Optimizing the operation of neural analytics on GPU in Windows OS

General information

It can take several minutes to launch neural analytics algorithms on NVIDIA GPU after server restart. At this time, the neural models are optimized for the current GPU type.

You can use the caching function to ensure that this operation is performed only once. Caching saves the optimization results on the hard drive and uses it for the subsequent analytics runs. 

Starting with DetectorPack 3.9, a utility was added to the Neuro Pack add-ons (see Installing DetectorPack add-ons), which allows you to create GPU neural network caches without using Axxon One. The presence of the cache speeds up the initialization and optimizes video memory consumption.

Optimizing the operation of neural analytics on GPU

To optimize the operation of the neural analytics on GPU, do the following:

1. Stop the server (see Stop the server).
   

   Attention!

   If the system has the software running on GPU, it is necessary to stop its operation.

2. In Windows OS, go to Settings → System → Display → Graphics Settings. Turn off the Hardware-accelerated GPU scheduling toggle. This option increases the load on the server.

3. Create the GPU_CACHE_DIR system variable (see Creating system variable) by specifying in the Variable value field the path to the cache location with an arbitrary folder name. For example, D:\GPU_cache. The specified directory will store the cache for all used detectors and neural networks.
   The cache size depends on the number of neural networks used and their type. The minimum size is 70 MB.
   

4. Run the command prompt as administrator.

5. To call the utility, in the command prompt, enter C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroPackGpuCacheGenerator.exe.

6. Press Enter.

7. Specify the ID of the required Nvidia GPU (see Selecting Nvidia GPU when configuring detectors).
8. Press Enter.

Optimizing the operation of the neural analytics on GPU is complete. The utility will create the caches of four neural networks included in the Neuro Pack add-ons:

• GeneralNMHuman_v1.0GPU_onnx.ann (or GeneralNMHuman_v1.0_onnx.ann, starting with Detector Pack 3.16)—person;
• smokeScanned_v1_onnx.ann (or bestSmoke_v1.ann starting with Detector Pack 3.14)—smoke detection;
• fireScanned_v1_onnx.ann (or bestFire_v1.ann starting with Detector Pack 3.14)—fire detection;
• reid_15_0_256__osnetfpn_segmentation_noise_20_common_29_onnx.ann—search for the similar in the Neural tracker (see Similitude search).
  

Creating GPU neural network caches using parameters

1. -p is a parameter to create a cache for a particular neural network.
   Command example:
   

   C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroPackGpuCacheGenerator.exe -p "<System disk>\<Neural network location directory>\Neural_network_name.ann"

   To create a cache for multiple neural networks, list the paths to the selected neural networks, separated by a space.
   Example of a command:

   C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroPackGpuCacheGenerator.exe -p "<System disk>\<Neural network location directory>\Neural_network_name.ann" "C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroSDK\WaterLevelRuleNet_origin_onnx.ann"

2. -v is a parameter to output the procedure log to the console during cache generation.
   Example of a command to automatically create caches of four neural networks included in the Neuro Pack add-ons with log output:
   

   C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroPackGpuCacheGenerator.exe -v

   Example of a command:
   

   C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroPackGpuCacheGenerator.exe -p "<System disk>\<Neural network location directory>\Neural_network_name.ann" -v

3. --int8=1 is a parameter to create a cache for those neural networks for which quantization is available. Neural networks for which the quantization mode is available are included in the Neuro Pack add-ons together with the *.info file. By default, the --int8=0 parameter is disabled.
   Example of a command:
   

   C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroPackGpuCacheGenerator.exe --int8=1

4. -f is a parameter to save logs of the caching procedure to files. It is available starting with DetectorPack 3.15. When you use the -v and -f parameters together, logs for each created cache are saved to: <Path to the cache folder created for the GPU_CACHE_DIR system variable>\caching-utility-log. A separate log file is created for each neural network. Log files created during previous runs of the utility are deleted.
   Example of a command for creating a cache with detailed logging to the console and saving logs to files:
   

   C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroPackGpuCacheGenerator.exe -v -f

The neural networks for which the quantization mode is available (see Neural tracker, Stopped object detector, Neural counter):

• GeneralNMCar_v1.0GPU_onnx.ann (or GeneralNMCar_v1.0_onnx.ann, starting with Detector Pack 3.16)—Vehicle.
• GeneralNMHuman_v1.0GPU_onnx.ann (or GeneralNMHuman_v1.0_onnx.ann, starting with Detector Pack 3.16)—Person.
• GeneralNMHumanTopView_v0.8GPU_onnx.ann (or GeneralNMHumanTopView_v0.8_onnx.ann, starting with Detector Pack 3.16)—Person (top-down view).

Starting with DetectorPack 3.11, the following neural networks were added:

• GeneralNMHumanAndVehicle_Nano_v1.0_GPU_onnx.ann—Person and vehicle (Nano).
• GeneralNMHumanAndVehicle_Medium_v1.0_GPU_onnx.ann—Person and vehicle (Medium).
• GeneralNMHumanAndVehicle_Large_v1.0_GPU_onnx.ann—Person and vehicle (Large).

Starting with DetectorPack 3.12, the following neural networks were added:

• GeneralNMHumanTopView_Nano_v1.0_GPU_onnx.ann—Person (top-down view Nano).
• GeneralNMHumanTopView_Medium_v1.0_GPU_onnx.ann—Person (top-down view Medium).
• GeneralNMHumanTopView_Large_v1.0_GPU_onnx.ann—Person (top-down view Large).