From d8dcdec04319dc44cd85ac9139459d0fbcd8b7de Mon Sep 17 00:00:00 2001 From: suryam789 Date: Mon, 17 Nov 2025 18:29:14 +0530 Subject: [PATCH 01/14] Update getting_started.md --- .../automated-self-checkout/getting_started.md | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/docs_src/use-cases/automated-self-checkout/getting_started.md b/docs_src/use-cases/automated-self-checkout/getting_started.md index f1a8789..601f160 100644 --- a/docs_src/use-cases/automated-self-checkout/getting_started.md +++ b/docs_src/use-cases/automated-self-checkout/getting_started.md @@ -1,5 +1,18 @@ # Getting Started +### **NOTE:** + +By default the application runs by pulling the pre-built images. If you want to build the images locally and then run the application, set the flag: + +```bash +REGISTRY=false + +usage: make REGISTRY=false (applicable for all commands like benchmark, benchmark-stream-density..) +Example: make run-demo REGISTRY=false +``` + +(If this is the first time, it will take some time to download videos, models, docker images and build images) + ## Step by step instructions: 1. Download the models using download_models/downloadModels.sh From b8589c515a7a8aca3363804086d1a9b7bab0952e Mon Sep 17 00:00:00 2001 From: suryam789 Date: Mon, 17 Nov 2025 18:35:06 +0530 Subject: [PATCH 02/14] Added REGISTRY to Common ENVs --- docs_src/use-cases/automated-self-checkout/advanced.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs_src/use-cases/automated-self-checkout/advanced.md b/docs_src/use-cases/automated-self-checkout/advanced.md index 30a7840..fb52f3c 100644 --- a/docs_src/use-cases/automated-self-checkout/advanced.md +++ b/docs_src/use-cases/automated-self-checkout/advanced.md @@ -70,7 +70,6 @@ The table below lists the environment variables (EVs) that can be used as inputs |`DOCKER_COMPOSE` | The docker-compose.yml file to run | src/docker-compose.yml | |`RETAIL_USE_CASE_ROOT` | The root directory for Automated Self Checkout in relation to the docker-compose.yml | .. | |`RESULTS_DIR` | Directory to output results | ../results | - |`REGISTRY` | Option to pull the pre-built images rather than creating them locally | true | === "Docker Compose Parameters" This list of parameters that can be set when running docker compose up @@ -92,6 +91,7 @@ The table below lists the environment variables (EVs) that can be used as inputs |`GST_DEBUG` | for running pipeline in gst debugging mode | 0, 1 | |`LOG_LEVEL` | log level to be set when running gst pipeline | ERROR, INFO, WARNING, and [more](https://gstreamer.freedesktop.org/documentation/tutorials/basic/debugging-tools.html?gi-language=c#the-debug-log) | |`OCR_RECLASSIFY_INTERVAL` | time interval in seconds for OCR classification | Ex: 5 | + |`REGISTRY` | Option to pull the pre-built images rather than creating them locally (by default:true) | false, true | |`RENDER_MODE` | for displaying pipeline and overlay CV metadata | 1, 0 | |`PIPELINE_COUNT` | Number of Automated Self Checkout Docker container instances to launch | Ex: 1 | |`PIPELINE_SCRIPT` | Pipeline script to run. | yolo11n.sh, yolo11n_effnetb0.sh, yolo11n_full.sh | From 54f411b0b458a021fd8e8a82cd3a3ae61645bd26 Mon Sep 17 00:00:00 2001 From: suryam789 Date: Mon, 17 Nov 2025 18:58:21 +0530 Subject: [PATCH 03/14] REGISTRY now true by default --- .../use-cases/automated-self-checkout/performance.md | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/docs_src/use-cases/automated-self-checkout/performance.md b/docs_src/use-cases/automated-self-checkout/performance.md index a4bdad6..5017eb1 100644 --- a/docs_src/use-cases/automated-self-checkout/performance.md +++ b/docs_src/use-cases/automated-self-checkout/performance.md @@ -15,6 +15,7 @@ make benchmark-quickstart ``` The above command would:
