Deploying to DeepStream for YOLOv4

The deep learning and computer vision models that you’ve trained can be deployed on edge devices, such as a Jetson Xavier or Jetson Nano, a discrete GPU, or in the cloud with NVIDIA GPUs. TAO Toolkit has been designed to integrate with DeepStream SDK, so models trained with TAO Toolkit will work out of the box with DeepStream SDK.

DeepStream SDK is a streaming analytic toolkit to accelerate building AI-based video analytic applications. This section will describe how to deploy your trained model to DeepStream SDK.

To deploy a model trained by TAO Toolkit to DeepStream we have two options:

Option 1: Integrate the .etlt model directly in the DeepStream app. The model file is generated by export.
Option 2: Generate a device-specific optimized TensorRT engine using TAO Deploy. The generated TensorRT engine file can also be ingested by DeepStream.
Option 3 (Deprecated for x86 devices): Generate a device-specific optimized TensorRT engine using TAO Converter.

Machine-specific optimizations are done as part of the engine creation process, so a distinct engine should be generated for each environment and hardware configuration. If the TensorRT or CUDA libraries of the inference environment are updated (including minor version updates), or if a new model is generated, new engines need to be generated. Running an engine that was generated with a different version of TensorRT and CUDA is not supported and will cause unknown behavior that affects inference speed, accuracy, and stability, or it may fail to run altogether.

Option 1 is very straightforward. The .etlt file and calibration cache are directly used by DeepStream. DeepStream will automatically generate the TensorRT engine file and then run inference. TensorRT engine generation can take some time depending on size of the model and type of hardware.

Engine generation can be done ahead of time with Option 2: TAO Deploy is used to convert the .etlt file to TensorRT; this file is then provided directly to DeepStream. The TAO Deploy workflow is similar to TAO Converter, which is deprecated for x86 devices from TAO version 4.0.x but is still required for deployment to Jetson devices.

See the Exporting the Model section for more details on how to export a TAO model.

TensorRT Open Source Software (OSS)

Important

As of 5.0.0, tao model converter is deprecated. This method may not be available in the future releases. This section is only applicable if you’re still using tao model converter for legacy. For tao deploy, please jump to Integrating YOLOv4 Model.

The TensorRT OSS build is required for YOLOv4 models. This is required because several TensorRT plugins that are required by these models are only available in TensorRT open source repo and not in the general TensorRT release. Specifically, for YOLOv4, we need the batchTilePlugin and batchedNMSPlugin.

If the deployment platform is x86 with an NVIDIA GPU, follow the TensorRT OSS on x86 instructions; if your deployment is on an NVIDIA Jetson platform, follow the TensorRT OSS on Jetson (ARM64) instructions.

TensorRT OSS on x86

Building TensorRT OSS on x86:

Install Cmake (>=3.13).

Note

TensorRT OSS requires cmake >= v3.13, so install cmake 3.13 if your cmake version is lower than 3.13c

Copy
Copied!

            
            sudo apt remove --purge --auto-remove cmake
wget https://github.com/Kitware/CMake/releases/download/v3.13.5/cmake-3.13.5.tar.gz
tar xvf cmake-3.13.5.tar.gz
cd cmake-3.13.5/
./configure
make -j$(nproc)
sudo make install
sudo ln -s /usr/local/bin/cmake /usr/bin/cmake

Get GPU architecture. The GPU_ARCHS value can be retrieved by the deviceQuery CUDA sample:

Copy
Copied!

            
            cd /usr/local/cuda/samples/1_Utilities/deviceQuery
sudo make
./deviceQuery

If the /usr/local/cuda/samples doesn’t exist in your system, you could download deviceQuery.cpp from this GitHub repo. Compile and run deviceQuery.

Copy
Copied!

            
            nvcc deviceQuery.cpp -o deviceQuery
./deviceQuery

This command will output something like this, which indicates the GPU_ARCHS is 75 based on CUDA Capability major/minor version.

Copy
Copied!

            
            Detected 2 CUDA Capable device(s)

Device 0: "Tesla T4"
  CUDA Driver Version / Runtime Version          10.2 / 10.2
  CUDA Capability Major/Minor version number:    7.5

Build TensorRT OSS:

Copy
Copied!

