From the course: Computer Vision for Data Scientists
Join today to access over 24,900 courses taught by industry experts.
EfficientNet
From the course: Computer Vision for Data Scientists
EfficientNet
- EfficientNet is a family of scalable and efficient deep neural network architectures that achieves state-of-the-art performance on various image classification tasks. Let's talk about some key points of this architecture. EfficientNet uses compound scaling to uniformly scale all dimensions of the depth, width, and resolution. This approach helps the network find an optimal balance between these dimensions at each scale. This results in better performance and more efficiency. As a network grows, each dimension grows in proportion. This allows EfficientNet to achieve more precise accuracy with as few parameters and FLOPS as possible. This, again, is what makes it an ideal architecture for resource constrained environments like mobile devices or small data centers. EfficientNet family is actually a family of eight architectures, ranging from EfficientNet B0, the baseline EfficientNet, to EfficientNet B7. Each subsequent model is…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.