- Run headless (no display needed: `RENDER_MODE=0`)
+- Pull pre-built images (`REGISTRY=true`)
- Use full pipeline (`PIPELINE_SCRIPT=obj_detection_age_prediction.sh`)
- Target GPU by default (`DEVICE_ENV=res/all-gpu.env`)
- Generate benchmark metrics
@@ -52,7 +53,7 @@ List of EVs: |`PIPELINE_COUNT` | number of Automated Self Checkout Docker container instances to launch | Ex: 1 | |`PIPELINE_SCRIPT` | pipeline script to run. | yolo11n_effnetb0.sh, obj_detection_age_prediction.sh, etc. | |`DEVICE_ENV` | device to use for classification and detection | res/all-cpu.env, res/all-gpu.env, res/det-gpu_class-npu.env, etc. | - |`REGISTRY` | option to pull pre-built images from registry rather than building them locally | true | + |`REGISTRY` | option to pull pre-built images from registry rather than building them locally (by default:true) | false, true | > **Note:** > Higher the `PIPELINE_COUNT`, higher the stress on the system. @@ -86,10 +87,13 @@ make PIPELINE_SCRIPT=obj_detection_age_prediction.sh DEVICE_ENV=res/all-gpu.env Stream 1: Object detection + classification on retail video
Stream 2: Face detection + age/gender prediction on age prediction video -### Benchmark command to pull pre-built images +### Benchmark command to build images locally + +!!! Note + By default the images are pulled from public repository. ```bash -make REGISTRY=true PIPELINE_COUNT=1 benchmark +make REGISTRY=false PIPELINE_COUNT=1 benchmark ``` From 9eec8f54ac13936e7d4ecd1042202c95b095a705 Mon Sep 17 00:00:00 2001 From: suryam789 Date: Mon, 17 Nov 2025 20:21:09 +0530 Subject: [PATCH 04/14] REGISTRY changes added --- .../getting_started.md | 30 ++++++++++++++----- 1 file changed, 22 insertions(+), 8 deletions(-) diff --git a/docs_src/use-cases/automated-self-checkout/getting_started.md b/docs_src/use-cases/automated-self-checkout/getting_started.md index 601f160..b5fdc3e 100644 --- a/docs_src/use-cases/automated-self-checkout/getting_started.md +++ b/docs_src/use-cases/automated-self-checkout/getting_started.md @@ -33,13 +33,7 @@ Example: make run-demo REGISTRY=false make download-sample-videos ``` -4. Build the demo Docker image - - ```bash - make build - ``` - -5. Start Automated Self Checkout using the Docker Compose file. The Docker Compose also includes an RTSP camera simulator that will infinitely loop through the sample videos downloaded in step 3. +4. Start Automated Self Checkout using the Docker Compose file. ```bash make run-render-mode @@ -50,6 +44,26 @@ Example: make run-demo REGISTRY=false ```bash make run-demo ``` +5. To build the images locally step by step: + - Follow the following steps: + ```bash + make download-models REGISTRY=false + make update-submodules REGISTRY=false + make download-sample-videos REGISTRY=false + ``` + - Now build the pipeline-runner image locally: + ```bash + make build REGISTRY=false + ``` + - Finally, start Automated self checkout using docker compose up. + ```bash + make run-render-mode REGISTRY=false + ``` + - The above series of commands can be executed using only one command: + + ```bash + make run-demo REGISTRY=false + ``` 6. Verify Docker containers @@ -107,7 +121,7 @@ Example: make run-demo REGISTRY=false {"objects":[{"detection":{"bounding_box":{"x_max":1.0,"x_min":0.6974737628926411,"y_max":0.8381138710318847,"y_min":0.44749696271196093},"confidence":0.7188630104064941,"label":"person","label_id":0},"h":422,"region_id":576,"roi_type":"person","w":581,"x":1339,"y":483}],"resolution":{"height":1080,"width":1920},"timestamp":133305076} ``` -8. Stop the demo using docker compose down +9. Stop the demo using docker compose down ```bash make down ``` From 852d6cb4f31e2ee0c949abafdae74ede13fc5be7 Mon Sep 17 00:00:00 2001 From: suryam789 Date: Mon, 17 Nov 2025 20:43:23 +0530 Subject: [PATCH 05/14] Update getting_started.md --- docs_src/use-cases/automated-self-checkout/getting_started.