From 23d3e7cf55acef613119eba8e9adb1887066ec22 Mon Sep 17 00:00:00 2001 From: tejaswinijayashanker943 Date: Fri, 10 Oct 2025 16:10:35 +0800 Subject: [PATCH 1/9] Added GPU device type to .env files for all apps and updated readme --- .../.env_pallet_defect_detection | 1 + .../.env_pcb_anomaly_detection | 1 + .../.env_weld_porosity_classification | 1 + .../.env_worker_safety_gear_detection | 1 + .../industrial-edge-insights-vision/README.md | 5 +++- .../docs/user-guide/get-started.md | 24 +++++++++++++++++++ .../pallet-defect-detection/payload_gpu.json | 23 ++++++++++++++++++ 7 files changed, 55 insertions(+), 1 deletion(-) create mode 100644 manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/payload_gpu.json diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/.env_pallet_defect_detection b/manufacturing-ai-suite/industrial-edge-insights-vision/.env_pallet_defect_detection index 1d18a1926..ea6caa582 100644 --- a/manufacturing-ai-suite/industrial-edge-insights-vision/.env_pallet_defect_detection +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/.env_pallet_defect_detection @@ -59,3 +59,4 @@ OPCUA_SERVER_PASSWORD= # Sample App, name should match the app dir name SAMPLE_APP=pallet-defect-detection +DEVICE=CPU # Possible values: CPU, GPU, NPU diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/.env_pcb_anomaly_detection b/manufacturing-ai-suite/industrial-edge-insights-vision/.env_pcb_anomaly_detection index 121c7e5ae..43981d354 100644 --- a/manufacturing-ai-suite/industrial-edge-insights-vision/.env_pcb_anomaly_detection +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/.env_pcb_anomaly_detection @@ -59,3 +59,4 @@ OPCUA_SERVER_PASSWORD= # Sample App, name should match the app dir name SAMPLE_APP=pcb-anomaly-detection +DEVICE=CPU # Possible values: CPU, GPU, NPU diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/.env_weld_porosity_classification b/manufacturing-ai-suite/industrial-edge-insights-vision/.env_weld_porosity_classification index b9449be0c..abb5970ff 100644 --- a/manufacturing-ai-suite/industrial-edge-insights-vision/.env_weld_porosity_classification +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/.env_weld_porosity_classification @@ -59,3 +59,4 @@ OPCUA_SERVER_PASSWORD= # Sample App, name should match the app dir name SAMPLE_APP=weld-porosity +DEVICE=CPU # Possible values: CPU, GPU, NPU diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/.env_worker_safety_gear_detection b/manufacturing-ai-suite/industrial-edge-insights-vision/.env_worker_safety_gear_detection index 5132990cd..bc8d79ed2 100644 --- a/manufacturing-ai-suite/industrial-edge-insights-vision/.env_worker_safety_gear_detection +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/.env_worker_safety_gear_detection @@ -59,3 +59,4 @@ OPCUA_SERVER_PASSWORD= # Sample App, name should match the app dir name SAMPLE_APP=worker-safety-gear-detection +DEVICE=CPU # Possible values: CPU, GPU, NPU diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/README.md b/manufacturing-ai-suite/industrial-edge-insights-vision/README.md index 1564c8f16..62f3f97fa 100644 --- a/manufacturing-ai-suite/industrial-edge-insights-vision/README.md +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/README.md @@ -36,6 +36,7 @@ Following directory structure consisting of generic deployment code as well as p pipeline-server-config.json setup.sh payload.json + payload_gpu.json helm/ apps/ application_name/ @@ -67,6 +68,8 @@ Following directory structure consisting of generic deployment code as well as p pre-requisite installer to setup envs, download artificats such as models/videos to `resources/` directory. It also sets executable permissions for scripts. - *payload.json*: A JSON array file containing one or more request(s) to be sent to DLStreamer Pipeline Server to launch GStreamer