Versions Compared

Old Version 1

changes.mady.by.user Alena Kniazeva

Saved on

compared with

New Version Current

changes.mady.by.user Alena Kniazeva

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.
Note
titleAttention!

Starting with with DetectorPack 3 3.11.1, the the Face Detection detector TV is  is no longer supported. We replaced it with the the Face Detection detector VA. You cannot use the the Face Detection TV and the Face Detection VA at detector TV and the Face detector VA at the same time (see see Manual for switching from the Face Detection detector TV to Face Detection detector VA).

Tip
Configuring the Face Detection detector TV

The TV Face Recognition Pack add-on   (see Installing DetectorPack add-ons) includes a utility that allows you to create GPU neural network caches without using Axxon One. The  The presence of the cache speeds up the initialization, optimizes video memory consumption and ensures the start and correct operation of the Face Detection detector TV on GPU.

To optimize the operation of the Face Detection detector TV on GPU, do the following:

  1. Stop the

    2. Server

  2. server (see

    3. Shutting down a Server

  3. Stopping the server).

    Note
    titleAttention!

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

  4. Create the GPU_CACHE_DIR system variable (see Appendix 9. Creating system variable)

    5. by specifying in

  5. . In the Variable value field

    6. the

  6. , specify the path to the cache location in Latin characters only. For example, D:\GPU_cache. The specified directory will store the cache for all used

    7. detection tools

  7. detectors and neural networks.

  8. Run the command line as administrator.

  9. To call the utility, enter in the command line: C:\Program Files\Common Files\AxxonSoft\DetectorPack\TvaFaceGpuCacheGenerator.exe

    10. (1)

  10. .

  11. Press Enter.

    12. Image Removed

  12. Specify the ID of the required GPU (

    13. 2, see 

  13. see Selecting Nvidia GPU when configuring

    14. detection tools

  14. detectors).

  15. Press Enter.

  16. If you want to change the resolution of the video stream for the Face

    17. Detection

  17. detector TV: 

    1. Enter y

    18. (3)

    1. .

    2. Specify the required resolution

    19. (4)

    1. . For example, 3840×2160 2688×1520. GPU uses the default video stream resolutions. Changing the resolution of the video stream from 1920*1080 and higher, increases the percentage of face detection. 


    20.  Press


  21. If you don't want to change the resolution of the video stream for the Face detector TV, enter n.

  22. Press Enter. The cache creation process starts. The cache creation is successful

    23. ,

  23. if the result value is "0".

Optimizing the operation of the Face Detection detector TV on GPU is complete.

Note
titleAttention!

The cache must be recreated in the following cases:

    if
  • if you update the TV Face Recognition Pack add-on (see
    •  
  • Installing DetectorPack add-ons),
  • if you change the
    • Nvidia GPU
  • Nvidia GPU model,
  • if you update the
    • Nvidia GPU
  • Nvidia GPU drivers.