TensorFlow Weekly Issue 5

TensorFlow Weekly Issue 5 — August 21, 2018

Hi there, these are the top TensorFlow links from my weekly curation. If you're having trouble viewing this email, please read the online version.

8 Things To Do Differently in Tensorflow’s Eager Execution Mode — One of my favorite videos from the Tensorflow 2018 Dev Summit is the one where Alex Passos introduces Tensorflow’s new Eager Execution mode...I tried out Eager on my last project, a fun little RNN to generate new Pokemon names. While building it, I discovered that there was more to using Eager than tf.enable_eager_execution(), especially for those of us who have already gotten used to the traditional Tensorflow way of doing things...
Sarah Wolf

Training and Serving ML models with tf.keras — In this blogpost, we will work through the process of training, exporting and serving a neural network with tf.keras. As an example, we will train a convolutional neural network on the Kaggle Planet dataset to predict labels for satellite images of the Amazon forest. The goal is to illustrate an end-to-end pipeline for a real-world use case...
Stijn Decubber

Gesture Detection Using Tensorflowjs — I recently built an end-to-end training tool for gesture recognition using deep learning...
Roshan Choxi

Neural Networks on Mobile Devices with TensorFlow Lite: A Tutorial — This will be a practical, end-to-end guide on how to build a mobile application using TensorFlow Lite that classifies images from a dataset for your projects...This application uses live camera and classifies objects instantly. The TFLite application will be smaller, faster, and more accurate than an application made using TensorFlow Mobile, because TFLite is made specifically to run neural nets on mobile platforms...We’ll be using the MobileNet model to train our network, which will keep the app smaller...
Sagar Sharma

How to build plant detector using tensorflow object detection model (Step by Step guide) — Nowadays technology are designed become more convenient to people. Object detection are widely applied in other field...Technological advancements in agriculture are necessary to increase productivity, quality and food security. In agriculture 4.0 research in applying Artificial Intelligence, Internet of Thing(IOT) technology to enhance in production crops...My task is research on develop a vision inspection software for Ginger Plant. In this project I will using Python with API Tensorflow and etc. My final research product is able to detect whether plant healthy, scroched, worm_eaten_plant...
Wey Wenn Wong

Emulating Logical Gates with a Neural Network — In this tutorial I want to show you how you can train a neural networks to perform the function of a network logical gates. I’m are going to dive into the purpose of each individual neuron in the network and show that none are wasted. We’ll ground this by using a problem example from Tensorflow Playground so that you can implement and experiment with this idea yourself.
James Fulton
 

Thanks for reading! If you have any feedback, just reply to this mail and I will get back to you.

Cheers,
Sebastian