pipeline(s). The payload data is associated with the *configs/pipeline-server-config.json* provided for that application. Each JSON inside the array has two keys- `pipeline` and `payload` that refers to the pipeline it belongs to and the payload used to launch an instance of the pipeline. + - *payload_gpu.json*: + A JSON array file containing one or more request(s) to be sent to DLStreamer Pipeline Server to launch GStreamer pipeline(s). The payload data is associated with the *configs/pipeline-server-config.json* provided for that application. Each JSON inside the array has two keys- `pipeline` and `payload` that refers to the pipeline it belongs to and the payload used to launch an instance of the pipeline. The device used here is GPU. - **helm**: contains helm charts and application specific pre-requisite installers, configurations and runtime data. The configs and data within it are similar to **apps** but are kept here for easy packaging. @@ -98,7 +101,7 @@ Please ensure that you have the correct version of the DL Streamer Pipeline Serv General instructions for docker based deployment is as follows. -1. Prepare the `.env` file for compose to source during deployment. This chosen env file defines the application you would be running. +1. Prepare the `.env` file for compose to source during deployment. This chosen env file defines the application you would be running. Please set the device type (CPU, GPU and NPU) here. 2. Run `setup.sh` to setup pre-requisites, download artifacts, etc. 3. Bring the services up with `docker compose up`. 4. Run `sample_start.sh` to start pipeline. This sends curl request with pre-defined payload to the running DLStreamer Pipeline Server. diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/docs/user-guide/get-started.md b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/docs/user-guide/get-started.md index 10dbf7813..b5fd52f11 100644 --- a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/docs/user-guide/get-started.md +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/docs/user-guide/get-started.md @@ -127,6 +127,30 @@ If not, follow the [installation guide for docker engine](https://docs.docker.co Payload for pipeline 'pallet_defect_detection' {"source":{"uri":"file:///home/pipeline-server/resources/videos/warehouse.avi","type":"uri"},"destination":{"frame":{"type":"webrtc","peer-id":"pdd"}},"parameters":{"detection-properties":{"model":"/home/pipeline-server/resources/models/pallet-defect-detection/model.xml","device":"CPU"}}} Posting payload to REST server at https:///api/pipelines/user_defined_pipelines/pallet_defect_detection Payload for pipeline 'pallet_defect_detection' posted successfully. Response: "4b36b3ce52ad11f0ad60863f511204e2" + ``` + ```bash + ./sample_start.sh -p pallet_defect_detection_gpu + ``` + + This command will look for the payload for the pipeline specified in the `-p` argument above, inside the `payload_gpu.json` file and launch a pipeline instance in DLStreamer Pipeline Server. Refer to the table, to learn about different available options. + + Output: + + ```bash + # Example output for Pallet Defect Detection + Environment variables loaded from /home/intel/OEP/edge-ai-suites/manufacturing-ai-suite/industrial-edge-insights-vision/.env + Running sample app: pallet-defect-detection + Checking status of dlstreamer-pipeline-server... + Server reachable. HTTP Status Code: 200 + Loading payload from /home/intel/OEP/edge-ai-suites/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/payload_gpu.json + Payload loaded successfully. + Starting pipeline: pallet_defect_detection_gpu + Launching pipeline: pallet_defect_detection_gpu + Extracting payload for pipeline: pallet_defect_detection_gpu + Found 1 payload(s) for pipeline: pallet_defect_detection_gpu + Payload for pipeline 