Integrating TLT Models into DeepStream

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. TLT has been designed to integrate with DeepStream SDK, so models trained with TLT 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 TLT 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 tlt-converter. The generated TensorRT engine file can also be ingested by DeepStream.

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. With option 2, the tlt-converter is used to convert the .etlt file to TensorRT; this file is then provided directly to DeepStream.

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

The following TLT models can be integrated into DeepStream 5.1:

  • Image Classification

  • Object Detection

    • Yolo V3

    • Yolo V4

    • DSSD

    • SSD

    • RetinaNet

    • DetectNet_v2

    • FasterRCNN

  • Instance Segmentation

    • Mask-RCNN

  • Semantic Segmentation

    • UNet

  • Character Recognition

  • MultiTask Classification

Of these models, the following do not support direct integration of the .etlt files into DeepStream:

  • YOLOv3

  • YOLOv4

  • UNet

  • Character Recognition

You can deploy most trained models with DeepStream SDK. Follow the instructions below to integrate TLT models with Deepstream.

We recommend running TLT models with DeepStream 5.1.

../_images/tlt_overview.png

The following models have been integrated into DeepStream 5.1 with other models on the roadmap for future releases.

Open Model Deployment

Model

Model output format

Prunable

INT8

Compatible with DS5.0/5.0.1

Compatible with DS5.1

TRT-OSS required

Image Classification

Encrypted UFF

Yes

Yes

Yes

Yes

No

MultiTask Classification

Encrypted UFF

Yes

Yes

No

Yes

No

DetectNet_v2

Encrypted UFF

Yes

Yes

Yes

Yes

No

FasterRCNN

Encrypted UFF

Yes

Yes

Yes

Yes

Yes

SSD

Encrypted UFF

Yes

Yes

Yes

Yes

Yes

YOLOv3

Encrypted ONNX

Yes

Yes

Yes

Yes (with TRT 7.1)

Yes

YOLOv4

Encrypted ONNX

Yes

Yes

Yes

Yes (with TRT 7.1)

Yes

DSSD

Encrypted UFF

Yes

Yes

Yes

Yes

Yes

RetinaNet

Encrypted UFF

Yes

Yes

Yes

Yes

Yes

MaskRCNN

Encrypted UFF

No

Yes

Yes

Yes

Yes

UNET

Encrypted ONNX

No

Yes

No

Yes

No

Character Recognition

Encrypted ONNX

No

Yes

No

Yes

No

Pre-trained Model Deployment

Model Name

Model arch

Model output format

Prunable

INT8

Compatible with DS5.0/5.0.1

Compatible with DS5.1

TRT-OSS required

PeopleNet

DetectNet_v2

Encrypted UFF

Yes

Yes

Yes

Yes

No

TrafficCamNet

DetectNet_v2

Encrypted UFF

Yes

Yes

Yes

Yes

No

DashCamNet

DetectNet_v2

Encrypted UFF

Yes

Yes

Yes

Yes

No

FaceDetect-IR

DetectNet_v2

Encrypted UFF

Yes

Yes

Yes

Yes

No

FaceDetect

DetectNet_v2

Encrypted UFF

Yes

Yes

Yes

Yes

No

VehicleMakeNet

Image Classification

Encrypted UFF

Yes

Yes

Yes

Yes

No

VehicleTypeNet

Image Classification

Encrypted UFF

Yes

Yes

Yes

Yes

No

LPDNet

DetectNet_v2

Encrypted UFF

Yes

Yes

Yes

Yes

No

LPRNet

Character Recognition

Encrypted ONNX

No

Yes

No

Yes

No

PeopleSegNet

MaskRCNN

Encrypted UFF

No

Yes

Yes

Yes

Yes

PeopleSemSegNet

UNET

Encrypted ONNX

No

Yes

No

Yes

Yes

Installation Prerequisites

  1. Install Jetpack 4.5.1 for Jetson devices.

    Note: For Jetson devices, use the following commands to manually increase the Jetson Power mode and maximize performance further by using the Jetson Clocks mode:

    sudo nvpmodel -m 0
    sudo /usr/bin/jetson_clocks
    
  1. Install Deepstream.

Deployment Files

The following files are required to run each TLT model with Deepstream:

  • ds_tlt.c: The application main file

  • nvdsinfer_custombboxparser_tlt: A custom parser function on infernece end nodes

  • Models: TLT models from NGC

  • Model configuration files: The Deepstream Inference configuration file

Sample Application

We have provided several reference applications on GitHub.

