Page History

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 from Starting with DetectorPack 3.9, a utility was added to the Neuro Pack add-ons (see see Installing DetectorPack addonsadd-ons), which allows you to create GPU neural network caches without using 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 GPUTo create GPU network caches using the utility, do the following:

1. Stop the

Server

2. server (see

Shutting down a Server).

3. Stop the server).
   

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

4. 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.
Create the

5. Create the 

6. GPU_CACHE_DIR system variable (

see Configuring the acceleration of GPU-based neuroanalytics)

7. 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.
   

8. Run the command prompt as administrator.

9. To call the utility,

open

10. in the command

line: C

11. prompt, enter C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroPackGpuCacheGenerator.exe

and press

12. .

13. Press Enter.

14. Specify the
required NVIDIA GPU and press
15. ID of the required Nvidia GPU (see Selecting Nvidia GPU when configuring detectors).
16. Press Enter.

Creation of GPU network caches using the utility 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
—human
• (or GeneralNMHuman_v1.0_onnx.ann, starting with Detector Pack 3.16)—person;
• smokeScanned_v1_onnx
.ann—smoke
• .ann (or bestSmoke_v1.ann starting with Detector Pack 3.14)—smoke detection;
• fireScanned_v1_onnx
.ann—fire
• .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
• ann—search for the similar in the Neural
Tracker
• tracker (see
Image Search
• Similitude search).
  
Image Removed

...

...

Creating GPU neural network caches using

...

parameters

1. -p is a

key

2. parameter to create a cache for a particular neural network.
   Command example:
   

   Code Block
   C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroPackGpuCacheGenerator.exe -p "<System disk>\

<Network

3. <Neural network location directory>\

Network

4. Neural_network_name.ann"

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

Command example

5. Example of a command:

   Code Block
   C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroPackGpuCacheGenerator.exe -p "<System disk>\

<Network

6. <Neural network location directory>\

Network

7. Neural_network_name.ann" "C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroSDK\WaterLevelRuleNet_origin_onnx.ann"

8. -v is a

key

9. parameter to output the procedure log to the console during cache generation.
   

Command example

10. Example of a command to automatically create caches of four neural networks included in the Neuro Pack add-ons with log output:
    

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

Command example

11. Example of a command:
    

    Code Block
    C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroPackGpuCacheGenerator.exe -p "<System disk>\

<Network

12. <Neural network location directory>\

Network

13. Neural_network_name.ann" -v

14. --int8=1 is a

key

15. parameter to create a

quantized version of the

16. 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

key

17. parameter is disabled.
    

Command example

18. Example of a command:
    

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

Note
title Attention!
The networks for which the quantization mode is available are included in the Neuro Pack add-ons together with the *.info file.

The
19. -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:
    

    Code Block
    language shell
    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).