arm-mirror

Here, we will be showcasing our seminar series “CPP for Image Processing and Machine Learning” including presentations and code examples. There are image processing and machine learning libraries out there which use C++ as a base and have become industry standards (ITK for medical imaging, OpenCV for computer vision and machine learning, Eigen for linear algebra, Shogun for machine learning). The documentation provided with these packages, though extensive, assume a certain level of experience with C++. Our tutorials are intended for those people who have basic understanding of medical image processing and machine learning but who are just starting to get their toes wet with C++ (and possibly have prior experience with Python or MATLAB). Here we will be focusing on how someone with a good theoretical background in image processing and machine learning can quickly prototype algorithms using CPP and extend them to create meaningful software packages.

Welcome to this 2 hour long guided project on creating and training an Object Localization model with TensorFlow. In this guided project, we are going to use TensorFlow's Keras API to create a convolutional neural network which will be trained to classify as well as localize emojis in images. Localization, in this context, means the position of the emojis in the images. This means that the network will have one input and two outputs. Think of this task as a simpler version of Object Detection. In Object Detection, we might have multiple objects in the input images, and an object detection model predicts the classes as well as bounding boxes for all of those objects. In Object Localization, we are working with the assumption that there is just one object in any given image, and our CNN model will classify and localize that object. Please note that you will need prior programming experience in Python. You will also need familiarity with TensorFlow. This is a practical, hands on guided project for learners who already have theoretical understanding of Neural Networks, Convolutional Neural Networks, and optimization algorithms like Gradient Descent but want to understand how to use use TensorFlow to solve computer vision tasks like Object Localization.