Go to documentation repository
Page History
| Tip |
|---|
The VA 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 detector VA on the GPU.
| Note | ||
|---|---|---|
| ||
You must recreate the cache when:
|
To optimize the operation of the Face detector VA on GPU, do the following:
Stop the server (see
Stopping Note title Attention! If the system
has uses the software that is running on the GPU,
it is necessary to you must stop its operation.
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.
- Run the command line as administrator .To call the utility, enter in the command line: C:\Program Files\Common Files\AxxonSoft\DetectorPack\VaFaceGpuCacheGenerator.exe
- .
Starting with Detector Pack 3.14
, if necessary, you can enter a query :
Call the utility, specifying the required
resolution of the video stream resolutions in the XxX or
[XxX ...] format, for example:XxX XxX format via the -r key. In this case you must not further specify the video stream resolution.
Example:Code Block language shell
codeC:\Program Files\Common Files\AxxonSoft\DetectorPack\VaFaceGpuCacheGenerator.exe -r
3840×21603840x2160
2688×1520In this case, 2688x1520If you don't
need to specify further the resolution of the video stream.specify the resolution explicitly, the utility uses the default 1920x1080 resolution for creating the cache.
Info title Note To get help information, you can enter
a the query in the command line:
Code Block C:\Program Files\Common Files\AxxonSoft\DetectorPack\VaFaceGpuCacheGenerator.exe --helpPress Enter.
Specify the ID of the required GPU (see Selecting Nvidia GPU when configuring detectors).
Press Enter. As a result, the process of creating the cache starts. If you get the "0" value, it means that the cache is created successfully.
- For Detector Pack 3.13 and older:
- In the command line, enter the C:\Program Files\Common Files\AxxonSoft\DetectorPack\VaFaceGpuCacheGenerator.exe query to call the utility.
Press Enter.
Specify the ID of the required GPU (see Selecting Nvidia GPU when configuring detectors).
Press Enter.
If you want to change the resolution of the video stream
for the Face detector VA :
Enter y.- Enter y. If you don't want to change the resolution of the video stream, enter n.
Specify the required resolution. For example,
3840×2160 2688×15203840x2160 2688x1520. The GPU uses the
default default 1920x1080 video stream
resolutionsresolution.
Changing If you change the resolution of the video stream from
1920*1080 1920x1080 and higher, it increases the percentage of face detection
..
Press Enter.
The cache creation process starts. The cache creation is successful if the result value is "0"As a result, the process of creating the cache starts. If you get the 0 value, it means that the cache is created successfully.
If you don't want to change the resolution of the video stream for the Face detector VA, enter n
The cache must be recreated in the following cases:
...
Optimizing the operation of the Face detector VA on the GPU is complete.
...
| title | Attention! |
|---|
.