diff --git a/docs/user-guide/architecture/pipelines.md b/docs/user-guide/architecture/pipelines.md index d6ade54..babbd18 100644 --- a/docs/user-guide/architecture/pipelines.md +++ b/docs/user-guide/architecture/pipelines.md @@ -24,7 +24,7 @@ Details about the latest version can be found in the [OpenVINO Release Notes](ht ### DL Streamer Pipeline -Rather than working directly with the OpenVINO APIs our solutions offers more practical ways to interface with OpenVINO. One method is using [Intel DL Streamer](https://github.com/dlstreamer/dlstreamer). This solution provides a no code way based on [GStreamer](https://gstreamer.freedesktop.org/) and [OpenVINO](https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/get-started.html) to deploy, process, and output a pipeline. +Rather than working directly with the OpenVINO APIs our solutions offers more practical ways to interface with OpenVINO. One method is using [Intel DL Streamer](https://github.com/open-edge-platform/dlstreamer). This solution provides a no code way based on [GStreamer](https://gstreamer.freedesktop.org/) and [OpenVINO](https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/get-started.html) to deploy, process, and output a pipeline. The diagrams show how we take advantage of Docker, Docker Compose, and environment variable files to pre-package DLStreamer based pipelines for our use cases. Leveraging Environment Variables allows users to modify properties on the fly when different configurations are required. diff --git a/docs/user-guide/architecture/v2.0.0/multiple-ovms-json-config.md b/docs/user-guide/architecture/v2.0.0/multiple-ovms-json-config.md index b0ac290..549c372 100644 --- a/docs/user-guide/architecture/v2.0.0/multiple-ovms-json-config.md +++ b/docs/user-guide/architecture/v2.0.0/multiple-ovms-json-config.md @@ -116,6 +116,6 @@ For clean-up, we can do deletion of the config json files when `make clean-all` -- +- - - see issue Classification profile crashed when run the 2nd instance switch from CPU to GPU.0 automated-self-checkout#322 diff --git a/docs/user-guide/architecture/v2.0.0/performance_benchmarking.md b/docs/user-guide/architecture/v2.0.0/performance_benchmarking.md index a3c58bc..725193b 100644 --- a/docs/user-guide/architecture/v2.0.0/performance_benchmarking.md +++ b/docs/user-guide/architecture/v2.0.0/performance_benchmarking.md @@ -47,19 +47,19 @@ Intel Performance Counter Monitor: System power usage For performance inputs we support RTSP video streams, USB camera, Intel® RealSense™ Camera, and video files. For longer benchmarking runs its' recommended to use a video loop with an RTSP stream for inference result consistency. As an option an RTSP [Camera Simulator](https://intel-retail.github.io/automated-self-checkout/run_camera_simulator.html) is provided with the performance script. -[Input Source Types](https://intel-retail.github.io/automated-self-checkout/pipelinebenchmarking.html#input-source-type) +[Input Source Types](https://intel-retail.github.io/automated-self-checkout/OVMS/pipelinebenchmarking.html#input-source-type) #### Specified Number of Pipelines If you are looking to test a specific number of pipelines on different hardware SKUs the `--pipelines` parameter can be used. This parameter will start the specified number of pipelines -[Specified Number of Pipelines](https://intel-retail.github.io/automated-self-checkout/pipelinebenchmarking.html#benchmark-specified-number-of-pipelines) +[Specified Number of Pipelines](https://intel-retail.github.io/automated-self-checkout/OVMS/pipelinebenchmarking.html#benchmark-specified-number-of-pipelines) [![Specified Number of Pipelines](./images/num-of-pipelines.jpg)](./images/num-of-pipelines.jpg) #### Consolidated Results -To make reading results easier, a consolidation script has been provided. This script will work with a single or multiple runs of the specified number of pipelines. Details about this process are found in [Benchmark Specified Number of Pipelines](https://intel-retail.github.io/automated-self-checkout/pipelinebenchmarking.html#benchmark-specified-number-of-pipelines) +To make reading results easier, a consolidation script has been provided. This script will work with a single or multiple runs of the specified number of pipelines. Details about this process are found in [Benchmark Specified Number of Pipelines](https://intel-retail.github.io/automated-self-checkout/OVMS/pipelinebenchmarking.html#benchmark-specified-number-of-pipelines) ```bash make consolidate ROOT_DIRECTORY= @@ -69,7 +69,7 @@ make consolidate ROOT_DIRECTORY= The stream density parameter can be used to find the maximum number of pipelines at a target frames per second (FPS) on a specific hardware SKU. By setting the `--stream_density` parameter to the desired FPS the script will continue to create pipelines until the average pipelines FPS falls below the desired FPS. The script will provide a detailed log to show each pipeline FPS during the test run. This option provides a method for testing the top performance when introducing a new pipeline or hardware SKU. -[Stream Density](https://intel-retail.github.io/automated-self-checkout/pipelinebenchmarking.html#benchmark-stream-density) +[Stream Density](https://intel-retail.github.io/automated-self-checkout/OVMS/pipelinebenchmarking.html#benchmark-stream-density) [![Stream Density](./images/stream-density.jpg)](./images/stream-density.jpg) @@ -87,4 +87,4 @@ Having a generic and scalable set of performance Docker containers will allow cu -[Pipeline Benchmarking](https://intel-retail.github.io/automated-self-checkout/pipelinebenchmarking.html) +[Pipeline