YoVDO

Fine-tuning Convolutional Networks to Classify Dog Breeds

Offered By: Coursera Project Network via Coursera

Tags

Convolutional Neural Networks (CNN) Courses Deep Learning Courses TensorFlow Courses Image Classification Courses Data Preprocessing Courses Model Evaluation Courses Confusion Matrix Courses

Course Description

Overview

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.

Syllabus

  • Fine-tuning Convolutional Networks to Classify Dog Breeds
    • 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.

Taught by

Ari Anastassiou

Related Courses

Clasificación de imágenes: ¿cómo reconocer el contenido de una imagen?
Universitat Autònoma de Barcelona (Autonomous University of Barcelona) via Coursera
Core ML: Machine Learning for iOS
Udacity
Fundamentals of Deep Learning for Computer Vision
Nvidia via Independent
Computer Vision and Image Analysis
Microsoft via edX
Using GPUs to Scale and Speed-up Deep Learning
IBM via edX