            
            git clone -b 21.08 https://github.com/nvidia/TensorRT
cd TensorRT/
git submodule update --init --recursive
export TRT_SOURCE=`pwd`
cd $TRT_SOURCE
mkdir -p build && cd build

Note

Make sure your GPU_ARCHS from step 2 is in TensorRT OSS CMakeLists.txt. If GPU_ARCHS is not in TensorRT OSS CMakeLists.txt, add -DGPU_ARCHS=<VER> as below, where <VER> represents GPU_ARCHS from step 2.

Copy
Copied!

            
            /usr/local/bin/cmake .. -DGPU_ARCHS=xy  -DTRT_LIB_DIR=/usr/lib/x86_64-linux-gnu/ -DCMAKE_C_COMPILER=/usr/bin/gcc -DTRT_BIN_DIR=`pwd`/out
make nvinfer_plugin -j$(nproc)

After building ends successfully, libnvinfer_plugin.so* will be generated under \`pwd\`/out/.

Replace the original libnvinfer_plugin.so*:

Copy
Copied!

            
            sudo mv /usr/lib/x86_64-linux-gnu/libnvinfer_plugin.so.8.x.y ${HOME}/libnvinfer_plugin.so.8.x.y.bak   // backup original libnvinfer_plugin.so.x.y
sudo cp $TRT_SOURCE/`pwd`/out/libnvinfer_plugin.so.8.m.n  /usr/lib/x86_64-linux-gnu/libnvinfer_plugin.so.8.x.y
sudo ldconfig

TensorRT OSS on Jetson (ARM64)

Install Cmake (>=3.13)

Note

TensorRT OSS requires cmake >= v3.13, while the default cmake on Jetson/Ubuntu 18.04 is cmake 3.10.2.

Upgrade TensorRT OSS using:

Copy
Copied!

            
            sudo apt remove --purge --auto-remove cmake
wget https://github.com/Kitware/CMake/releases/download/v3.13.5/cmake-3.13.5.tar.gz
tar xvf cmake-3.13.5.tar.gz
cd cmake-3.13.5/
./configure
make -j$(nproc)
sudo make install
sudo ln -s /usr/local/bin/cmake /usr/bin/cmake

Get GPU architecture based on your platform. The GPU_ARCHS for different Jetson platform are given in the following table.

Jetson Platform GPU_ARCHS

Nano/Tx1 53

Tx2 62

AGX Xavier/Xavier NX 72

Build TensorRT OSS:

Copy
Copied!

            
            git clone -b 21.03 https://github.com/nvidia/TensorRT
cd TensorRT/
git submodule update --init --recursive
export TRT_SOURCE=`pwd`
cd $TRT_SOURCE
mkdir -p build && cd build

Note

The -DGPU_ARCHS=72 below is for Xavier or NX, for other Jetson platform, change 72 referring to GPU_ARCHS from step 2.

Copy
Copied!

            
            /usr/local/bin/cmake .. -DGPU_ARCHS=72  -DTRT_LIB_DIR=/usr/lib/aarch64-linux-gnu/ -DCMAKE_C_COMPILER=/usr/bin/gcc -DTRT_BIN_DIR=`pwd`/out
make nvinfer_plugin -j$(nproc)

After building ends successfully, libnvinfer_plugin.so* will be generated under ‘pwd’/out/.

Replace "libnvinfer_plugin.so*" with the newly generated.

Copy
Copied!

            
            sudo mv /usr/lib/aarch64-linux-gnu/libnvinfer_plugin.so.8.x.y ${HOME}/libnvinfer_plugin.so.8.x.y.bak   // backup original libnvinfer_plugin.so.x.y
sudo cp `pwd`/out/libnvinfer_plugin.so.8.m.n  /usr/lib/aarch64-linux-gnu/libnvinfer_plugin.so.8.x.y
sudo ldconfig

Integrating the model with DeepStream

To integrate a model trained by TAO Toolkit with DeepStream, you should generate a device-specific optimized TensorRT engine using TAO Deploy.. The generated TensorRT engine file can then be ingested by DeepStream. DeepStream can also generate TensorRT engine on-the-fly for YOLOv4 if only ONNX models are provided.

