Inference with deepstream yolov5s-3.0 on 2 camera long delay (20-25s)

constantin.fite · March 12, 2021, 2:29pm

Description

Hi, I’m currently running inference with deepstream yolov5s-3.0 on 2 camera IP on a jetson nano 4GB and its runs with a long delay.
Here you can see the log

I saw that the jetson nano can handle multiple IP camera with full FPS. I have 20 seconds delay minimum.
My GPU is at 99% usage.

I tested with another model : yolov3 tiny and I had the same problem.

Environment

Deepstream:5.1
Jetpack: 4.5.1

Relevant Files

Here’s my config files and the model to run with deepstream

config_infer_primary.txt (444 Bytes) deepstream_app_config.txt (1.1 KB)
yolov5s.engine (19.9 MB)

Steps To Reproduce

I follow this tutorial to run yolov5 with deepstream :

github.com

marcoslucianops/DeepStream-Yolo/blob/master/YOLOv5.md

# YOLOv5
NVIDIA DeepStream SDK 5.1 configuration for YOLOv5 models

Thanks [DanaHan](https://github.com/DanaHan/Yolov5-in-Deepstream-5.0), [wang-xinyu](https://github.com/wang-xinyu/tensorrtx) and [Ultralytics](https://github.com/ultralytics/yolov5)

Supported version: YOLOv5 3.0/3.1

##

* [Requirements](#requirements)
* [Convert PyTorch model to wts file](#convert-pytorch-model-to-wts-file)
* [Convert wts file to TensorRT model](#convert-wts-file-to-tensorrt-model)
* [Compile nvdsinfer_custom_impl_Yolo](#compile-nvdsinfer_custom_impl_yolo)
* [Testing model](#testing-model)

##

### Requirements
* Python3
```

This file has been truncated. show original

I run the command deepstream-app -c deepstream_app_config.txt

If you have any idea ? Thanks

NVES · March 12, 2021, 1:37pm

Hi,
Can you try running your model with trtexec command, and share the “”–verbose"" log in case if the issue persist

You can refer below link for all the supported operators list, in case any operator is not supported you need to create a custom plugin to support that operation

github.com

onnx/onnx-tensorrt/blob/master/docs/operators.md

# Supported ONNX Operators

TensorRT 7.2 supports operators up to Opset 13. Latest information of ONNX operators can be found [here](https://github.com/onnx/onnx/blob/master/docs/Operators.md)

TensorRT supports the following ONNX data types: FLOAT32, FLOAT16, INT8, and BOOL

> Note: There is limited support for INT32 and INT64 types. TensorRT will attempt to cast down INT64 to INT32 where possible. If not possible, TensorRT will throw an error. See the [TensorRT layer support matrix](https://docs.nvidia.com/deeplearning/sdk/tensorrt-support-matrix/index.html#layers-precision-matrix) for more information on data type support.

## Operator Support Matrix

| Operator                  | Supported? | Restrictions                                                                                                                             |
|---------------------------|------------|------------------------------------------------------------------------------------------------------------------------------------------|
| Abs                       | Y          |
| Acos                      | Y          |
| Acosh                     | Y          |
| Add                       | Y          |
| And                       | Y          |
| ArgMax                    | Y          |
| ArgMin                    | Y          |
| Asin                      | Y          |

This file has been truncated. show original

Also, request you to share your model and script if not shared already so that we can help you better.

Thanks!

constantin.fite · March 12, 2021, 2:59pm

thanks for your reply,
I add the model in the post above

I run ./trtexec yolov5s.engine but it doesn’t support the model format

spolisetty · March 12, 2021, 3:37pm

Hi @constantin.fite,

You may get better help here. Please post your query in DeepStream forum.

Thank you.