Fine-tuning Convolutional Networks to Classify Dog Breeds

Offered By
Coursera Project Network
In this Guided Project, you will:

Create TensorFlow pipelines

Interpret model performance and ask poignant questions about the data

Fine-tune large-scale model on our niche dataset

Clock2 hours
IntermediateIntermediate
CloudNo download needed
VideoSplit-screen video
Comment DotsEnglish
LaptopDesktop only

In this 2 hour-long project, you will learn how to approach an image classification task using TensorFlow. You will learn how to effectively preprocess your data to improve model generalizability, as well as build a performant modeling pipeline. Furthermore, you will learn how to accurately evaluate model performance using a confusion matrix; how to interpret results; and how to ask poignant questions about your dataset. Finally, you will fine-tune an existing, state-of-the-art-ready model to improve performance further. 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.

Skills you will develop

Convolutional Neural NetworkMachine LearningImage PreprocessingTensorflowFine-tuning

Learn step-by-step

In a video that plays in a split-screen with your work area, your instructor will walk you through these steps:

  1. Introduction to the project and exploratory data analysis

  2. Convolutional Neural Network quickstart guide

  3. Dataset (image) preprocessing

  4. Building a performant model pipeline

  5. Designing and evaluating a basic Convolutional Neural Network

  6. Fine-tuning a large-scale model for our usecase

How Guided Projects work

Your workspace is a cloud desktop right in your browser, no download required

In a split-screen video, your instructor guides you step-by-step

Frequently asked questions

Frequently Asked Questions

More questions? Visit the Learner Help Center.