Go to documentation repository
Page History
Starting from DetectorPack 3.9, a utility was added to the Neuro Pack add-ons (see Installing DetectorPack addons), which allows you to create GPU network caches without using Axxon Next. The presence of the cache speeds up the initialization and optimizes video memory consumption.
To optimize the operation of the neural analytics on GPUTo create GPU network caches using the utility, do the following:
Stop the Server (see Shutting down a Server).
Note title Attention! If the system has the software running on GPU, it is necessary to stop its operation.
Create the GPU_CACHE_DIR system variable (see
Configuring the acceleration of GPU-based neuroanalytics)Appendix 10. Creating system variable) by specifying in the Variable value field the path to the cache location with an arbitrary folder name. For example, D:\AN_GPU_cache. The specified directory will store the cache for all used detection tools and neural networks.
To call the utility, open in the command line: C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroPackGpuCacheGenerator.exe and and press Enter.
- Specify the ID of the required NVIDIA GPU GPU (see General Information on Configuring Detection) and press Enter.
Creation of GPU network caches using the utility Optimizing the operation of the neural analytics on GPU is complete. The utility will create the caches of four networks included in the Neuro Pack add-ons:
- GeneralNMHuman_v1.0GPU_onnx.ann—human;
- smokeScanned_v1_onnx.ann—smoke detection;
- fireScanned_v1_onnx.ann—fire detection;
- reid_15_0_256__osnetfpn_segmentation_noise_20_common_29_onnx.ann—search for the similar in the Neural Tracker (see Image Search).
...
Note | ||
---|---|---|
| ||
If you update the Neuro Pack add-ons (see Installing DetectorPack addons) or change the NVIDIA GPU model, the cache must be recreated |
...
. |
Creating GPU network caches using registry keysparameters:
-p is a key parameter to create a cache for a particular network.
Command example:Code Block C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroPackGpuCacheGenerator.exe -p "<System disk>\<Network location directory>\Network_name.ann"
To create a cache for multiple networks, list the paths to the selected networks, separated by a space.
Command example:Code Block C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroPackGpuCacheGenerator.exe -p "<System disk>\<Network location directory>\Network_name.ann" "C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroSDK\WaterLevelRuleNet_origin_onnx.ann"
-v is a key parameter to output the procedure log to the console during cache generation.
Command example to automatically create caches of four networks included in the Neuro Pack add-ons with log output:Code Block C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroPackGpuCacheGenerator.exe -v
Command example:
Code Block C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroPackGpuCacheGenerator.exe -p "<System disk>\<Network location directory>\Network_name.ann" -v
--int8=1 is a key parameter to create a quantized version of the cache for those networks for which quantization is available. By default, the --int8=0 key parameter is disabled.
Command example:Code Block C:\Program Files\Common Files\AxxonSoft\DetectorPack\NeuroPackGpuCacheGenerator.exe --int8=1
Note title Attention! The networks for which the quantization mode is available are included in the Neuro Pack add-ons together with the *.info file.
The networks for which the quantization mode is available:
- GeneralNMCar_v1.0GPU_onnx.ann—vehicles.
- GeneralNMHuman_v1.0GPU_onnx.ann—human.
- GeneralNMHumanTopView_v0.8GPU_onnx.ann—human, top view.