Documentation for Axxon One 1.0.

Previous page Fine-tuning the Face detection tool  Configuring Face detection (VL) Next page

Cache affects the initialization speed-up and optimizes video memory consumption.

To optimize Face detection operation on GPU, do the following:

  1. Shut down the Server (see Shutting down a Server).

    Attention!

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

  2. Create the GPU_CACHE_DIR system variable (see Appendix 10. Creating system variable). Specify in the Variable value field the path to the cache location with an arbitrary folder name. For example, D:\AN_GPU_cache.

    Note

    The cache of all detection tools and neural networks will be stored in the specified directory.

  3. Run the command line as administrator.

  4. Open the C:\Program Files\Common Files\AxxonSoft\DetectorPack\TvaFaceGpuCacheGenerator.exe file (1) in the command line.

    Attention!

    TvaFaceGpuCacheGenerator.exe requires at least 1.4 GB of free video memory to run on GPU.


  5. Specify the ID of the required GPU (2, see General Information on Configuring Detection).

  6. If you want to change the resolution of the video stream for Face detection, you should enter y (3) and specify the required resolution (4).

    Note

    GPU uses the default video stream resolutions. Changing the resolution of the video stream will increase the percentage of face detection when using the resolutions from 1920*1080 and higher.

  7.  Press Enter. The cache creation process will start. It will take about 20 minutes. The cache creation was successful, if the result value is “0”. 

Optimization of Face detection on GPU is complete.

Attention!

When you update the add-on Face Recognition Pack (see Installing DetectorPack addons) or change the NVIDIA GPU model, you need to recreate the cache.

  • No labels