Page History

General information

It can take several minutes to launch neural analytics algorithms on NVIDIA GPU after Server restart. Meanwhile, 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 3.11, 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 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 Starting and stopping the Axxon One Server in Linux OS).
   

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

2. Login as

root

3. ngp superuser:

   1. In the command prompt, run the command:

      Code Block
      language bash
      sudo

-i

4. 1. su ngp

   2. Enter the password for the root superuser.

5. Create a folder with a custom name to store the cache. For example:

   Code Block
   language bash
   mkdir /opt/AxxonSoft/AxxonOne/gpucache

6. Change folder permissions:

   Code Block
   language bash
   chmod -R 777 /opt/AxxonSoft/AxxonOne/gpucache

7. Create the GPU_CACHE

system

8. _DIR system variable:

   1. Go to the /opt/AxxonSoft/AxxonOne/ folder:

      Code Block
      language bash
      cd /opt/AxxonSoft/AxxonOne

   2. Open the instance.conf file for editing:

      Code Block
      language bash
      nano instance.conf

   3. Add the following line to the file:

      Code Block
      language bash
      export GPU_CACHE_DIR="/opt/AxxonSoft/AxxonOne/gpucache"

   4. Save the file using the Ctrl+O keyboard shortcut.

   5. Exit file editing mode using the Ctrl+X keyboard shortcut.

   6. Run the following command in the terminal:

      Code Block
      language bash
      export GPU_CACHE_DIR="/opt/AxxonSoft/AxxonOne/gpucache"

9. Go to the /opt/AxxonSoft/DetectorPack/ folder:

   Code Block
   language bash
   cd /opt/AxxonSoft/DetectorPack

10. Run the following command:

    Code Block
    language bash
    ./NeuroPackGpuCacheGenerator

    Note
    title Attention!
    If more than one NVIDIA GPU is available, you will be able to select one. To do this, specify a number from 0 to 3 which corresponds to the required device in the list.

Optimizing the operation of the neural analytics on 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—person;
• smokeScanned_v1_onnx.
ann—smoke
• ann—smoke detection;
• fireScanned_v1_onnx.
ann—fire
• ann—fire detection;
• reid_15_0_256__osnetfpn_segmentation_noise_20_common_29_onnx.
ann—search
• ann—search for the similar in the neurotracker (see Image search).
  

Creating GPU neural network caches using parameters

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

   Code Block
   ./NeuroPackGpuCacheGenerator -p /opt/AxxonSoft/DetectorPack/NeuroSDK/GeneralNMHumanAndVehicle_Nano_v1.0_GPU_onnx.ann

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

   Code Block
   ./NeuroPackGpuCacheGenerator -v

3. --int8=1 is a parameter to create a quantized version of the cache for those neural networks for which quantization is available. By default, the --int8=0 parameter is disabled.
   Command example:
   

   Code Block
   ./NeuroPackGpuCacheGenerator -p /opt/AxxonSoft/DetectorPack/NeuroSDK/GeneralNMHumanAndVehicle_Nano_v1.0_GPU_onnx.ann --int8=1

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

   
   

The neural networks for which the quantization mode is available (

...

see Neurotracker,

...

Stopped object detector, Neurocounter):

• GeneralNMCar_v1.0GPU_onnx.ann

...

• —Vehicle.
• GeneralNMHuman_v1.0GPU_onnx.ann—Person.
• GeneralNMHumanTopView_v0.8GPU_onnx.

...

• ann—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).