'pallet_defect_detection_gpu' {"source":{"uri":"file:///home/pipeline-server/resources/videos/warehouse.avi","type":"uri"},"destination":{"frame":{"type":"webrtc","peer-id":"pdd"}},"parameters":{"detection-properties":{"model":"/home/pipeline-server/resources/models/pallet-defect-detection/model.xml","device":"GPU"}}} + Posting payload to REST server at https:///api/pipelines/user_defined_pipelines/pallet_defect_detection_gpu + Payload for pipeline 'pallet_defect_detection' posted successfully. Response: "4b36b3ce52ad11f0ad60863f511204e2" ``` > **NOTE:** This will start the pipeline. To view the inference stream on WebRTC, open a browser and navigate to https:///mediamtx/pdd/ for Pallet Defect Detection diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/payload_gpu.json b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/payload_gpu.json new file mode 100644 index 000000000..30a1dd6b8 --- /dev/null +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/payload_gpu.json @@ -0,0 +1,23 @@ +[ + { + "pipeline": "pallet_defect_detection_gpu", + "payload":{ + "source": { + "uri": "file:///home/pipeline-server/resources/videos/warehouse.avi", + "type": "uri" + }, + "destination": { + "frame": { + "type": "webrtc", + "peer-id": "pdd" + } + }, + "parameters": { + "detection-properties": { + "model": "/home/pipeline-server/resources/models/pallet-defect-detection/deployment/Detection/model/model.xml", + "device": "GPU" + } + } + } + } +] \ No newline at end of file From 8e8e4529af144191043930e28b46cafef2836b22 Mon Sep 17 00:00:00 2001 From: tejaswinijayashanker943 Date: Fri, 10 Oct 2025 18:00:30 +0800 Subject: [PATCH 2/9] Payload JSON file will be chose based on DEVICE set in .env file - tested. --- .../docs/user-guide/get-started.md | 8 +++++--- .../industrial-edge-insights-vision/sample_start.sh | 12 ++++++++++-- 2 files changed, 15 insertions(+), 5 deletions(-) diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/docs/user-guide/get-started.md b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/docs/user-guide/get-started.md index b5fd52f11..6eeb6f811 100644 --- a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/docs/user-guide/get-started.md +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/docs/user-guide/get-started.md @@ -128,6 +128,7 @@ If not, follow the [installation guide for docker engine](https://docs.docker.co Posting payload to REST server at https:///api/pipelines/user_defined_pipelines/pallet_defect_detection Payload for pipeline 'pallet_defect_detection' posted successfully. Response: "4b36b3ce52ad11f0ad60863f511204e2" ``` + ```bash ./sample_start.sh -p pallet_defect_detection_gpu ``` @@ -142,15 +143,16 @@ If not, follow the [installation guide for docker engine](https://docs.docker.co Running sample app: pallet-defect-detection Checking status of dlstreamer-pipeline-server... Server reachable. HTTP Status Code: 200 + Using GPU payload file based on DEVICE=GPU Loading payload from /home/intel/OEP/edge-ai-suites/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/payload_gpu.json Payload loaded successfully. Starting pipeline: pallet_defect_detection_gpu Launching pipeline: pallet_defect_detection_gpu Extracting payload for pipeline: pallet_defect_detection_gpu Found 1 payload(s) for pipeline: pallet_defect_detection_gpu - Payload for pipeline 'pallet_defect_detection_gpu' {"source":{"uri":"file:///home/pipeline-server/resources/videos/warehouse.avi","type":"uri"},"destination":{"frame":{"type":"webrtc","peer-id":"pdd"}},"parameters":{"detection-properties":{"model":"/home/pipeline-server/resources/models/pallet-defect-detection/model.xml","device":"GPU"}}} - Posting payload to REST server at https:///api/pipelines/user_defined_pipelines/pallet_defect_detection_gpu - Payload for pipeline 'pallet_defect_detection' posted successfully. Response: "4b36b3ce52ad11f0ad60863f511204e2" + Payload for pipeline 'pallet_defect_detection_gpu' {"source":{"uri":"file:///home/pipeline-server/resources/videos/warehouse.avi","type":"uri"},"destination":{"frame":{"type":"webrtc","peer-id":"pdd"}},"parameters":{"detection-properties":{"model":"/home/pipeline-server/resources/models/pallet-defect-detection/deployment/Detection/model/model.xml","device":"GPU"}}} + Posting payload to REST server at https://10.107.248.78/api/pipelines/user_defined_pipelines/pallet_defect_detection_gpu + Payload for pipeline 'pallet_defect_detection_gpu' posted successfully. Response: "32d21dc2a5bf11f0bdcd3e9cdb54fa68" ``` > **NOTE:** This will start the pipeline. To view the inference stream on WebRTC, open a browser and navigate to https:///mediamtx/pdd/ for Pallet Defect Detection diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/sample_start.sh b/manufacturing-ai-suite/industrial-edge-insights-vision/sample_start.sh index f20b0f970..240ad973c 100755 --- a/manufacturing-ai-suite/industrial-edge-insights-vision/sample_start.sh +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/sample_start.sh @@ -42,8 +42,16 @@ init() { } load_payload() { - # Load all pipelines payload - PAYLOAD_FILE="$APP_DIR/payload.json" + # Load all pipelines payload based on DEVICE environment variable + # Use payload_gpu.json if DEVICE=GPU, otherwise use payload.json (default for CPU) + if [[ "$DEVICE" == "GPU" ]]; then + PAYLOAD_FILE="$APP_DIR/payload_gpu.json" + echo "Using GPU payload file based on DEVICE=$DEVICE" + else + PAYLOAD_FILE="$APP_DIR/payload.json" + echo "Using CPU payload file (DEVICE=${DEVICE:-CPU})" + fi + if [[ -f "$PAYLOAD_FILE" ]]; then echo "Loading payload from $PAYLOAD_FILE" if command -v jq &>/dev/null; then From 6e17c3fd896f7a85b9fcb234bff17b5684b857fd Mon Sep 17 00:00:00 2001 From: tejaswinijayashanker943 Date: Fri, 10 Oct 2025 18:33:19 +0800 Subject: [PATCH 3/9] Added playload JSON for GPU device type for PCB Anomaly detection. --- .../docs/user-guide/get-started.md | 27 +++++++++++++++++++ .../pcb-anomaly-detection/payload_gpu.json | 23 ++++++++++++++++ .../apps/weld-porosity/payload_gpu.json | 23 ++++++++++++++++ 3 files changed, 73 insertions(+) create mode 100644 manufacturing-ai-suite/industrial-edge-insights-vision/apps/pcb-anomaly-detection/payload_gpu.json create mode 100644 manufacturing-ai-suite/industrial-edge-insights-vision/apps/weld-porosity/payload_gpu.json diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pcb-anomaly-detection/docs/user-guide/get-started.md b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pcb-anomaly-detection/docs/user-guide/get-started.md index 2d5a054fe..759b08056 100644 --- a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pcb-anomaly-detection/docs/user-guide/get-started.md +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pcb-anomaly-detection/docs/user-guide/get-started.md @@ -125,6 +125,33 @@ If not, follow the [installation guide for docker engine](https://docs.docker.co Payload for pipeline 'pcb_anomaly_detection' posted successfully. Response: "f0c0b5aa5d4911f0bca7023bb629a486" ``` + ```bash + ./sample_start.sh -p pcb_anomaly_detection_gpu + ``` + + This command will look for the payload for the pipeline specified in the `-p` argument above, inside the `payload_gpu.json` file and launch a pipeline instance in DLStreamer Pipeline Server. Refer to the table, to learn about different available options. + + Output: + + ```bash + # Example output for PCB Anomaly Detection + Environment variables loaded from[WORKDIR]/manufacturing-ai-suite/industrial-edge-insights-vision/.env + Running sample app: pcb-anomaly-detection + Checking status of dlstreamer-pipeline-server... + Server reachable. HTTP Status Code: 200 + Using GPU payload file based on DEVICE=GPU + Loading payload from [WORKDIR]/manufacturing-ai-suite/ + industrial-edge-insights-vision/apps/pcb-anomaly-detection/payload_gpu.json + Payload loaded successfully. + Starting pipeline: pcb_anomaly_detection_gpu + Launching pipeline: pcb_anomaly_detection_gpu + Extracting payload for pipeline: pcb_anomaly_detection_gpu + Found 1 payload(s) for pipeline: pcb_anomaly_detection_gpu + Payload for pipeline 'pcb_anomaly_detection_gpu' {"source":{"uri":"file:///home/pipeline-server/resources/videos/anomalib_pcb_test.avi","type":"uri"},"destination":{"frame":{"type":"webrtc","peer-id":"anomaly"}},"parameters":{"classification-properties":{"model":"/home/pipeline-server/resources/models/pcb-anomaly-detection/deployment/Anomaly classification/model/model.xml","device":"GPU"}}} + Posting payload to REST server at https://10.107.248.78/api/pipelines/user_defined_pipelines/pcb_anomaly_detection_gpu + Payload for pipeline 'pcb_anomaly_detection_gpu' posted successfully. Response: "8b20d362a5c211f0a58caedecd052c61" + ``` + > **NOTE:** This will start the pipeline. The inference stream can be viewed on WebRTC, in a browser at the following url: ```bash diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pcb-anomaly-detection/payload_gpu.json b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pcb-anomaly-detection/payload_gpu.json new file mode 100644 index 000000000..36a456545 --- /dev/null +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pcb-anomaly-detection/payload_gpu.json @@ -0,0 +1,23 @@ +[ + { + "pipeline": "pcb_anomaly_detection_gpu", + "payload":{ + "source": { + "uri": "file:///home/pipeline-server/resources/videos/anomalib_pcb_test.avi", + "type": "uri" + }, + "destination": { + "frame": { + "type": "webrtc", + "peer-id": "anomaly" + } + }, + "parameters": { + "classification-properties": { + "model": "/home/pipeline-server/resources/models/pcb-anomaly-detection/deployment/Anomaly classification/model/model.xml", + "device": "GPU" + } + } + } + } +] diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/weld-porosity/payload_gpu.json b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/weld-porosity/payload_gpu.json new file mode 100644 index 000000000..417a30fdb --- /dev/null +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/weld-porosity/payload_gpu.json @@ -0,0 +1,23 @@ +[ + { + "pipeline": "weld_porosity_classification_gpu", + "payload": { + "source": { + "uri": "file:///home/pipeline-server/resources/videos/welding.avi", + "type": "uri" + }, + "destination": { + "frame": { + "type": "webrtc", + "peer-id": "weld" + } + }, + "parameters": { + "classification-properties": { + "model": "/home/pipeline-server/resources/models/weld-porosity/deployment/Classification/model/model.xml", + "device": "GPU" + } + } + } + } +] \ No newline at end of file From 3aa671537d07ad3987009f34e8306e228934d98c Mon Sep 17 00:00:00 2001 From: tejaswinijayashanker943 Date: Fri, 10 Oct 2025 19:34:38 +0800 Subject: [PATCH 4/9] Added Worker Safety Gear Detection GPU based Payload JSON and updated readme. --- .../docs/user-guide/get-started.md | 26 ++++++++++++++++++ .../docs/user-guide/get-started.md | 27 +++++++++++++++++++ .../payload_gpu.json | 23 ++++++++++++++++ 3 files changed, 76 insertions(+) create mode 100644 manufacturing-ai-suite/industrial-edge-insights-vision/apps/worker-safety-gear-detection/payload_gpu.json diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/weld-porosity/docs/user-guide/get-started.md b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/weld-porosity/docs/user-guide/get-started.md index b2aa5d582..3bb3ebf0c 100644 --- a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/weld-porosity/docs/user-guide/get-started.md +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/weld-porosity/docs/user-guide/get-started.md @@ -131,6 +131,32 @@ If not, follow the [installation