pabaq / coursera-tensorflow-advanced-techniques-specialization Goto Github PK

This repository contains my work on the assignments and labs from the TensorFlow Advanced Techniques Specialization offered by deeplearning.ai on Coursera.

Expand your knowledge of the Functional API and build exotic non-sequential model types. Learn how to optimize training in different environments with multiple processors and chip types and get introduced to advanced computer vision scenarios such as object detection, image segmentation, and interpreting convolutions. Explore generative deep learning including the ways AIs can create new content from Style Transfer to Auto Encoding, VAEs, and GANs.

Understand the underlying basis of the Functional API and build exotic non-sequential model types, custom loss functions, and layers.

• Week 1 - Functional APIs
• Week 2 - Custom Loss Functions
• Week 3 - Custom Layers
• Week 4 - Custom Models

Learn how optimization works and how to use GradientTape and Autograph. Optimize training in different environments with multiple processors and chip types.

• Week 1 - Differentiation and Gradients
• Week 2 - Custom Training
• Week 3 - Graph Mode
• Week 4 - Distributed Training

Practice object detection, image segmentation, and visual interpretation of convolutions.

• Week 1 - Introduction to Computer Vision
• Week 2 - Object Detection
• Week 3 - Image Segmentation
• Week 4 - Visualization and Interpretability

Explore generative deep learning and how AI can create new content, from style transfer through auto-encoding and VAEs to generative adversarial networks.

• Week 1 - Style Transfer
• Week 2 - AutoEncoders
• Week 3 - Variational AutoEncoders
• Week 4 - GANs

Coursera TensorFlow Advanced Techniques Specialization