> This page is for version 9.2 (default). > For other versions, use one of these documentation indexes: > - 9.2 (default): https://docs.nvidia.com/deepstream/9.2/llms.txt > - Archives: https://docs.nvidia.com/deepstream/archives/llms.txt > For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/deepstream/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/deepstream/_mcp/server. # 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.txt | Demonstrates 30 stream decodes with primary inferencing | For all platforms. | | source30_1080p_dec_infer-resnet_tiled_display.yml | YAML based config file to demonstrate 30 stream decode with primary inference for dGPU and Jetson AGX Orin platforms only. | For all platforms. | | source4_1080p_dec_infer-resnet_tiled_display.txt | Demonstrates four stream decodes with primary inferencing, object tracking, and two different secondary classifiers | For all platforms. | | source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display.yml | YAML based config file to demonstrate four stream decode with primary inferencing, object tracking, and two different secondary classifiers | For all platforms. | | source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_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 x86 platforms only | | config_infer_primary.txt | Configures a nvinfer element as primary detector | For all platforms. | | config_infer_primary.yml | YAML based config file to configure a nvinfer element as primary detector | For all platforms. | | config_infer_secondary_vehiclemake.txt, config_infer_secondary_vehicletypes.txt | Configure a nvinfer element as secondary classifier | For all platforms. | | config_infer_secondary_vehiclemake.yml, config_infer_secondary_vehicletypes.yml | YAML based config file to configure a nvinfer element as secondary classifier | For all platforms. | | config_tracker_IOU.yml | Config file for IOU tracker | For all platforms. | | config_tracker_NvSORT.yml | Config file for NvSORT tracker | For all platforms. | | config_tracker_NvDeepSORT.yml | Config file for NvDeepSORT tracker | For all platforms. | | config_tracker_NvDCF_accuracy.yml | Config file for NvDCF tracker for higher accuracy | For all platforms. | | config_tracker_NvDCF_max_perf.yml | Config file for NvDCF tracker for max perf mode | For all platforms. | | config_tracker_NvDCF_perf.yml | Config file for NvDCF tracker for perf mode | For all platforms. | | config_preprocess.txt | Config file for using preprocess in PGIE mode | For all platforms. | | config_preprocess_sgie.txt | Config file for using preprocess in SGIE mode | For all platforms. | | source4_1080p_dec_preprocess_infer-resnet_preprocess_sgie_tiled_display.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 all platforms. | | source30_1080p_dec_preprocess_infer-resnet_tiled_display.txt | Demonstrates 30 stream decodes with preprocess plugin in PGIE mode followed by primary inferencing | For all platforms. | | sources_30.csv | CSV file for 30 sources required in source30_1080p_dec_infer-resnet_tiled_display.yml | For all platforms. | | sources_4.csv | CSV file for 30 sources required in source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display.yml | For all platforms. | | source1_usb_dec_infer_resnet.txt | Demonstrates one USB camera as input | For all platforms. | | source1_csi_dec_infer_resnet.txt | Demonstrates one CSI camera as input | For Jetson only | | source2_csi_usb_dec_infer_resnet.txt | Demonstrates one CSI camera and one USB camera as inputs | For Jetson only | | source6_csi_dec_infer_resnet.txt | Demonstrates six CSI cameras as inputs | For Jetson only | | source2_1080p_dec_infer-resnet_demux.txt | Demonstrates demux mode for two sources | For all platforms. | | config_mux_source4.txt, config_mux_source30.txt | Sample nvstreammux (new) config files. For more details see [Section Mux Config Properties](/DS_plugin_gst_nvstreammux2_config_file_properties) | For all platforms. | **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.txt | 30 Decode + Infer | | source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display.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 | **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 | | --------------------------------------------------- | --------------------------------- | | 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 | * 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 | ### 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. * samples/ prepare_ds_triton_model_repo.sh: Prepare the Model repository for Triton Inference Server 1. Creates engine files for ONNX based models provided as part of SDK. * 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. 2. Create engine files for downloaded models. * uninstall.sh: Used to clean up previous DS installation.