Quantcast
Channel: TAO Toolkit - NVIDIA Developer Forums
Viewing all articles
Browse latest Browse all 497

Calibration option on TensorRT FP16

$
0
0

We were using int8 model with calibration file for better accuracy and fast i want to know whether this calibration feature is available for FP16 model weights as well so that we can improve the accuracy of FP16

Reference used :

2 posts - 2 participants

Read full topic


Viewing all articles
Browse latest Browse all 497

Trending Articles