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs_src/use-cases/automated-self-checkout/getting_started.md b/docs_src/use-cases/automated-self-checkout/getting_started.md index b5fdc3e..68342e2 100644 --- a/docs_src/use-cases/automated-self-checkout/getting_started.md +++ b/docs_src/use-cases/automated-self-checkout/getting_started.md @@ -121,7 +121,7 @@ Example: make run-demo REGISTRY=false {"objects":[{"detection":{"bounding_box":{"x_max":1.0,"x_min":0.6974737628926411,"y_max":0.8381138710318847,"y_min":0.44749696271196093},"confidence":0.7188630104064941,"label":"person","label_id":0},"h":422,"region_id":576,"roi_type":"person","w":581,"x":1339,"y":483}],"resolution":{"height":1080,"width":1920},"timestamp":133305076} ``` -9. Stop the demo using docker compose down +8. Stop the demo using docker compose down ```bash make down ``` From 46d0ca6fa7f31486395442562461f2c0d4a97ca1 Mon Sep 17 00:00:00 2001 From: suryam789 Date: Tue, 18 Nov 2025 13:56:52 +0530 Subject: [PATCH 06/14] Pre-built by default --- docs_src/use-cases/automated-self-checkout/getting_started.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs_src/use-cases/automated-self-checkout/getting_started.md b/docs_src/use-cases/automated-self-checkout/getting_started.md index 68342e2..ae3f39b 100644 --- a/docs_src/use-cases/automated-self-checkout/getting_started.md +++ b/docs_src/use-cases/automated-self-checkout/getting_started.md @@ -49,7 +49,7 @@ Example: make run-demo REGISTRY=false ```bash make download-models REGISTRY=false make update-submodules REGISTRY=false - make download-sample-videos REGISTRY=false + make download-sample-videos ``` - Now build the pipeline-runner image locally: ```bash From cca4468c93db5746a096c4011dcdd6422bce7723 Mon Sep 17 00:00:00 2001 From: suryam789 Date: Tue, 18 Nov 2025 14:01:39 +0530 Subject: [PATCH 07/14] Pre-built by default --- .../loss-prevention/getting_started.md | 33 +++++++++++++++++-- 1 file changed, 30 insertions(+), 3 deletions(-) diff --git a/docs_src/use-cases/loss-prevention/getting_started.md b/docs_src/use-cases/loss-prevention/getting_started.md index e654490..a4ed027 100644 --- a/docs_src/use-cases/loss-prevention/getting_started.md +++ b/docs_src/use-cases/loss-prevention/getting_started.md @@ -1,5 +1,18 @@ # Getting Started +### **NOTE:** + +By default the application runs by pulling the pre-built images. If you want to build the images locally and then run the application, set the flag: + +```bash +REGISTRY=false + +usage: make REGISTRY=false (applicable for all commands like benchmark, benchmark-stream-density..) +Example: make run-lp REGISTRY=false +``` + +(If this is the first time, it will take some time to download videos, models, docker images and build images) + ## Step by step instructions: 1. Download the models using download_models/downloadModels.sh @@ -28,7 +41,7 @@ **NOTE:- User can directly run single make command that internally called all above command and run the Loss Prevention application.** -5. Run Loss Prevention appliaction with single command. +- Run Loss Prevention appliaction with single command. ```bash make run-lp @@ -36,11 +49,25 @@ - Running Loss Prevention application with ENV variables: ```bash - REGISTRY=true CAMERA_STREAM=camera_to_workload_full.json WORKLOAD_DIST=workload_to_pipeline_cpu.json make run-lp + CAMERA_STREAM=camera_to_workload_full.json WORKLOAD_DIST=workload_to_pipeline_cpu.json make run-lp ``` - `REGISTRY=true`: pre-built images are pulled.
`CAMERA_STREAM=camera_to_workload_full.json`: runs all 6 workloads.
`WORKLOAD_DIST=workload_to_pipeline_cpu.json`: all workloads run on CPU.
