TensorRT INT8 engine calibration cache

AI & Data Science Deep Learning (Training & Inference) TensorRT
,
1

Description

To generate int8.engine, I’m calibrating .onnx file. After calibration process, calibration cache is generated where I can see dynamic range(?) for each layer. But it is hexadecimal(?). I’d like to know decimal number.

values in cahe file I got are, below
TRT-8001-EntropyCalibration2
input_0: 3c99d942
17: 3d654c77
18: 3d8b3dd1
19: 3d8b3dd1
20: 3d8b3dd1
output_0: 3e3977b6

But, I’d like to know decimal numbers which are something like below style
input_0: 1.00
17: 8.69
18: 8.69
19: 8.69
20: 12.8
output_0: 0.03

How can I convert numbers ?
3d8b3dd1 => 1032535505 => ??

Best regards.

Environment

TensorRT Version:
GPU Type:
Nvidia Driver Version:
CUDA Version:
CUDNN Version:
Operating System + Version:
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

Relevant Files

Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)

Steps To Reproduce

Please include:

  • Exact steps/commands to build your repro
  • Exact steps/commands to run your repro
  • Full traceback of errors encountered
3

Hi, Please refer to the below links to perform inference in INT8

Thanks!

5

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.