For YOLOv4, you will need to build the TensorRT open-source plugins and custom bounding-box parser. The instructions to build TensorRT open-source plugins are provided in the TensorRT Open Source Software (OSS) section above. The instructions to build a custom bounding-box parser are provided in the Prerequisites for YOLOv4 Model section below, and the required code can be found in this GitHub repo.

To integrate the models with DeepStream, you need the following:

Download and install DeepStream SDK. The installation instructions for DeepStream are provided in the DeepStream Development Guide.
An exported .onnx model file and optional calibration cache for INT8 precision.
TensorRT 7+ OSS Plugins .
A labels.txt file containing the labels for classes in the order in which the networks produces outputs.
A sample config_infer_*.txt file to configure the nvinfer element in DeepStream. The nvinfer element handles everything related to TensorRT optimization and engine creation in DeepStream.

DeepStream SDK ships with an end-to-end reference application which is fully configurable. Users can configure input sources, inference model, and output sinks. The app requires a primary object detection model, followed by an optional secondary classification model. The reference application is installed as deepstream-app. The graphic below shows the architecture of the reference application.

There are typically 2 or more configuration files that are used with this app. In the install directory, the config files are located in samples/configs/deepstream-app or sample/configs/tlt_pretrained_models. The main config file configures all the high level parameters in the pipeline above. This would set input source and resolution, number of inferences, tracker and output sinks. The other supporting config files are for each individual inference engine. The inference specific config files are used to specify models, inference resolution, batch size, number of classes and other customization. The main config file will call all the supporting config files. Here are some config files in samples/configs/deepstream-app for your reference.

source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt: Main config file
config_infer_primary.txt: Supporting config file for primary detector in the pipeline above
config_infer_secondary_*.txt: Supporting config file for secondary classifier in the pipeline above

The deepstream-app will only work with the main config file. This file will most likely remain the same for all models and can be used directly from the DeepStream SDK will little to no change. User will only have to modify or create config_infer_primary.txt and config_infer_secondary_*.txt.

Integrating a YOLOv4 Model

To run a YOLOv4 model in DeepStream, you need a label file and a DeepStream configuration file. In addition, you need to compile the TensorRT 7+ Open source software and YOLOv4 bounding box parser for DeepStream.

A DeepStream sample with documentation on how to run inference using the trained YOLOv4 models from TAO Toolkit is provided on GitHub repo..

Prerequisites for YOLOv4 Model

YOLOv4 requires batchTilePlugin, resizeNearestPlugin, and batchedNMSPlugin. These plugins are available in the TensorRT open source repo, but not in TensorRT 7.0. Detailed instructions to build TensorRT OSS can be found in TensorRT Open Source Software (OSS).
YOLOv4 requires YOLOv3 custom bounding box parsers that are not built-in inside the DeepStream SDK. The source code to build YOLOv3 custom bounding box parsers is available in GitHub repo. The following instructions can be used to build bounding box parser:

Step1: Install git-lfs (git >= 1.8.2)

Copy
Copied!

            
            curl -s https://packagecloud.io/install/repositories/github/git-lfs/script.deb.sh | sudo bash
sudo apt-get install git-lfs
git lfs install

Step 2: Download Source Code with SSH or HTTPS

Copy
Copied!

            
            git clone -b release/tlt3.0 https://github.com/NVIDIA-AI-IOT/deepstream_tlt_apps

Step 3: Build

Copy
Copied!

            
            // or Path for DS installation
export CUDA_VER=10.2         // CUDA version, e.g. 10.2
make

This generates libnvds_infercustomparser_tlt.so in the directory post_processor.

Label File

The label file is a text file containing the names of the classes that the YOLOv4 model is trained to detect. The order in which the classes are listed here must match the order in which the model predicts the output. During the training, TAO YOLOv4 will specify all class names in lower case and sort them in alphabetical order. For example, if the dataset_config is:

Copy
Copied!

