The goal of this app is to introduce deep learning enthusiast to computer vision, starting from basics and then turning to more modern deep learning models. Deep learning for Computer vision app will cover both image and video recognition, including image classification and annotation, object recognition and image search, various object detection techniques, motion estimation, object tracking in video, human action recognition, and finally image stylization, editing and new image generation. In course project, students will learn how to build face recognition and manipulation system to understand the internal mechanics of this technology, probably the most renown and often demonstrated in movies and TV-shows example of computer vision and AI.

Main Specific Topic:

✔ What is Deep Learning?.
✔ Image Fundamentals.
✔ Image Classification Basics.
✔ Datasets for Image Classification.
✔ Configuring Your Development Environment
✔ Create First Image Classifier.
✔ Parameterized Learning
✔ Optimization Methods and Regularization.
✔ Neural Network Fundamentals.
✔ Convolutional Neural Networks.
✔ Training Your First CNN .
✔ Saving and Loading Your Models
✔ LeNet: Recognizing Handwritten Digits.
✔ MiniVGGNet: Going Deeper with CNNs
✔ Learning Rate Schedulers.
✔ Spotting Underfitting and Overfitting.
✔ Checkpointing Models.
✔ Visualizing Network Architectures.
✔ Computer Vision Concepts and Practice examples
✔ Out-of-the-box CNNs for Classification.
✔ Python programming core topics.
✔ Data Science Topics Python Code examples.
✔ Machine Learning with Code examples.