Computer Vision Essential Training: Deep Learning for Image Classification

Focused View

Harpreet Sahota

4:01:47

42 View

01 - Introduction

01 - Computer vision introduction.mp4

00:51

02 - What you should know.mp4

02:32

02 - 1. Computer Vision

01 - What is computer vision.mp4

02:21

02 - A history of computer vision.mp4

05:43

03 - Limitations of traditional CV techniques.mp4

03:53

04 - ImageNet.mp4

05:32

05 - The deep learning revolution.mp4

04:34

03 - 2. Introduction to Convolutional Neural Networks

01 - Overview of CNNs.mp4

06:25

02 - Why CNNs.mp4

03:04

03 - Convolutional layers.mp4

08:24

04 - Types of convolutions.mp4

15:39

05 - Pooling layers.mp4

04:50

06 - Activation functions.mp4

05:55

07 - Fully connected layers.mp4

04:29

04 - 3. How Networks Are Trained

01 - Supervised learning and loss functions.mp4

04:14

02 - Backpropagation in CNNs.mp4

05:33

03 - Optimization techniques.mp4

06:56

04 - Regularization and data augmentation.mp4

06:23

05 - 4. The Evolution of CNN Architectures

01 - LeNet.mp4

07:30

02 - AlexNet.mp4

06:35

03 - VGG.mp4

04:53

04 - ResNet.mp4

05:56

05 - MobileNetV1.mp4

04:15

06 - MobileNetV2.mp4

05:23

07 - MobileNetV3.mp4

08:49

08 - EfficientNet.mp4

07:10

06 - 5. Transfer Learning

01 - Introduction to transfer learning.mp4

03:13

02 - Types of transfer learning.mp4

04:30

03 - Steps in feature extracting and fine-tuning.mp4

03:48

04 - Best practices for transfer learning.mp4

05:20

07 - 6. PyTorch Crash Course

01 - Setting up the environment.mp4

03:01

02 - Dataset and DataLoader.mp4

03:46

03 - Training setup.mp4

03:22

04 - The training loop.mp4

03:23

05 - Testing and evaluation.mp4

02:57

06 - Inference.mp4

02:42

08 - 7. Hands-on Transfer Learning with SuperGradients

01 - Introduction to SuperGradients.mp4

02:21

02 - The trainer.mp4

04:14

03 - Required training params.mp4

03:50

04 - Optional training params.mp4

06:39

05 - Training the model.mp4

03:13

06 - Predicting with the model.mp4

04:28

07 - How to solve almost any image classification problem with SG.mp4

06:19

09 - 8. Training Tricks

01 - Exponential moving average.mp4

03:44

02 - Weight averaging.mp4

04:14

03 - Batch accumulation.mp4

04:29

04 - Precise BatchNorm.mp4

03:21

05 - Zero weight decay on BatchNorm and bias.mp4

02:37

06 - Training tricks in SuperGradients.mp4

07:35

10 - Conclusion

01 - Next steps.mp4

00:52

Description

Computer vision has come a long way since its humble beginnings. And today, it’s one of the most talked-about fields in tech. Join instructor Harpreet Sahota in this comprehensive overview of the history and evolution of this increasingly important industry, developing your understanding of convolutional neural networks, network training, deep learning models for image classification tasks, transfer learning with pretrained models, and more. Explore the wide variety of functionalities offered by the SuperGradients flexible training library, which gives you the power to shorten and streamline the model development lifecycle. Along the way, Harpreet shares practical insights on how to train models and networks more effectively, applying state-of-the-art techniques like exponential moving average, weighted average, batch accumulation, and BatchNorm.

Note: This course requires a basic working knowledge of machine learning as well as experience with Python and PyTorch.

More details

User Reviews

Rating

average 0

Total votes0

Focused display

Machine Learning

Artificial Intelligence

Computer Vision

Harpreet Sahota

Instructor's Courses

Linkedin Learning

View courses Linkedin Learning

LinkedIn Learning is an American online learning provider. It provides video courses taught by industry experts in software, creative, and business skills. It is a subsidiary of LinkedIn. All the courses on LinkedIn fall into four categories: Business, Creative, Technology and Certifications. It was founded in 1995 by Lynda Weinman as Lynda.com before being acquired by LinkedIn in 2015. Microsoft acquired LinkedIn in December 2016.