One of the major difficulties with image classification models is the lack of labeled data. It is difficult to assemble a labeled dataset of sufficient size to train a model well; it is an extremely time consuming and laborious task. This is not such a problem for MNIST, since the images are relatively simple. They are greyscale and largely consist only of target features, there are no distracting background features, and the images are all aligned the same way and are of the same scale. A small dataset of 60,000 images is quite sufficient to train a model well. It is rare to find such a well-organized and consistent dataset in the problems we encounter in real life. Images are often of variable quality, and the target features can be obscured or distorted. They can also be of widely variable scales and rotations. The solution is to use a model architecture that...
- Tech Categories
- Best Sellers
- New Releases
- Books
- Videos
- Audiobooks
Tech Categories Popular Audiobooks
- Articles
- Newsletters
- Free Learning
You're reading from Deep Learning with PyTorch Quick Start Guide
David Julian is a freelance technology consultant and educator. He has worked as a consultant for government, private, and community organizations on a variety of projects, including using machine learning to detect insect outbreaks in controlled agricultural environments (Urban Ecological Systems Ltd., Bluesmart Farms), designing and implementing event management data systems (Sustainable Industry Expo, Lismore City Council), and designing multimedia interactive installations (Adelaide University). He has also written Designing Machine Learning Systems With Python for Packt Publishing and was a technical reviewer for Python Machine Learning and Hands-On Data Structures and Algorithms with Python - Second Edition, published by Packt.
Read more about David Julian
Unlock this book and the full library FREE for 7 days
Author (1)
David Julian is a freelance technology consultant and educator. He has worked as a consultant for government, private, and community organizations on a variety of projects, including using machine learning to detect insect outbreaks in controlled agricultural environments (Urban Ecological Systems Ltd., Bluesmart Farms), designing and implementing event management data systems (Sustainable Industry Expo, Lismore City Council), and designing multimedia interactive installations (Adelaide University). He has also written Designing Machine Learning Systems With Python for Packt Publishing and was a technical reviewer for Python Machine Learning and Hands-On Data Structures and Algorithms with Python - Second Edition, published by Packt.
Read more about David Julian