+ +5. To build the images locally step by step: + - Follow the following steps: + ```bash + make download-models REGISTRY=false + make update-submodules REGISTRY=false + make download-sample-videos + make run-render-mode REGISTRY=false + ``` + + - The above series of commands can be executed using only one command: + + ```bash + make run-lp REGISTRY=false + ``` 6. View the Dynamically Generated GStreamer Pipeline. >*Since the GStreamer pipeline is generated dynamically based on the provided configuration(camera_to_workload and workload_to_pipeline json), the pipeline.sh file gets updated every time the user runs make run-lp or make benchmark. This ensures that the pipeline reflects the latest changes.* From fab5ff1f6b29cb579967c424c084b268a8703fcc Mon Sep 17 00:00:00 2001 From: suryam789 Date: Tue, 18 Nov 2025 15:06:38 +0530 Subject: [PATCH 08/14] Pre-built by default --- docs_src/use-cases/loss-prevention/advanced.md | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/docs_src/use-cases/loss-prevention/advanced.md b/docs_src/use-cases/loss-prevention/advanced.md index 85551ca..6adf69c 100644 --- a/docs_src/use-cases/loss-prevention/advanced.md +++ b/docs_src/use-cases/loss-prevention/advanced.md @@ -9,6 +9,7 @@ make benchmark-quickstart ``` The above command would:
- Run headless (no display needed: `RENDER_MODE=0`)
+- Pull pre-built images (`REGISTRY=true`)
- Target GPU by default (`WORKLOAD_DIST=workload_to_pipeline_gpu.json`)
- Run 6 streams, each with different workload (`CAMERA_STREAM=camera_to_workload_full.json`)
- Generate benchmark metrics
@@ -32,7 +33,7 @@ Runs with:
- `CAMERA_STREAM=camera_to_workload.json`
- `WORKLOAD_DIST=workload_to_pipeline.json`
- `PIPELINE_COUNT=1`
-- `REGISTRY=false`
+- `REGISTRY=true`
You can override these values through the following Environment Variables. @@ -42,7 +43,7 @@ You can override these values through the following Environment Variables. |`PIPELINE_COUNT` | number of Loss Prevention Docker container instances to launch | Ex: 1 | |`WORKLOAD_DIST` | to define how each workload is assigned to a specific processing unit (CPU, GPU, NPU) | workload_to_pipeline_cpu.json, workload_to_pipeline_gpu.json, workload_to_pipeline_gpu-npu.json, workload_to_pipeline_hetero.json, workload_to_pipeline.json | |`CAMERA_STREAM` | to define camera settings and their associated workloads for the pipeline | camera_to_workload.json, camera_to_workload_full.json | -|`REGISTRY` | option to pull the pre-built images rather than creating them locally | true, false | +|`REGISTRY` | option to pull the pre-built images rather than creating them locally | false, true | > **Note:** > Higher the `PIPELINE_COUNT`, higher the stress on the system. @@ -99,11 +100,12 @@ You can override these values through the following Environment Variables. ### Benchmark command with environment variable overrides ```bash -make benchmark WORKLOAD_DIST=workload_to_pipeline_gpu-npu.json CAMERA_STREAM=camera_to_workload_full.json +make benchmark WORKLOAD_DIST=workload_to_pipeline_gpu-npu.json CAMERA_STREAM=camera_to_workload_full.json REGISTRY=false ``` Runs with:
- `RENDER_MODE=0`
+- `REGISTRY=false` (Builds images locally)
- `CAMERA_STREAM=camera_to_workload_full.json`
- `WORKLOAD_DIST=workload_to_pipeline_gpu-npu.json`
- `PIPELINE_COUNT=1`
@@ -112,7 +114,7 @@ Runs with:
### See the benchmarking results ```sh -make consolidate-metrics +make consolidate-metrics cat benchmark/metrics.csv ``` From c4bb3b8fc9295de663fbaba9a59b976b0673f9c0 Mon Sep 17 00:00:00 2001 From: suryam789 Date: Tue, 18 Nov 2025 20:02:28 +0530 Subject: [PATCH 09/14] Pre-built by default --- .../order-accuracy/getting_started.md | 34 ++++++++++++++++--- 1 file changed, 29 insertions(+), 5 deletions(-) diff --git a/docs_src/use-cases/order-accuracy/getting_started.md b/docs_src/use-cases/order-accuracy/getting_started.md index 8003674..dff1acc 100644 --- a/docs_src/use-cases/order-accuracy/getting_started.md +++ b/docs_src/use-cases/order-accuracy/getting_started.md @@ -1,5 +1,18 @@ # Getting Started +### **NOTE:** + +By default the application runs by pulling the pre-built images. If you want to build the images locally and then run the application, set the flag: + +```bash +REGISTRY=false + +usage: make REGISTRY=false (applicable for all commands like benchmark, benchmark-stream-density..) +Example: make run-demo REGISTRY=false +``` + +(If this is the first time, it will take some time to download videos, models, docker images and build images) + ## Step by step instructions: 1. Download the models using download_models/downloadModels.sh @@ -26,12 +39,23 @@ make run-render-mode ``` - **NOTE:- User can directly run single make command that internally called all above command and run the Order Accuracy application.