guide for docker engine](https://docs.docker.co ``` + ```bash + ./sample_start.sh -p weld_porosity_classification_gpu + ``` + + This command will look for the payload for the pipeline specified in `-p` argument above, inside the `payload_gpu.json` file and launch the a pipeline instance in DLStreamer Pipeline Server. Refer to the table, to learn about different options available. + + Output: + + ```bash + + Environment variables loaded from /home/intel/OEP/new/edge-ai-suites/manufacturing-ai-suite/industrial-edge-insights-vision/.env + Running sample app: weld-porosity + Checking status of dlstreamer-pipeline-server... + Server reachable. HTTP Status Code: 200 + Using GPU payload file based on DEVICE=GPU + Loading payload from /home/intel/OEP/new/edge-ai-suites/manufacturing-ai-suite/industrial-edge-insights-vision/apps/weld-porosity/payload_gpu.json + Payload loaded successfully. + Starting pipeline: weld_porosity_classification_gpu + Launching pipeline: weld_porosity_classification_gpu + Extracting payload for pipeline: weld_porosity_classification_gpu + Found 1 payload(s) for pipeline: weld_porosity_classification_gpu + Payload for pipeline 'weld_porosity_classification_gpu' {"source":{"uri":"file:///home/pipeline-server/resources/videos/welding.avi","type":"uri"},"destination":{"frame":{"type":"webrtc","peer-id":"weld"}},"parameters":{"classification-properties":{"model":"/home/pipeline-server/resources/models/weld-porosity/deployment/Classification/model/model.xml","device":"GPU"}}} + Posting payload to REST server at https://10.107.248.78/api/pipelines/user_defined_pipelines/weld_porosity_classification_gpu + Payload for pipeline 'weld_porosity_classification_gpu' posted successfully. Response: "e978a766a5c511f0b5ed5abd6f584899" + ``` + > **NOTE:** This will start the pipeline. The inference stream can be viewed on WebRTC, in a browser, at the following url: ```bash diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/worker-safety-gear-detection/docs/user-guide/get-started.md b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/worker-safety-gear-detection/docs/user-guide/get-started.md index c65bf83d3..b78fc8b1f 100644 --- a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/worker-safety-gear-detection/docs/user-guide/get-started.md +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/worker-safety-gear-detection/docs/user-guide/get-started.md @@ -124,6 +124,33 @@ If not, follow the [installation guide for docker engine](https://docs.docker.co Payload for pipeline 'worker_safety_gear_detection' posted successfully. Response: "784b87b45d1511f08ab0da88aa49c01e" ``` + ```bash + ./sample_start.sh -p worker_safety_gear_detection_gpu + ``` + + This command will look for the payload for the pipeline specified in the `-p` argument above, inside the `payload_gpu.json` file and launch a pipeline instance in DLStreamer Pipeline Server. Refer to the table, to learn about different available options. + + Output: + + ```bash + # Example output for Worker Safety gear detection + Environment variables loaded from [WORKDIR]/manufacturing-ai-suite/industrial-edge-insights-vision/.env + Running sample app: worker-safety-gear-detection + Checking status of dlstreamer-pipeline-server... + Server reachable. HTTP Status Code: 200 + Using GPU payload file based on DEVICE=GPU + Loading payload from [WORKDIR]/manufacturing-ai-suite/industrial-edge-insights-vision/apps/worker-safety-gear-detection/payload_gpu.json + Payload loaded successfully. + Starting pipeline: worker_safety_gear_detection_gpu + Launching pipeline: worker_safety_gear_detection_gpu + Extracting payload for pipeline: worker_safety_gear_detection_gpu + Found 1 payload(s) for pipeline: worker_safety_gear_detection_gpu + Payload for pipeline 