Optimizing the operation of the Face detector TV on GPU in Windows OS

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 presence of the cache speeds up the initialization, optimizes video memory consumption and ensures the start and correct operation of the Face detector TV on GPU.

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

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

   Attention!

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

2. Create the GPU_CACHE_DIR system variable (see Appendix 9. Creating system variable). In the Variable value field, 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 detectors and neural networks.
   

3. Run the command line as administrator.

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

5. Press Enter.

6. Specify the ID of the required GPU (see Selecting Nvidia GPU when configuring detectors).

7. Press Enter.
   

8. If you want to change the resolution of the video stream for the Face detector TV: 

   1. Enter y.

   2. Specify the required resolution. 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. 
      

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

10. Press Enter. The cache creation process starts. The cache creation is successful if the result value is "0".
    

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