Vitis AI Quantizer - 1.4.1 English

Vitis AI User Guide (UG1414)

Document ID
Release Date
1.4.1 English

By converting the 32-bit floating-point weights and activations to fixed-point like INT8, the Vitis AI quantizer can reduce the computing complexity without losing prediction accuracy. The fixed-point network model requires less memory bandwidth, thus providing faster speed and higher power efficiency than the floating-point model.

Figure 1. Vitis AI Quantizer