'worker_safety_gear_detection_gpu' {"source":{"uri":"file:///home/pipeline-server/resources/videos/Safety_Full_Hat_and_Vest.avi","type":"uri"},"destination":{"frame":{"type":"webrtc","peer-id":"worker_safety"}},"parameters":{"detection-properties":{"model":"/home/pipeline-server/resources/models/worker-safety-gear-detection/deployment/Detection/model/model.xml","device":"GPU"}}} + Posting payload to REST server at https://10.107.248.78/api/pipelines/user_defined_pipelines/worker_safety_gear_detection_gpu + Payload for pipeline 'worker_safety_gear_detection_gpu' posted successfully. Response: "04fca2f8a5cb11f0bfae5a85c03cd2f6" + ``` + + NOTE: This will start the pipeline. The inference stream can be viewed on WebRTC, in a browser, at the following url: ```sh diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/worker-safety-gear-detection/payload_gpu.json b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/worker-safety-gear-detection/payload_gpu.json new file mode 100644 index 000000000..160fcb08a --- /dev/null +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/worker-safety-gear-detection/payload_gpu.json @@ -0,0 +1,23 @@ +[ + { + "pipeline": "worker_safety_gear_detection_gpu", + "payload":{ + "source": { + "uri": "file:///home/pipeline-server/resources/videos/Safety_Full_Hat_and_Vest.avi", + "type": "uri" + }, + "destination": { + "frame": { + "type": "webrtc", + "peer-id": "worker_safety" + } + }, + "parameters": { + "detection-properties": { + "model": "/home/pipeline-server/resources/models/worker-safety-gear-detection/deployment/Detection/model/model.xml", + "device": "GPU" + } + } + } + } +] \ No newline at end of file From b6c2d6227ffe2b4a83462b6192ab05dadfac3a2f Mon Sep 17 00:00:00 2001 From: Tejaswini Jayashanker Date: Thu, 16 Oct 2025 10:18:10 +0530 Subject: [PATCH 5/9] Updated peer-id to payload_gpu.json Co-authored-by: Ashish Jagadish --- .../apps/pallet-defect-detection/payload_gpu.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/payload_gpu.json b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/payload_gpu.json index 30a1dd6b8..3dcc49361 100644 --- a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/payload_gpu.json +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pallet-defect-detection/payload_gpu.json @@ -9,7 +9,7 @@ "destination": { "frame": { "type": "webrtc", - "peer-id": "pdd" + "peer-id": "pddgpu" } }, "parameters": { From 6b885c7dbae8077fc30866549276020551cf1d6a Mon Sep 17 00:00:00 2001 From: Tejaswini Jayashanker Date: Thu, 16 Oct 2025 10:18:33 +0530 Subject: [PATCH 6/9] Updated peer-id to payload_gpu.json Co-authored-by: Ashish Jagadish --- .../apps/pcb-anomaly-detection/payload_gpu.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pcb-anomaly-detection/payload_gpu.json b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pcb-anomaly-detection/payload_gpu.json index 36a456545..b64742814 100644 --- a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pcb-anomaly-detection/payload_gpu.json +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pcb-anomaly-detection/payload_gpu.json @@ -9,7 +9,7 @@ "destination": { "frame": { "type": "webrtc", - "peer-id": "anomaly" + "peer-id": "anomalygpu" } }, "parameters": { From 1f75542308995b2ed77a8a3734e9830f8bdd1076 Mon Sep 17 00:00:00 2001 From: Tejaswini Jayashanker Date: Thu, 16 Oct 2025 10:18:49 +0530 Subject: [PATCH 7/9] Updated peer-id to payload_gpu.json Co-authored-by: Ashish Jagadish --- .../apps/weld-porosity/payload_gpu.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/weld-porosity/payload_gpu.json b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/weld-porosity/payload_gpu.json index 417a30fdb..9bf843c64 100644 --- a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/weld-porosity/payload_gpu.json +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/weld-porosity/payload_gpu.json @@ -9,7 +9,7 @@ "destination": { "frame": { "type": "webrtc", - "peer-id": "weld" + "peer-id": "weldgpu" } }, "parameters": { From 48d154f537a75392bc9816b26494e57329f69147 Mon Sep 17 00:00:00 2001 From: Tejaswini Jayashanker Date: Thu, 16 Oct 2025 10:19:00 +0530 Subject: [PATCH 8/9] Updated peer-id to payload_gpu.json Co-authored-by: Ashish Jagadish --- .../apps/worker-safety-gear-detection/payload_gpu.