** - -5. Run Order Accuracy appliaction with single command. - +- The above series of commands can be executed using only one command: + + ```bash + make run-demo + ``` + +5. To build the images locally step by step: +- Follow the following steps: + ```bash + make download-models REGISTRY=false + make update-submodules REGISTRY=false + make download-sample-videos + make run-render-mode REGISTRY=false + ``` +- The above series of commands can be executed using only one command: ```bash - make run-demo + make run-demo REGISTRY=false ``` 6. Verify Docker containers From d2aa50ec93079441e38034fbd0e1585a73021c15 Mon Sep 17 00:00:00 2001 From: suryam789 Date: Tue, 18 Nov 2025 20:12:15 +0530 Subject: [PATCH 10/14] Pre-built by default --- docs_src/use-cases/order-accuracy/advanced.md | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/docs_src/use-cases/order-accuracy/advanced.md b/docs_src/use-cases/order-accuracy/advanced.md index 70f0718..559d651 100644 --- a/docs_src/use-cases/order-accuracy/advanced.md +++ b/docs_src/use-cases/order-accuracy/advanced.md @@ -9,6 +9,7 @@ make benchmark-quickstart ``` The above command would:
- Run headless (no display needed: `RENDER_MODE=0`)
+- Pull pre-built images (`REGISTRY=true`)
- Target GPU by default (`DEVICE_ENV=res/all-gpu.env`)
- Generate benchmark metrics
- Run `make consolidate-metrics` automatically
@@ -28,6 +29,7 @@ make benchmark ``` Runs with:
- `RENDER_MODE=0`
+- `REGISTRY=true`
- `DEVICE_ENV=res/all-cpu.env`
- `PIPELINE_COUNT=1`
@@ -36,6 +38,7 @@ You can override these values through the following Environment Variables. | Variable | Description | Values | |:----|:----|:---| |`RENDER_MODE` | for displaying pipeline and overlay CV metadata | 1, 0 | +|`REGISTRY` | to pull pre-built images from public registry | false, true | |`PIPELINE_COUNT` | number of Loss Prevention Docker container instances to launch | Ex: 1 | |`DEVICE_ENV` | path to device specific environment file that will be loaded into the pipeline container | res/all-cpu.env, res/all-gpu.env, res/all-npu.env, res/all-dgpu.env | @@ -53,10 +56,16 @@ make DEVICE_ENV=res/all-gpu.env benchmark make DEVICE_ENV=res/all-npu.env benchmark ``` +### Benchmark command to build images locally + +```bash +make REGISTRY=false benchmark +``` + ## See the benchmarking results. ```sh -make consolidate-metrics +make consolidate-metrics cat benchmark/metrics.csv ``` From efb4614aff278cb5674ec3adc63f9e050b0a8166 Mon Sep 17 00:00:00 2001 From: suryam789 Date: Tue, 18 Nov 2025 20:39:44 +0530 Subject: [PATCH 11/14] Added TAG --- docs_src/use-cases/loss-prevention/getting_started.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs_src/use-cases/loss-prevention/getting_started.md b/docs_src/use-cases/loss-prevention/getting_started.md index a4ed027..59567b7 100644 --- a/docs_src/use-cases/loss-prevention/getting_started.md +++ b/docs_src/use-cases/loss-prevention/getting_started.md @@ -2,7 +2,7 @@ ### **NOTE:** -By default the application runs by pulling the pre-built images. If you want to build the images locally and then run the application, set the flag: +By default the application runs by pulling the pre-built images with `TAG=rc1`. If you want to build the images locally and then run the application, set the flag: ```bash REGISTRY=false From 467372109156137d07c5d27b421be058d87e921f Mon Sep 17 00:00:00 2001 From: suryam789 Date: Tue, 18 Nov 2025 20:46:55 +0530 Subject: [PATCH 12/14] Added TAG --- docs_src/use-cases/loss-prevention/advanced.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/docs_src/use-cases/loss-prevention/advanced.md b/docs_src/use-cases/loss-prevention/advanced.md index 6adf69c..644ef2d 100644 --- a/docs_src/use-cases/loss-prevention/advanced.md +++ b/docs_src/use-cases/loss-prevention/advanced.md @@ -10,6 +10,7 @@ make benchmark-quickstart The above command would:
- Run headless (no display needed: `RENDER_MODE=0`)
- Pull pre-built images (`REGISTRY=true`)
+- Images tag: rc1 (`TAG=rc1`)
- Target GPU by default (`WORKLOAD_DIST=workload_to_pipeline_gpu.json`)
- Run 6 streams, each with different workload (`CAMERA_STREAM=camera_to_workload_full.json`)
- Generate benchmark metrics
@@ -30,6 +31,7 @@ make benchmark ``` Runs with:
- `RENDER_MODE=0`
+- `TAG=rc1`
- `CAMERA_STREAM=camera_to_workload.json`
- `WORKLOAD_DIST=workload_to_pipeline.json`
- `PIPELINE_COUNT=1`
@@ -44,6 +46,7 @@ You can override these values through the following Environment Variables. |`WORKLOAD_DIST` | to define how each workload is assigned to a specific processing unit (CPU, GPU, NPU) | workload_to_pipeline_cpu.json, workload_to_pipeline_gpu.json, workload_to_pipeline_gpu-npu.json, workload_to_pipeline_hetero.json, workload_to_pipeline.json | |`CAMERA_STREAM` | to define camera settings and their associated workloads for the pipeline | camera_to_workload.json, camera_to_workload_full.json | |`REGISTRY` | option to pull the pre-built images rather than creating them locally | false, true | +|`TAG` | tag for the images pulled | rc1 | > **Note:** > Higher the `PIPELINE_COUNT`, higher the stress on the system. From 88e73febf921993f537241c511c04b4c6782bda5 Mon Sep 17 00:00:00 2001 From: suryam789 Date: Tue, 18 Nov 2025 21:03:44 +0530 Subject: [PATCH 13/14] Removed TAG --- docs_src/use-cases/loss-prevention/getting_started.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs_src/use-cases/loss-prevention/getting_started.md b/docs_src/use-cases/loss-prevention/getting_started.md index 59567b7..a4ed027 100644 --- a/docs_src/use-cases/loss-prevention/getting_started.md +++ b/docs_src/use-cases/loss-prevention/getting_started.md @@ -2,7 +2,7 @@ ### **NOTE:** -By default the application runs by pulling the pre-built images with `TAG=rc1`. If you want to build the images locally and then run the application, set the flag: +By default the application runs by pulling the pre-built images. If you want to build the images locally and then run the application, set the flag: ```bash REGISTRY=false From 1b20fe2037cc88823525955848180df25c88700d Mon Sep 17 00:00:00 2001 From: suryam789 Date: Tue, 18 Nov 2025 21:04:34 +0530 Subject: [PATCH 14/14] Removed TAG --- docs_src/use-cases/loss-prevention/advanced.md | 3 --- 1 file changed, 3 deletions(-) diff --git a/docs_src/use-cases/loss-prevention/advanced.md b/docs_src/use-cases/loss-prevention/advanced.md index 644ef2d..6adf69c 100644 --- a/docs_src/use-cases/loss-prevention/advanced.md +++ b/docs_src/use-cases/loss-prevention/advanced.md @@ -10,7 +10,6 @@ make benchmark-quickstart The above command would:
- Run headless (no display needed: `RENDER_MODE=0`)
- Pull pre-built images (`REGISTRY=true`)
-- Images tag: rc1 (`TAG=rc1`)
- Target GPU by default (`WORKLOAD_DIST=workload_to_pipeline_gpu.json`)
- Run 6 streams, each with different workload (`CAMERA_STREAM=camera_to_workload_full.json`)
- Generate benchmark metrics
@@ -31,7 +30,6 @@ make benchmark ``` Runs with:
- `RENDER_MODE=0`
-- `TAG=rc1`
- `CAMERA_STREAM=camera_to_workload.json`
- `WORKLOAD_DIST=workload_to_pipeline.json`
- `PIPELINE_COUNT=1`
@@ -46,7 +44,6 @@ You can override these values through the following Environment Variables. |`WORKLOAD_DIST` | to define how each workload is assigned to a specific processing unit (CPU, GPU, NPU) | workload_to_pipeline_cpu.json, workload_to_pipeline_gpu.json, workload_to_pipeline_gpu-npu.json, workload_to_pipeline_hetero.json, workload_to_pipeline.json | |`CAMERA_STREAM` | to define camera settings and their associated workloads for the pipeline | camera_to_workload.json, camera_to_workload_full.json | |`REGISTRY` | option to pull the pre-built images rather than creating them locally | false, true | -|`TAG` | tag for the images pulled | rc1 | > **Note:** > Higher the `PIPELINE_COUNT`, higher the stress on the system.