Reference app for YOLOv3/YOLOv4, FasterRCNN, SSD/DSSD, RetinaNet, MaskRCNN, UNet - DeepStream TLT reference app

Reference app for License plate detection and Recognition - DeepStream LPR app

Pre-trained models - License Plate Detection (LPDNet) and Recognition (LPRNet)

The following steps outline how to run the License Plate Detection and Recognition application: DeepStream LPR app

Download the Repository

git clone https://github.com/NVIDIA-AI-IOT/deepstream_lpr_app.git

Download the Models

cd deepstream_lpr_app

mkdir -p ./models/tlt_pretrained_models/trafficcamnet
cd ./models/tlt_pretrained_models/trafficcamnet
wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_trafficcamnet/versions/pruned_v1.0/files/trafficnet_int8.txt
wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_trafficcamnet/versions/pruned_v1.0/files/resnet18_trafficcamnet_pruned.etlt
cd -

mkdir -p ./models/LP/LPD
cd ./models/LP/LPD
wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_lpdnet/versions/pruned_v1.0/files/usa_pruned.etlt
wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_lpdnet/versions/pruned_v1.0/files/usa_lpd_cal.bin
wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_lpdnet/versions/pruned_v1.0/files/usa_lpd_label.txt
cd -

mkdir -p ./models/LP/LPR
cd ./models/LP/LPR
wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_lprnet/versions/deployable_v1.0/files/us_lprnet_baseline18_deployable.etlt
touch labels_us.txt
cd -

Convert the Models to TRT Engine

See the TLT Converter section.

./tlt-converter -k nvidia_tlt -p image_input,1x3x48x96,4x3x48x96,16x3x48x96 models/LP/LPR/us_lprnet_baseline18_deployable.etlt -t fp16 -e models/LP/LPR/lpr_us_onnx_b16.engine

Build and Run

make
cd deepstream-lpr-app

For US car plate recognition:

cp dict_us.txt dict.txt

Start to run the application:

./deepstream-lpr-app <1:US car plate model|2: Chinese car plate model> <1: output as h264 file| 2:fakesink 3:display output>
[0:ROI disable|1:ROI enable] [input mp4 file path and name] [input mp4 file path and name] ... [input mp4 file path and name] [output 264 file path and name]

For detailed instructions about running this application, refer to this GitHub repository.

Pre-trained models - PeopleNet, TrafficCamNet, DashCamNet, FaceDetectIR, Vehiclemakenet, Vehicletypenet, PeopleSegNet, PeopleSemSegNet

PeopleNet

Follow these instructions to run the PeopleNet model in DeepStream:

  1. Download the model:

    mkdir -p $HOME/peoplenet && \
    wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_peoplenet/versions/pruned_v2.1/files/resnet34_peoplenet_pruned.etlt \
    -O $HOME/peoplenet/resnet34_peoplenet_pruned.etlt
    
  2. Run the application:

    xhost +
    docker run --gpus all -it --rm -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY=$DISPLAY -v $HOME:/opt/nvidia/deepstream/deepstream-5.1/samples/models/tlt_pretrained_models \
    -w /opt/nvidia/deepstream/deepstream-5.1/samples/configs/tlt_pretrained_models nvcr.io/nvidia/deepstream:5.1-21.02-samples \
    deepstream-app -c deepstream_app_source1_peoplenet.txt
    

TrafficCamNet

Follow these instructions to run the TrafficCamNet model in DeepStream:

