Docker commands not running inside container when invoking from the command line

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
GPU

• DeepStream Version
Various

• JetPack Version (valid for Jetson only)
• TensorRT Version
Various

• NVIDIA GPU Driver Version (valid for GPU only)
N/A

• Issue Type( questions, new requirements, bugs)
question

• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
See below

• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

Hi All,

The default behaviour seems to have change with docker

Old behaviour:

Input:

docker run --rm nvcr.io/nvidia/deepstream:6.0-devel echo hello

Output:

hello

New behaviour:

Input:

docker run --rm nvcr.io/nvidia/deepstream:6.3-gc-triton-devel echo hello

Output:

===============================
   DeepStreamSDK 6.3.0
===============================

*** LICENSE AGREEMENT ***
By using this software you agree to fully comply with the terms and conditions
of the License Agreement. The License Agreement is located at
/opt/nvidia/deepstream/deepstream/LicenseAgreement.pdf. If you do not agree
to the terms and conditions of the License Agreement do not use the software.


=============================
== Triton Inference Server ==
=============================

NVIDIA Release 23.03 (build 56086596)
Triton Server Version 2.32.0

Copyright (c) 2018-2023, NVIDIA CORPORATION & AFFILIATES.  All rights reserved.

Various files include modifications (c) NVIDIA CORPORATION & AFFILIATES.  All rights reserved.

This container image and its contents are governed by the NVIDIA Deep Learning Container License.
By pulling and using the container, you accept the terms and conditions of this license:
https://developer.nvidia.com/ngc/nvidia-deep-learning-container-license

WARNING: The NVIDIA Driver was not detected.  GPU functionality will not be available.
   Use the NVIDIA Container Toolkit to start this container with GPU support; see
   https://docs.nvidia.com/datacenter/cloud-native/ .

How do I get the old behaviour back?

2

This is the closest I can get:

Input:

docker run --rm --entrypoint=/bin/bash nvcr.io/nvidia/deepstream:6.3-gc-triton-devel -c "echo hello"

Output:

hello
4

Could you describe how this issue specifically affects your use case?

5

Sure, I base my custom docker build from a deepstream base image. My Dockerfile injects my model, compiles the yolo plugin etc. My image is then ready to run inference.

I then have a script that loops over a bunch of video files. This script runs natively, not in docker. For each file, I call e.g. docker run --rm my-image <command>, passing in the commands/arguments to run inference on the file.

It should be noted that the old behaviour mimics the same output you get elsewhere:

docker run --rm ubuntu  echo hello
hello
6

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

OK. We’ll check that. Could you use the command you attached before first?

docker run --rm --entrypoint=/bin/bash nvcr.io/nvidia/deepstream:6.3-gc-triton-devel -c "echo hello"
7

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