This course is about using deep learning to perform image segmentation with Tensorflow 2. It will show you a step by step guide on how to build powerful deep learning driven image segmentation tasks in computer vision.
The course will show you how to use Mask RCNN deep learning model in order to perform image segmentation. Mask RCNN is one of the widely used neural networks for image segmentation tasks.
The course will help you answer these questions:
1/ What is image segmentation?
2/ What are the different types of segmentation in computer vision?
3/ How do you prepare a custom dataset for training Mask RCNN model?
4/ What tools are used for annotating a dataset for image segmentation?
5/ How do you transform your images and annotations to tfrecords format?
6/ How do you use Tensorflow 2 object detection API for training Mask RCNN model?
7/ How do you use Tensorflow 2 object detection API for evaluating Mask RCNN model?
8/ How to run the training of Mask RCNN model on your local machine?
9/ How to create an account on google cloud platform (GCP)
10/ How to setup a project on google cloud platform (GCP)
11/ How to run the training of Mask RCNN model on google ai platform?
12/ How do you export a SavedModel from your training checkpoints?
13/ How do you use your SavedModel to perform image segmentation on new images?
14/ How do you use Mask RCNN to build a powerful image segmentation model for segmenting different parts of a damaged car (door, hood, lamps, ...). Which is by the way the course project!
And a lot more!
My strategy with this course is to enable you to build powerful AI solutions for image segmentation in computer vision.