Computer Vision for Data Scientists
Offered By: LinkedIn Learning
Course Description
Overview
Get a comprehensive introduction to computer vision and learn how to train models and neural networks for image classification.
Syllabus
Introduction
- Computer vision introduction
- What you should know
- What is computer vision?
- A history of computer vision
- Limitations of traditional CV techniques
- ImageNet
- The deep learning revolution
- Overview of CNNs
- Why CNNs?
- Convolutional layers
- Types of convolutions
- Pooling layers
- Activation functions
- Fully connected layers
- Supervised learning and loss functions
- Backpropagation in CNNs
- Optimization techniques
- Regularization and data augmentation
- LeNet
- AlexNet
- VGG
- ResNet
- MobileNetV1
- MobileNetV2
- MobileNetV3
- EfficientNet
- Introduction to transfer learning
- Types of transfer learning
- Steps in feature extracting and fine-tuning
- Best practices for transfer learning
- Setting up the environment
- Dataset and DataLoader
- Training setup
- The training loop
- Testing and evaluation
- Inference
- Introduction to SuperGradients
- The trainer
- Required training params
- Optional training params
- Training the model
- Predicting with the model
- How to solve almost any image classification problem with SG
- Exponential moving average
- Weight averaging
- Batch accumulation
- Precise BatchNorm
- Zero weight decay on BatchNorm and bias
- Training tricks in SuperGradients
- Next steps
Taught by
Harpreet Sahota
Related Courses
Deep Learning with Python and PyTorch.IBM via edX Introduction to Machine Learning
Duke University via Coursera How Google does Machine Learning em Português Brasileiro
Google Cloud via Coursera Intro to Deep Learning with PyTorch
Facebook via Udacity Secure and Private AI
Facebook via Udacity