33
/
AIzaSyB4mHJ5NPEv-XzF7P6NDYXjlkCWaeKw5bc
November 1, 2025
3909867
288434
1
Public Timelines
FAQ Get premium

mar 24, 2018 - QAT: Quantization and training of neural networks for efficient integer-arithmetic-only inference, CVPR

Description:

QAT employs the affine mapping of integers to real values with two constant parameters: Scale and Zeropoint. It first subtracts the Zero-point parameter from data (weights/activation), then divides the data by scale parameter, and finally getting the quantized results with rounding operation and affine mapping.

Added to timeline:

29 Mar 2020
1
0
808

Date:

mar 24, 2018
Now
~ 7 years and 6 months ago