Benchmarking](https://intel-retail.github.io/automated-self-checkout/OVMS/pipelinebenchmarking.html) diff --git a/docs/user-guide/architecture/v2.0.0/target-device.md b/docs/user-guide/architecture/v2.0.0/target-device.md index 94830bf..24e24e3 100644 --- a/docs/user-guide/architecture/v2.0.0/target-device.md +++ b/docs/user-guide/architecture/v2.0.0/target-device.md @@ -44,14 +44,14 @@ Update the platform parameter to match the target_device standard used by OpenVI | Device | Parameter | Description | Links | | -------------------------------- | ---------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------- | -| CPU | CPU | Use CPU only | [OVMS Parameters](https://docs.openvino.ai/2023.1/ovms_docs_parameters.html) | -| GPU | GPU | Use default GPU | [OVMS Parameters](https://docs.openvino.ai/2023.1/ovms_docs_parameters.html) | +| CPU | CPU | Use CPU only | [OVMS Parameters](https://docs.openvino.ai/2025/model-server/ovms_docs_parameters.html) | +| GPU | GPU | Use default GPU | [OVMS Parameters](https://docs.openvino.ai/2025/model-server/ovms_docs_parameters.html) | | Specified GPU | GPU.x | Use a specific GPU. ex. GPU.0 = integrated GPU, GPU.1 = discrete Arc GPU | [OVMS Parameters](https://docs.openvino.ai/2023.1/ovms_docs_parameters.html) | | Mixed Contifuration | MULTI:x,y | Use a combination of devices for inferencing ex. MULTI:CPU,GPU.1 will use the CPU and discrete Arc GPU for inferencing | [OVMS Parameters](https://docs.openvino.ai/2023.1/ovms_docs_parameters.html) | | Automatic Device Selection | AUTO | Allow OpenVINO to automatically select the optimal device for inferencing | Possibly depricated? | | Automatic Device Selection | AUTO | Allow OpenVINO to automatically select the optimal device for inferencing | Possibly depricated? | -| Heterogeneous Execution | HETERO | Allows OpenVINO to execute inference on multiple devices | [Heterogeneous Execution](https://docs.openvino.ai/2023.1/openvino_docs_OV_UG_Hetero_execution.html) | -| Heterogeneous Execution Priority | HETERO:x,y | Allows OpenVINO to execute inference on multiple devices and set the priority of device. ex. HETERO:CPU,GPU.1 will prioritize CPU and discrete Arc GPU for inferencing | [Heterogeneous Execution](https://docs.openvino.ai/2023.1/openvino_docs_OV_UG_Hetero_execution.html) | +| Heterogeneous Execution | HETERO | Allows OpenVINO to execute inference on multiple devices | [Heterogeneous Execution](https://docs.openvino.ai/2025/openvino-workflow/running-inference/inference-devices-and-modes/hetero-execution.html) | +| Heterogeneous Execution Priority | HETERO:x,y | Allows OpenVINO to execute inference on multiple devices and set the priority of device. ex. HETERO:CPU,GPU.1 will prioritize CPU and discrete Arc GPU for inferencing | [Heterogeneous Execution](https://docs.openvino.ai/2025/openvino-workflow/running-inference/inference-devices-and-modes/hetero-execution.html) | ## Applicable Repos diff --git a/docs/user-guide/loss-prevention/get-started.md b/docs/user-guide/loss-prevention/get-started.md index dfd7b84..2031c9b 100644 --- a/docs/user-guide/loss-prevention/get-started.md +++ b/docs/user-guide/loss-prevention/get-started.md @@ -9,7 +9,7 @@ - Intel hardware (CPU, iGPU, dGPU, NPU) - Intel drivers: - [Intel GPU drivers](https://dgpu-docs.intel.com/driver/client/overview.html) - - [NPU](https://dlstreamer.github.io/dev_guide/advanced_install/advanced_install_guide_prerequisites.html#prerequisite-2-install-intel-npu-drivers) + - [NPU](https://docs.openedgeplatform.intel.com/dev/edge-ai-libraries/dlstreamer/dev_guide/advanced_install/advanced_install_guide_prerequisites.html#prerequisite-2-install-intel-npu-drivers) - Sufficient disk space for models, videos, and results > **Note:** First-time setup downloads AI models, sample videos, and Docker images - this may take 5-15 minutes depending on your internet connection. diff --git a/docs/user-guide/order-accuracy/dine-in/get-started/system-requirements.md b/docs/user-guide/order-accuracy/dine-in/get-started/system-requirements.md index f8af884..3f193eb 100644 --- a/docs/user-guide/order-accuracy/dine-in/get-started/system-requirements.md +++ b/docs/user-guide/order-accuracy/dine-in/get-started/system-requirements.md @@ -41,7 +41,7 @@ Ubuntu 22.04 LTS is the validated platform (matches the `python:3.13-slim` base ### GPU Drivers -Intel GPU drivers must be installed from [packages.intel.com](https://packages.intel.com). Verify the GPU is accessible to Docker: +Intel GPU drivers must be installed from . Verify the GPU is accessible to Docker: ```bash ls /dev/dri/ diff --git a/docs/user-guide/troubleshooting.md b/docs/user-guide/troubleshooting.md index 33711ad..d751c16 100644 --- a/docs/user-guide/troubleshooting.md +++ b/docs/user-guide/troubleshooting.md @@ -32,7 +32,7 @@ eval $gstLaunchCmd ## Q: How can I use an Intel RealSense Camera as the input? -A: To use a RealSense camera as an input for any of the retail use cases, you need to obtain the serial number first. Follow the instructions in the [RealSense repository](https://github.com/IntelRealSense/librealsense/tree/master/tools/enumerate-devices) to run `rs-enumerate-devices` and obtain the following information: +A: To use a RealSense camera as an input for any of the retail use cases, you need to obtain the serial number first. Follow the instructions in the [RealSense repository](https://github.com/realsenseai/librealsense/tree/master/tools/enumerate-devices) to run `rs-enumerate-devices` and obtain the following information: ``` Device Name Serial Number Firmware Version