NVIDIA Developer Forums

How to know Quantization error in TensorRT2.1 for quantized models into INT8/FP16 ?

Accelerated Computing GPU-Accelerated Libraries

adit_bhrgv July 30, 2017, 1:11pm 1

Hello,

Can anyone please let me know if we can calculate or visualize the Quantization error in TensorRT2.1 using half-precision or INT8 quantization ?

Thanks for your help !

Topic		Replies	Views	Activity
pre-quantized models on Jetson AGX Xavier Jetson AGX Xavier	10	940	October 18, 2021
Int8 quantization TensorRT	1	484	December 16, 2021
Quantize model with pytorch-quantization Jetson Orin NX pytorch , generative_ai	4	777	April 3, 2024
TensorRT 8-bit Quantization questions TensorRT	7	4796	April 26, 2018
Q's on TensorRT GPU-Accelerated Libraries	3	1178	August 7, 2017
About the time taken for FP16 inference and int8 inference in TensorRT TensorRT tensorrt	1	336	November 15, 2023
Can TensorRT 7.1.3 convert an INT8 pytorch QAT model to engine? TensorRT	3	707	April 21, 2022
Quantization in TensorRt Jetson Nano tensorrt	6	1823	March 2, 2022
Unable to quantization FP8 in TensorRT TensorRT tensorrt	1	419	June 20, 2023
INT8 quantization with Torch-TensorRT fails TensorRT tensorrt , pytorch	3	871	June 29, 2022