  1. Download the model:

    mkdir -p $HOME/trafficcamnet && \
    wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_trafficcamnet/versions/pruned_v1.0/files/resnet18_trafficcamnet_pruned.etlt \
    -O $HOME/trafficcamnet/resnet18_trafficcamnet_pruned.etlt && \
    wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_trafficcamnet/versions/pruned_v1.0/files/trafficnet_int8.txt \
    -O $HOME/trafficcamnet/trafficnet_int8.txt
    
  2. Run the application:

    xhost +
    docker run --gpus all -it --rm -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY=$DISPLAY -v $HOME:/opt/nvidia/deepstream/deepstream-5.1/samples/models/tlt_pretrained_models \
    -w /opt/nvidia/deepstream/deepstream-5.1/samples/configs/tlt_pretrained_models nvcr.io/nvidia/deepstream:5.1-21.02-samples \
    deepstream-app -c deepstream_app_source1_trafficcamnet.txt
    

DashCamNet + Vehiclemakenet + Vehicletypenet

Follow these instructions to run the DashCamNet model as primary detector and Vehiclemakenet and Vehicletypenet as secondary classifier in DeepStream:

  1. Download the model:

    mkdir -p $HOME/dashcamnet && \
    wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_dashcamnet/versions/pruned_v1.0/files/resnet18_dashcamnet_pruned.etlt \
    -O $HOME/dashcamnet/resnet18_dashcamnet_pruned.etlt && \
    wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_dashcamnet/versions/pruned_v1.0/files/dashcamnet_int8.txt \
    -O $HOME/dashcamnet/dashcamnet_int8.txt
    mkdir -p $HOME/vehiclemakenet && \
    wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_vehiclemakenet/versions/pruned_v1.0/files/resnet18_vehiclemakenet_pruned.etlt \
    -O $HOME/vehiclemakenet/resnet18_vehiclemakenet_pruned.etlt && \
    wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_vehiclemakenet/versions/pruned_v1.0/files/vehiclemakenet_int8.txt \
    -O $HOME/vehiclemakenet/vehiclemakenet_int8.txt
    mkdir -p $HOME/vehicletypenet && \
    wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_vehicletypenet/versions/pruned_v1.0/files/resnet18_vehicletypenet_pruned.etlt \
    -O $HOME/vehicletypenet/resnet18_vehicletypenet_pruned.etlt && \
    wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_vehicletypenet/versions/pruned_v1.0/files/vehicletypenet_int8.txt \
    -O $HOME/vehicletypenet/vehicletypenet_int8.txt
    
  2. Run the application:

    xhost +
    docker run --gpus all -it --rm -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY=$DISPLAY -v $HOME:/opt/nvidia/deepstream/deepstream-5.1/samples/models/tlt_pretrained_models \
    -w /opt/nvidia/deepstream/deepstream-5.1/samples/configs/tlt_pretrained_models nvcr.io/nvidia/deepstream:5.1-21.02-samples \
    deepstream-app -c deepstream_app_source1_dashcamnet_vehiclemakenet_vehicletypenet.txt
    

FaceDetectIR

Follow these instructions to run the FaceDetectIR model in DeepStream:

  1. Download the model:

    mkdir -p $HOME/facedetectir && \
    wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_facedetectir/versions/pruned_v1.0/files/resnet18_facedetectir_pruned.etlt \
    -O $HOME/facedetectir/resnet18_facedetectir_pruned.etlt && \
    wget https://api.ngc.nvidia.com/v2/models/nvidia/tlt_facedetectir/versions/pruned_v1.0/files/facedetectir_int8.txt \
    -O $HOME/facedetectir/facedetectir_int8.txt
    
  2. Run the application:

    xhost +
    docker run --gpus all -it --rm -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY=$DISPLAY -v $HOME:/opt/nvidia/deepstream/deepstream-5.1/samples/models/tlt_pretrained_models \
    -w /opt/nvidia/deepstream/deepstream-5.1/samples/configs/tlt_pretrained_models nvcr.io/nvidia/deepstream:5.1-21.02-samples \
    deepstream-app -c deepstream_app_source1_facedetectir.txt
    

