Explore

Image Understanding with TensorFlow on GCP

Approx. 12 hours to complete

Save Course

Go to Course

Course Summary

Learn how to use TensorFlow and Google Cloud Platform to build image recognition models and improve your skills in computer vision.

Key Learning Points

Understand the basics of image recognition and machine learning
Build and train image recognition models using TensorFlow and GCP
Learn how to deploy and scale your models on GCP

Learning Outcomes

Ability to build and train image recognition models using TensorFlow and GCP
Understanding of the basics of machine learning and computer vision
Knowledge of how to deploy and scale models on GCP

Prerequisites or good to have knowledge before taking this course

Basic programming knowledge in Python
Familiarity with machine learning concepts

Course Difficulty Level

Intermediate

Course Format

Online
Self-paced

Similar Courses

Deep Learning with TensorFlow
Applied Data Science with Python

Related Education Paths

Notable People in This Field

Founder, Coursera
Co-Director, Stanford Institute for Human-Centered Artificial Intelligence

Related Books

Description

This is the third course of the Advanced Machine Learning on GCP specialization. In this course,

We will take a look at different strategies for building an image classifier using convolutional neural networks. We'll improve the model's accuracy with augmentation, feature extraction, and fine-tuning hyperparameters while trying to avoid overfitting our data. We will also look at practical issues that arise, for example, when you don’t have enough data and how to incorporate the latest research findings into our models. You will get hands-on practice building and optimizing your own image classification models on a variety of public datasets in the labs we’ll work on together. Prerequisites: Basic SQL, familiarity with Python and TensorFlow

Outline

Welcome to Image Understanding with TensorFlow on GCP
Course Introduction
Getting Started with Google Cloud Platform and Qwiklabs
Images as Visual Data
Structured vs Unstructured Data
How to Send Feedback

Linear and DNN Models
Introduction
Linear Models
Lab Intro: Linear Models for Image Classification
Lab Solution: Linear Models for Image Classification
DNN Models Review
Lab Intro: DNN Models for Image Classification
Lab Solution: DNN Models for Image Classification
Review: What is Dropout?
Lab Intro: DNNs with Dropout Layer for Image Classification
Lab Solution: DNNs with Dropout Layer for Image Classification

Convolutional Neural Networks (CNNs)
Introduction
Understanding Convolutions
CNN Model Parameters
Working with Pooling Layers
Implementing CNNs with TensorFlow
Lab Intro: Creating an Image Classifier with a Convolutional Neural Network
Lab Solution: Creating an Image Classifier with a Convolutional Neural Network

Dealing with Data Scarcity
The Data Scarcity Problem
Data Augmentation
Lab Intro: Implementing image augmentation
Lab Solution: Implementing image augmentation
Transfer Learning
Lab Intro: Implementing Transfer Learning
Lab Solution: Implementing Transfer Learning
No Data, No Problem

Going Deeper Faster
Introduction
Batch Normalization
Residual Networks
Accelerators (CPU vs GPU, TPU)
TPU Estimator
Demo: TPU Estimator
Neural Architecture Search
Summary

Pre-built ML Models for Image Classification
Introduction
Pre-built ML Models
Cloud Vision API
Demo: Vision API
AutoML Vision
Demo: AutoML
AutoML Architecture
Lab Intro: Training with Pre-built ML Models using Cloud Vision API and AutoML
Lab Solution: Training with Pre-built ML Models using Cloud Vision API and AutoML

Summary
Summary
Additional Resources

Summary of User Reviews

This course on image understanding using TensorFlow on GCP has received positive reviews from many users. It provides a comprehensive understanding of image processing and is well-structured. One key aspect that many users thought was good is the hands-on experience it offers.

Pros from User Reviews

Comprehensive understanding of image processing
Well-structured course
Hands-on experience
Great for beginners
Engaging and informative lectures

Cons from User Reviews

Some users found the course to be too basic
Not enough information on advanced topics
Some sections were too fast-paced
No one-on-one support from instructors
Some technical issues with labs and assignments

Recommended for you

Deep Learning with Python - Novice to Pro!

Practical recipes on Neural Network modeling, Reinforcement & Transfer Learning using Python's Deep Learning tools Deep Learning is revolutionizing a wide range of industries....

Save Course

The Complete Guide to TensorFlow 1.x

Become an expert in machine learning and deep learning with the new TensorFlow 1. x If yes, then this course is for you!...

Save Course

Deep Learning for Beginners in Python: Work On 12+ Projects

Work On 12+ Projects, Deep Learning Python, TensorFlow 2. 0, Neural Networks, NLP, Data Science, Machine Learning, More ! . ....

Save Course

AI Workflow: Machine Learning, Visual Recognition and NLP

This is the fourth course in the IBM AI Enterprise Workflow Certification specialization.     Out-of-the-box Watson models for natural language understanding and visual recognition will be used....

Save Course