Advanced Computer Vision with TensorFlow

Colleagues, the Advanced Computer Vision with TensorFlow program will equip you to explore image classification, image segmentation, object localization, object detection, apply transfer learning to object localization and detection. Apply object detection models such as regional-CNN and ResNet-50, customize existing models, and build your own models to detect, localize, and label your own rubber duck images. Implement image segmentation using variations of the fully convolutional network (FCN) including U-Net and mask-RCNN to identify and detect numbers, pets and zombies. Identify which parts of an image are being used by your model to make its predictions using class activation maps and saliency maps and apply machine learning interpretation methods to inspect and improve the design of AlexNet. Training modules include: 1) Introduction to Computer Vision: Describe multi-label classification, and distinguish between semantic segmentation and instance segmentation, 2) Object Detection: Understand object detection models, such as regional-CNN and ResNet-50. You’ll use object detection models that you’ll retrieve from TensorFlow Hub, download your own models and configure them for training, 3) Image Segmentation: Assign class labels to each pixel, and perform detailed identification of objects compared to bounding boxes. You will build the convolutional neural network, U-Net, and Mask R-CNN to identify, and 4) Visualization and Interpretability: Understand how your model arrives at its decisions and visualize a model’s intermediate layer activations.

Enroll today (individuals & teams welcome): https://tinyurl.com/h4uspery 

Much career success, Lawrence E. Wilson - Artificial Intelligence Academy