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/worker-safety-gear-detection/payload_gpu.json b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/worker-safety-gear-detection/payload_gpu.json index 160fcb08a..5eea25dc7 100644 --- a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/worker-safety-gear-detection/payload_gpu.json +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/worker-safety-gear-detection/payload_gpu.json @@ -9,7 +9,7 @@ "destination": { "frame": { "type": "webrtc", - "peer-id": "worker_safety" + "peer-id": "worker_safety_gpu" } }, "parameters": { From f4d08b2bae3a10aa055a57a48cacad8495b3c566 Mon Sep 17 00:00:00 2001 From: Tejaswini Jayashanker Date: Thu, 16 Oct 2025 10:20:04 +0530 Subject: [PATCH 9/9] Updated get-started.md to be precise Co-authored-by: Ashish Jagadish --- .../docs/user-guide/get-started.md | 27 ------------------- 1 file changed, 27 deletions(-) diff --git a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pcb-anomaly-detection/docs/user-guide/get-started.md b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pcb-anomaly-detection/docs/user-guide/get-started.md index 759b08056..2d5a054fe 100644 --- a/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pcb-anomaly-detection/docs/user-guide/get-started.md +++ b/manufacturing-ai-suite/industrial-edge-insights-vision/apps/pcb-anomaly-detection/docs/user-guide/get-started.md @@ -125,33 +125,6 @@ If not, follow the [installation guide for docker engine](https://docs.docker.co Payload for pipeline 'pcb_anomaly_detection' posted successfully. Response: "f0c0b5aa5d4911f0bca7023bb629a486" ``` - ```bash - ./sample_start.sh -p pcb_anomaly_detection_gpu - ``` - - This command will look for the payload for the pipeline specified in the `-p` argument above, inside the `payload_gpu.json` file and launch a pipeline instance in DLStreamer Pipeline Server. Refer to the table, to learn about different available options. - - Output: - - ```bash - # Example output for PCB Anomaly Detection - Environment variables loaded from[WORKDIR]/manufacturing-ai-suite/industrial-edge-insights-vision/.env - Running sample app: pcb-anomaly-detection - Checking status of dlstreamer-pipeline-server... - Server reachable. HTTP Status Code: 200 - Using GPU payload file based on DEVICE=GPU - Loading payload from [WORKDIR]/manufacturing-ai-suite/ - industrial-edge-insights-vision/apps/pcb-anomaly-detection/payload_gpu.json - Payload loaded successfully. - Starting pipeline: pcb_anomaly_detection_gpu - Launching pipeline: pcb_anomaly_detection_gpu - Extracting payload for pipeline: pcb_anomaly_detection_gpu - Found 1 payload(s) for pipeline: pcb_anomaly_detection_gpu - Payload for pipeline 'pcb_anomaly_detection_gpu' {"source":{"uri":"file:///home/pipeline-server/resources/videos/anomalib_pcb_test.avi","type":"uri"},"destination":{"frame":{"type":"webrtc","peer-id":"anomaly"}},"parameters":{"classification-properties":{"model":"/home/pipeline-server/resources/models/pcb-anomaly-detection/deployment/Anomaly classification/model/model.xml","device":"GPU"}}} - Posting payload to REST server at https://10.107.248.78/api/pipelines/user_defined_pipelines/pcb_anomaly_detection_gpu - Payload for pipeline 'pcb_anomaly_detection_gpu' posted successfully. Response: "8b20d362a5c211f0a58caedecd052c61" - ``` - > **NOTE:** This will start the pipeline. The inference stream can be viewed on WebRTC, in a browser at the following url: ```bash