Quantization

Share

In deep learning, quantization is the process of substituting floating-point weights and/or activations with low precision compact representations. As a result, the memory size and computational cost of using neural networks are decreased, which can be important for edge applications. Quantization is one of several optimization methods for reducing the size of neural networks while also achieving high-performance accuracy.

Filter terms by

Related resources

deci-updates-tensorboard-blog-featured-2
Open Source
deci-infery-updates-blog-featured
Engineering
deci-winter-release-2023-blog-featured-5
Algorithms