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
10.55k stars 2.1k forks source link

Missing Data for the Samples #2018

Closed ismetdagli closed 2 years ago

ismetdagli commented 2 years ago

Description

I'm currently using Xavier AGX and AGX Orin platforms with 7.1.3 and 8.4.0 versions respectively. Many of the samples can't run because they throw missing data errors. Here are some of the names from my attempts:

-sample_fasterRCNN -sample_uff_ssd -sample_int8 -sample_ssd -sample_uff_mask_rcnn

Environment

TensorRT Version: 8.4.0 NVIDIA GPU: ORIN AGX with NVIDIA Ampere architecture NVIDIA Driver Version: CUDA Version: 11.4 CUDNN Version: Operating System: Ubuntu 20.04 Python Version (if applicable): Tensorflow Version (if applicable): PyTorch Version (if applicable): Baremetal or Container (if so, version):

Steps To Reproduce

$Go to /samples $make (compile all the samples) $Go to /bin $Run the samples seperately

zerollzeng commented 2 years ago

there is a corresponding readme in each sample that contains the data preparation like https://github.com/NVIDIA/TensorRT/tree/main/samples/sampleFasterRCNN, Perhaps that's what you are missing.

nvpohanh commented 2 years ago

Closing for now since there is not response for >14 days. Please reopen if the issue still exists. Thanks