Sample Configurations and Streams#

Contents of the package#

This section provides information about included sample configs and streams.

  • samples: Directory containing sample configuration files, streams, and models to run the sample applications.

samples/configs/deepstream-app: Configuration files for the reference application

The following table provides information about configuration files for the reference application in samples/configs/deepstream-app directory.

Sample configs for the reference application in samples/configs/deepstream-app#

Configuration File

Description

Platform

source30_1080p_dec_infer-resnet_tiled_display_int8.txt

Demonstrates 30 stream decodes with primary inferencing

For dGPU and Jetson AGX Orin platforms only.

source30_1080p_dec_infer-resnet_tiled_display_int8.yml

YAML based config file to demonstrate 30 stream decode with primary inferencingFor dGPU and Jetson AGX Orin platforms only.

For dGPU and Jetson AGX Orin platforms only.

source4_1080p_dec_infer-resnet_tiled_display_int8.txt

Demonstrates four stream decodes with primary inferencing, object tracking, and two different secondary classifiers

For dGPU and Jetson AGX Orin platforms only.

source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.yml

YAML based config file to demonstrate four stream decode with primary inferencing, object tracking, and two different secondary classifiers

For dGPU and Jetson AGX Orin platforms only.

source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8_gpu1.txt

Demonstrates four stream decodes with primary inferencing, object tracking, and two different secondary classifiers on GPU 1 (for systems that have multiple GPU cards)

For dGPU platforms only

config_infer_primary.txt

Configures a nvinfer element as primary detector

For dGPU and Jetson

config_infer_primary.yml

YAML based config file to configure a nvinfer element as primary detector

For dGPU and Jetson

config_infer_secondary_vehiclemake.txt, config_infer_secondary_vehicletypes.txt

Configure a nvinfer element as secondary classifier

For dGPU and Jetson

config_infer_secondary_vehiclemake.yml, config_infer_secondary_vehicletypes.yml

YAML based config file to configure a nvinfer element as secondary classifier

For dGPU and Jetson

config_tracker_IOU.yml

Config file for IOU tracker

For dGPU and Jetson

config_tracker_NvSORT.yml

Config file for NvSORT tracker

For dGPU and Jetson

config_tracker_NvDeepSORT.yml

Config file for NvDeepSORT tracker

For dGPU and Jetson

config_tracker_NvDCF_accuracy.yml

Config file for NvDCF tracker for higher accuracy

For dGPU and Jetson

config_tracker_NvDCF_max_perf.yml

Config file for NvDCF tracker for max perf mode

For dGPU and Jetson

config_tracker_NvDCF_perf.yml

Config file for NvDCF tracker for perf mode

For dGPU and Jetson

config_preprocess.txt

Config file for using preprocess in PGIE mode

For dGPU and Jetson

config_preprocess_sgie.txt

Config file for using preprocess in SGIE mode

For dGPU and Jetson

source4_1080p_dec_preprocess_infer-resnet_preprocess_sgie_tiled_display_int8.txt

Demonstrates four stream decodes with preprocess plugin in PGIE mode followed by primary inferencing, preprocess plugin in SGIE mode, and two different secondary classifiers

For dGPU and Jetson AGX Orin platforms only.

source30_1080p_dec_preprocess_infer-resnet_tiled_display_int8.txt

Demonstrates 30 stream decodes with preprocess plugin in PGIE mode followed by primary inferencing

For dGPU and Jetson AGX Orin platforms only.

sources_30.csv

CSV file for 30 sources required in source30_1080p_dec_infer-resnet_tiled_display_int8.yml

For dGPU and Jetson AGX Orin platforms only.

sources_4.csv

CSV file for 30 sources required in source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.yml

For dGPU and Jetson AGX Orin platforms only.

source1_usb_dec_infer_resnet_int8.txt

Demonstrates one USB camera as input

For dGPU and Jetson

source1_csi_dec_infer_resnet_int8.txt

Demonstrates one CSI camera as input

For Jetson only

source2_csi_usb_dec_infer_resnet_int8.txt

Demonstrates one CSI camera and one USB camera as inputs

For Jetson only

source6_csi_dec_infer_resnet_int8.txt

Demonstrates six CSI cameras as inputs

For Jetson only

source2_1080p_dec_infer-resnet_demux_int8.txt

Demonstrates demux mode for two sources

For dGPU and Jetson

config_mux_source4.txt, config_mux_source30.txt

Sample nvstreammux (new) config files. For more details see Section Mux Config Properties

For dGPU and Jetson

samples/configs/deepstream-app-triton: Configuration files for the reference application for inferencing using Triton Inference Server.

The following table provides information about configuration files for the reference application in samples/configs/deepstream-app-triton directory.

Sample configs for the reference application for inferencing using Triton Inference Server in samples/configs/deepstream-app-triton#

Configuration File

Description

source30_1080p_dec_infer-resnet_tiled_display_int8.txt

30 Decode + Infer

source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt

4 Decode + Infer + SGIE + Tracker

source1_primary_classifier.txt

Single source + full frame classification

source1_1080p_dec_infer_peoplesemsegnet_shuffle.txt

Single source + semantic segmentation

source1_primary_detector_peoplenet_transformer.txt

Single source + full frame classification

source1_primary_detector.txt

Single source + object detection using ssd

Note

Other classification models can be used by changing the ds-triton nvinferserver config file in the [*-gie] group of application config file.

  • Configuration files for ds-triton nvinferserver element in configs/deepstream-app-triton/. The following table provides information about configuration files for the reference application in samples/configs/deepstream-app-triton directory.