            
            dataset_config {
  data_sources: {
      label_directory_path: "/workspace/tao-experiments/data/training/label_2"
      image_directory_path: "/workspace/tao-experiments/data/training/image_2"
  }
  target_class_mapping {
    key: "car"
    value: "car"
  }
  target_class_mapping {
    key: "person"
    value: "person"
  }
  target_class_mapping {
    key: "bicycle"
    value: "bicycle"
  }
  validation_data_sources: {
      label_directory_path: "/workspace/tao-experiments/data/val/label"
      image_directory_path: "/workspace/tao-experiments/data/val/image"
  }
}

Then the corresponding yolov4_labels.txt file would be:

Copy
Copied!

            
            bicycle
car
person

DeepStream Configuration File

The detection model is typically used as a primary inference engine. It can also be used as a secondary inference engine. To run this model in the sample deepstream-app, you must modify the existing config_infer_primary.txt file to point to this model.

Integrate the TensorRT engine file with the DeepStream app

Generate TensorRT engine using TAO Deploy.
Once the engine file is generated successfully, modify the following parameters to use this engine with DeepStream.
Copy

Copied!
```
            
            model-engine-file=<PATH to generated TensorRT engine>
        
```

All other parameters are common between the two approaches. To use the custom bounding box parser instead of the default parsers in DeepStream, modify the following parameters in [property] section of primary infer configuration file:

Copy
Copied!

            
            parse-bbox-func-name=NvDsInferParseCustomBatchedNMSTLT
custom-lib-path=<PATH to libnvds_infercustomparser_tlt.so>

Add the label file generated above using:

Copy
Copied!

            
            labelfile-path=<YOLOv4 labels>

For all the options, see the configuration file below. To learn about what all the parameters are used for, refer to the DeepStream Development Guide.

Here’s a sample config file, pgie_yolov4_config.txt:

Copy
Copied!

            
            [property]
gpu-id=0
net-scale-factor=1.0
offsets=103.939;116.779;123.68
model-color-format=1
labelfile-path=<Path to yolov4_labels.txt>
model-engine-file=<PATH to generated TensorRT engine>
infer-dims=3;384;1248
maintain-aspect-ratio=1
uff-input-order=0
uff-input-blob-name=Input
batch-size=1
## 0=FP32, 1=INT8, 2=FP16 mode
network-mode=0
num-detected-classes=3
interval=0
gie-unique-id=1
is-classifier=0
#network-type=0
#no cluster
cluster-mode=3
output-blob-names=BatchedNMS
parse-bbox-func-name=NvDsInferParseCustomBatchedNMSTLT
custom-lib-path=<Path to libnvds_infercustomparser_tlt.so>

[class-attrs-all]
pre-cluster-threshold=0.3
roi-top-offset=0
roi-bottom-offset=0
detected-min-w=0
detected-min-h=0
detected-max-w=0
detected-max-h=0

Integrate the ONNX model with the DeepStream app

The ONNX model can also be integrated into DeepStream directly. Here’s a sample config file, pgie_yolov4_config.txt:

Copy
Copied!

            
            [property]
gpu-id=0
net-scale-factor=1.0
offsets=103.939;116.779;123.68
model-color-format=1
labelfile-path=<Path to yolov4_labels.txt>
onnx-file=<Path to ONNX model>
maintain-aspect-ratio=1
batch-size=1
## 0=FP32, 1=INT8, 2=FP16 mode
network-mode=0
num-detected-classes=3
interval=0
gie-unique-id=1
is-classifier=0
#network-type=0
#no cluster
cluster-mode=3
parse-bbox-func-name=NvDsInferParseCustomBatchedNMSTLT
custom-lib-path=<Path to libnvds_infercustomparser_tlt.so>

[class-attrs-all]
pre-cluster-threshold=0.3
roi-top-offset=0
roi-bottom-offset=0
detected-min-w=0
detected-min-h=0
detected-max-w=0
detected-max-h=0

Jetson Platform	GPU_ARCHS
Nano/Tx1	53
Tx2	62
AGX Xavier/Xavier NX	72