search

NVIDIA / TensorRT

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
https://developer.nvidia.com/tensorrt
Apache License 2.0
10.75k stars 2.13k forks source link

Segmentation fault in int8 calibration using existing calibration cache file #669

Closed liming312 closed 4 years ago

liming312 commented 4 years ago

Description

When I convert a model to int8 quantized model using existing calibration cache file (just generated in last run), there is "Segmentation fault" error as shown in the image below. But I do the conversion with calibration data (do not use off-the-shell calibration cache file), there is no such error.

Environment

TensorRT Version: 7.0.0.11 GPU Type: Tesla T4 Nvidia Driver Version: 418.67 CUDA Version: 10.0 CUDNN Version: 7.6.5 Operating System + Version: Debian 9.11 Python Version (if applicable): 3.7.4 TensorFlow Version (if applicable): N/A PyTorch Version (if applicable): 1.4.0 Baremetal or Container (if container which image + tag):

Relevant Files

Here is the conversion output. The are many warnings above the first line in the image. image

tianwen0110 commented 2 years ago

hi, have you solved this problem?