PeopleSegNet

Follow these instructions to run the PeopleSegNet model in DeepStream:

  1. Download the Repository:

    git clone https://github.com/NVIDIA-AI-IOT/deepstream_tlt_apps.git
    
  2. Download the model:

    ngc registry model download-version "nvidia/tlt_peoplesegnet:deployable_v2.0"
    

    or

    wget --content-disposition https://api.ngc.nvidia.com/v2/models/nvidia/tlt_peoplesegnet/versions/deployable_v2.0/zip \
    -O tlt_peoplesegnet_deployable_v2.0.zip
    
  3. Build TRT OSS Plugin:

    TRT-OSS instructions are provided in https://github.com/NVIDIA-AI-IOT/deepstream_tlt_apps/tree/master#1-build-trt-oss-plugin

  4. Build the application:

    export CUDA_VER=xy.z              // xy.z is CUDA version, e.g. 10.2
    make
    
  5. Run the application:

    SHOW_MASK=1 ./apps/ds-tlt -c configs/peopleSegNet_tlt/pgie_peopleSegNetv2_tlt_config.txt -i \
    /opt/nvidia/deepstream/deepstream-5.1/samples/streams/sample_720p.h264 -d
    

PeopleSemSegNet

Follow these instructions to run the PeopleSemSegNet model in DeepStream:

  1. Download tlt-converter and the model:

    mkdir $HOME/deepstream
    cd $HOME/deepstream
    wget https://developer.nvidia.com/cuda111-cudnn80-trt72
    unzip cuda111-cudnn80-trt72
    cp cuda11.1_cudnn8.0_trt7.2/tlt-converter ./
    chmod 0777 tlt-converter
    ngc registry model download-version "nvidia/tlt_peoplesemsegnet:deployable_v1.0"
    
  2. Run the application:

    xhost +
    docker run --gpus all -it --rm -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY=$DISPLAY  -v $HOME:$HOME -w $HOME/deepstream \
    nvcr.io/nvidia/deepstream:5.1-21.02-devel ./tlt-converter -k tlt_encode -p input_1,1x3x544x960,1x3x544x960,1x3x544x960 -t fp16 -e \
    tlt_peoplesemsegnet_vdeployable_v1.0/unet_resnet18.etlt_b1_gpu0_fp16.engine tlt_peoplesemsegnet_vdeployable_v1.0/peoplesemsegnet.etlt ; \
    git clone https://github.com/NVIDIA-AI-IOT/deepstream_tlt_apps.git ; cd deepstream_tlt_apps ; export CUDA_VER=11.1 ; export SHOW_MASK=1 ; make ; \
    sed -i "s/..\/..\/models\/unet\/unet_resnet18.etlt_b1_gpu0_fp16.engine/..\/..\/..\/tlt_peoplesemsegnet_vdeployable_v1.0\/unet_resnet18.etlt_b1_gpu0_fp16.engine/g" \
    configs/unet_tlt/pgie_unet_tlt_config.txt ; sed -i "s/infer-dims=3;608;960/infer-dims=3;544;960/g"  configs/unet_tlt/pgie_unet_tlt_config.txt ; \
    sed -i "s/unet_labels.txt/..\/..\/..\/tlt_peoplesemsegnet_vdeployable_v1.0\/labels.txt/g"  configs/unet_tlt/pgie_unet_tlt_config.txt ; \
    sed -i "s/num-detected-classes=3/num-detected-classes=2/g"  configs/unet_tlt/pgie_unet_tlt_config.txt ; ./apps/ds-tlt -c configs/unet_tlt/pgie_unet_tlt_config.txt \
    -i /opt/nvidia/deepstream/deepstream-5.1/samples/streams/sample_720p.h264 -d
    

General purpose CV model architecture - Classification, Object detection and Segmentation

A sample DeepStream app to run a classification, object detection, and semantic and instance segmentation network is provided in here.

TRT-OSS instructions are provided in the repo above. For more information about each individual model architecture, see the Deploying to DeepStream section under each model: