Latest Courses
The Basics of Blockchain & HyperLedger FabricCheck course
APIs in Action: Build API-Based ApplicationsCheck course
JavaScript - The Complete Modern JavaScript Masterclass 2020Check course
Python programming Bible - From Beginner to AdvancedCheck course
Learn Pro Advanced Python ProgrammingCheck course
Javascript Certification practice using HTML5 , HTML, CSS3Check course
JavaScript for BeginnersCheck course
Data Science, Deep Learning and Machine Learning with PythonCheck course
Learning Path: Java: Natural Language Processing with JavaCheck course
The Basics of Blockchain & HyperLedger FabricCheck course
APIs in Action: Build API-Based ApplicationsCheck course
JavaScript - The Complete Modern JavaScript Masterclass 2020Check course
Python programming Bible - From Beginner to AdvancedCheck course
Project: Classification with Transfer Learning in Keras

Project: Classification with Transfer Learning in Keras

Add your review
Add to wishlistAdded to wishlistRemoved from wishlist 0
Add to compare
8.3/10 (Our Score)
Product is rated as #204 in category Machine Learning

In this 1.5 hour long project–based course, you will learn to create and train a Convolutional Neural Network (CNN) with an existing CNN model architecture, and its pre–trained weights. We will use the MobileNet model architecture along with its weights trained on the popular ImageNet dataset. By using a model with pre–trained weights, and then training just the last layers on a new dataset, we can drastically reduce the training time required to fit the model to the new data . The pre–trained model has already learned to recognize thousands on simple and complex image features, and we are using its output as the input to the last layers that we are training. In order to be successful in this project, you should be familiar with Python, Neural Networks, and CNNs. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions. Rhyme is Coursera’s hands–on project–based learning platform. On Rhyme, learners get instant access to pre–configured cloud desktops containing all the software and data they need. Rhyme helps learners apply the knowledge they learned in other Coursera courses into specific tools and use–cases. So they become …

Instructor Details

Amit is a Machine Learning Engineer with focus in creating deep learning based computer vision and signal processing products. He has led chat bot development at a large corporation in the past. Amit is one of the Machine Learning and Data Science instructors at Rhyme.

Specification: Project: Classification with Transfer Learning in Keras

Duration 4 hours
Year 2020
Level Intermediate
Certificate Yes
Quizzes Yes

2 reviews for Project: Classification with Transfer Learning in Keras

4.0 out of 5
0
2
0
0
0
Write a review
Show all Most Helpful Highest Rating Lowest Rating
  1. Avatar

    Ali E

    Good course, but still misses a key step: how to save and reuse the modified model without having to rebuild it from scratch? Literature about this topic is at best ambiguous if not flat out lacking. You should include the method for saving and reloading customized models with custom layers and/or standard layers that have been added to the pre trained models.

    Helpful(0) Unhelpful(0)You have already voted this
  2. Avatar

    Utkarsh R

    Learning a topic using Hands on project is way better than passive learning in my opinion. Explanation could’ve been much better. They can use slides and animation to explain the core functioning of objects.

    Helpful(0) Unhelpful(0)You have already voted this

    Add a review

    Your email address will not be published. Required fields are marked *

    This site uses Akismet to reduce spam. Learn how your comment data is processed.

    Project: Classification with Transfer Learning in Keras
    Project: Classification with Transfer Learning in Keras

    Price tracking

    Register New Account
    Reset Password
    Compare items
    • Total (0)
    Compare