/selfie2anime-with-tflite

Comments (0)