This repo contains the kotlin implementation of TensorflowLite Example Apps here, which are mostly implemented in java rightnow. So if you like to see the kotlin, you can go through the repo!

Star ⭐️ this repo to support the project!

Congrats the project got accepted to Google Dev Library 🎉🎉

This is an end-to-end example of BERT Question & Answer application built with TensorFlow 2.0, and tested on SQuAD dataset.

Developed by: Dhruv Nagarajan

An Android app which uses the MiDaS model to perform monocular depth estimation on RGB images directly. The app displays a depth map over the live camera feed and works for both the front and the rear cameras.

Contributed from: this repo

End-to-end sample of a digit classifier model built with TensorFlow 2.0 (Keras API), and trained on MNIST dataset.

Added from: this repo

The used model, DeepLab is a state-of-art deep learning model for semantic image segmentation, where the goal is to assign semantic labels (e.g. person, dog, cat) to every pixel in the input image.

Added from: this repo

OCR is the process of recognizing characters from images using computer vision and machine learning techniques. This reference app demos how to use TensorFlow Lite to do OCR. It uses a text detection model and a text recognition model as a pipeline to recognize texts.

Added from: this repo

This is an app that continuously detects the body parts in the frames seen by your device's camera. These instructions walk you through building and running the demo on an Android device. In this Camera captures are discarded immediately after use, nothing is stored or saved.

Added from: this repo

This is an app that continuously detects the body parts in the frames seen by your device's camera. These instructions walk you through building and running the demo on an Android device. Camera captures are discarded immediately after use, nothing is stored or saved.

Added from: this repo

This application built with TensorFlow 2.0, and the model is trained based on the public MovieLens dataset. The dataset and model is used for research purpose.

Developed by: Dhruv Nagarajan

This Android application demonstrates how to classify sound on-device. It uses:

• TFLite Task Library
• YAMNet, an audio event classification model.

Added from: this repo

Artistic style transfer is an optimization technique used to take two images: a content image and a style reference image (such as an artwork by a famous painter) and blend them together so the output image looks like the content image, but “painted” in the style of the style reference image.

Added from: this repo

This is an end-to-end example of movie review sentiment classification built with TensorFlow 2.0 (Keras API), and trained on IMDB dataset. The demo app processes input movie review texts, and classifies its sentiment into negative (0) or positive (1).

Developed by: Sunit Roy

Zero-Reference Deep Curve Estimation or Zero-DCE formulates low-light image enhancement as the task of estimating an image-specific tonal curve with a deep neural network.

Developed by: Sunit Roy

📎On Device Training

📎Speech commands

📎Smart reply

📎Object detection

📎Model personalization

📎Super resolution

📎Gesture detection

📎Image classification

📎Reinforcement learning

• Adding all pre-existing example apps to the repo
• Designing & Creating other apps using the new Task API
• Designing & Creating example apps with the Interpreter, to show the implementation.
• Maintaining the Apps

Apache License 2.0