    Sample configs for ds-triton nvinferserver element in samples/configs/deepstream-app-triton#

    Configuration File

    Description

    config_infer_plan_engine_primary.txt

    Primary Object Detector

    config_infer_secondary_plan_engine_vehiclemake.txt

    Secondary Vehicle Make Classifier

    config_infer_secondary_plan_engine_vehicletypes.txt

    Secondary Vehicle Type Classifier

    config_infer_primary_classifier_densenet_onnx.txt

    DenseNet-121 v1.2 classifier

    config_infer_primary_classifier_inception_graphdef_postprocessInTriton.txt

    TensorFlow Inception v3 classifier - Post processing in Triton

    config_infer_primary_classifier_inception_graphdef_postprocessInDS.txt

    TensorFlow Inception v3 classifier - Post processing in DeepStream

    config_infer_primary_detector_ssd_inception_v2_coco_2018_01_28.txt

    TensorFlow SSD Inception V2 Object Detector

    config_infer_primary_classifier_mobilenet_v1_graphdef.txt

    TensorFlow Mobilenet V1 classifier

    config_infer_primary_detector_ssd_mobilenet_v1_coco_2018_01_28.txt

    TensorFlow Mobilenet V1 Object Detector

samples/configs/deepstream-app-triton-grpc: Configuration files for the reference application for inferencing using Triton Inference Server gRPC

The following table provides information about configuration files for the reference application using Triton Inference Server gRPC in samples/configs/deepstream-app-triton-grpc directory.

Sample configs for inferencing using Triton Inference Server gRPC in samples/configs/deepstream-app-triton-grpc#

Configuration File

Description

source30_1080p_dec_infer-resnet_tiled_display_int8.txt

30 Decode + Infer

source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt

4 Decode + Infer + SGIE + Tracker

  • Configuration files for ds-triton nvinferserver element in configs/deepstream-app-triton-grpc/. The following table provides information about configuration files for the reference application using Triton Inference Server nvinferserver in samples/configs/deepstream-app-triton-grpc directory.

    Sample configs for inferencing using Triton Inference Server gRPC in samples/configs/deepstream-app-triton-grpc#

    Configuration File

    Description

    config_infer_plan_engine_primary.txt

    Primary Object Detector

    config_infer_secondary_plan_engine_vehiclemake.txt

    Secondary Vehicle Make Classifier

    config_infer_secondary_plan_engine_vehicletypes.txt

    Secondary Vehicle Type Classifier

  • NVIDIA TAO Toolkit pretrained Models:

    • samples/configs/tao_pretrained_models: Contains README.md to obtain configs and models for TAO toolkit.

  • samples: Directory containing sample configuration files, models, and streams to run the sample applications.

  • samples/streams: The following streams are provided with the DeepStream SDK:

    Streams

    Type of Stream

    sample_1080p_h264.mp4

    H264 containerized stream

    sample_1080p_h265.mp4

    H265 containerized stream

    sample_720p.h264

    H264 elementary stream

    sample_720p.jpg

    JPEG image

    sample_720p_mjpeg.mp4

    MJPEG containerized stream

    sample_720p.mp4

    Containerized stream

    sample_cam5.mp4

    H264 containerized stream (360D camera stream)

    sample_cam6.mp4

    H264 containerized stream (360D camera stream)

    sample_industrial.jpg

    JPEG image

    yoga.jpg

    Image for perspective projection in Dewarper

    yoga.mp4

    Containerized stream

    sample_qHD.mp4

    Used for MaskRCNN

    sample_qHD.h264

    H264 elementary stream

    sample_push.mov

    H264 containerized stream

    sample_ride_bike.mov

    H264 containerized stream

    sample_run.mov

    H264 containerized stream

    sample_walk.mov

    H264 containerized stream

    fisheye_dist.mp4

    Containerized stream

    sonyc_mixed_audio.wav

    Audio bitstream

    sample_office.mp4

    Containerized stream

    pointcloud

    Contains input files for lidar application

  • samples/models: The following sample models are provided with the SDK:

DeepStream Reference application

Model

Model Type

No. of Classes

Resolution

Primary Detector

Resnet18

4

960 × 544

Secondary Vehicle Make Classifier

Resnet18

20

224 × 224

Secondary Vehicle Type Classifier

Resnet18

6

224 × 224

Segmentation example

Model

Model Type

No. of Classes

Resolution

Industrial

Resnet18 + UNet

1

512 x 512

Semantic

Resnet18 + UNet

4

512 x 512

Instance

Resnet50 + Maskrcnn

2

1344 x 832

Scripts included along with package#

Note

  • The script prepare_classification_test_video.sh mentioned below requires ffmpeg to be installed. Some of the low level codec libraries need to be re-installed along with ffmpeg.

  • Use the following command to install/re-install ffmpeg: apt-get install --reinstall libflac8 libmp3lame0 libxvidcore4 ffmpeg

The following scripts are included along with the sample applications package:

  • samples/ prepare_classification_test_video.sh: Downloads Imagenet test images and creates a video out of it to test with Classification models like TensorFlow Inception, ONNX DenseNet etc.

  • samples/ prepare_ds_triton_model_repo.sh: Prepare the Model repository for Triton Inference Server

    1. Creates engine files for Caffe and UFF based models provided as part of SDK.

    2. Downloads Model files for ONNX DenseNet , SSD Inception V2 Coco, Inception v3.

    For additional information on the above models, refer to:

  • samples/ prepare_ds_triton_tao_model_repo.sh: Prepare the Model repository for Triton Tao Inference Server

    1. Downloads Model files for Peoplenet Transformer, Peoplesemsegnet Shuffle, Facenet.

    2. Create engine files for downloaded models.

  • uninstall.sh: Used to clean up previous DS installation.