Int8 get the same result, but in FP16 the result is correct

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

Description

A clear and concise description of the bug or issue.

Environment

**TensorRT Version8.2.1.8:
**GPU Type2060:
Nvidia Driver Version:
**CUDA Version11.1:
**CUDNN Version8.1:
**Operating System + Versionwin10:
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

as said, in FP16 i can get the correct result, but when infer in int8 mode, the result is a fixed value， no matter the input changed.
in calibrationtable file ,i find many Unnamed Layer* . is there something wrong with my onnx model.

thanks for help
CAR_Frame_mobilev3_2021_10_22_17_15.onnx (16.0 MB)
calbrationTable.int8 (6.1 KB)

2

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

Thanks!