We will use Ubuntu image as base, for that we should extend our new image from ubuntu official repository. As we are going to run object detection example we need to install all dependencies. All steps you can find on installation page. For detailed steps to install Tensorflow, follow the Tensorflow installation instructions. Let's make /tensorflow/models/research our working directory: The Tensorflow Object Detection API uses Protobufs to configure model and training parameters.

Whether you are counting cars on a road or people who are stranded on rooftops in a natural disaster, there are plenty of use cases for object detection. Often times, pre-trained object detection models do not suit your needs and you need to create your own custom models. How can you use machine learning to train your own custom model without substantive computing power and time? How can you use your custom-trained model to detect objects, in real time, with complete user privacy, all on a device with limited computing power? In this code pattern, you'll build an iOS, Android, or web app (or all three) that lets you use your own custom-trained models to detect objects.

This allows for more fine-grained information about the extent of the object within the box. So when would we need this extra granularity?

This allows for more fine-grained information about the extent of the object within the box. So when would we need this extra granularity?

This allows for more fine-grained information about the extent of the object within the box. So when would we need this extra granularity?

We discussed her blog post and GitHub project where she wrote an iOS app that detects Taylor Swift in pictures. More notably, she's open-sourced the code, so you can make your own Taylor Swift detector! Of course, you can train the model on whatever it is that you want to detect. The TensorFlow team recently updated the model to not only draw a bounding box, but also fill in the specific region of the image where the detection happened, which is absolutely magical! Check out the video above for the full interview, where we break down, step-by-step and piece-by-piece, the process Sara went through to get this built.

Deep inside the many functionalities and tools of TensorFlow, lies a component named TensorFlow Object Detection API. The purpose of this library, as the name says, is to train a neural network capable of recognizing objects in a frame, for example, an image. The use cases and possibilities of this library are almost limitless. It could be trained to detect people in an image, cats, cars, raccoons and many more. Due to this reason, I became interested in trying it myself with a custom model trained on my own.