Skip to main content
Version: 3.1.0 (latest)

System requirements

Hardware

Nvidia

Agent Configuration: 0.1 CPU cores, 0.4 GB RAM.

Per-thread consumption: 20–25 FPS for FP32 computation accuracy. All CPU consumption is calculated as the number of threads with hyperthreading.

NameCPURAMVRAMGPU (FP32)
Video Decompression0.2 threads (0.15 cores)
Face Identification1.1 threads (0.7 cores)1.3 GB+3 GB per 1 million faces0.25 Gb1.2 TFLOPs
Face Identification (CPU only)2.3 threads (1.6 cores)3.5 Gb+3 Gb for 1 million faces
Body Detection and Skeletal Tracking1.3 threads (0.9 cores)0.4 Gb0.3 Gb Cuda 0.2 Gb Tensor1.4 TFLOPs Cuda 1.0 TFLOP Tensor
Human Activity Recognition (HAR) is added to the body detector consumption.0.2 threads (0.13 cores)0.2 GB0.3 GB3.0 TFLOP Cuda 2.5 TFLOP Tensor
UAD new objects (700×700)1.9 threads (1.3 cores)1.9 GB1.8 GB3.8 TFLOP
Object Detection (phone, cigarettes, etc.)0.4 threads (0.3 cores)0.17 GB0.15 GB1.2 TFLOPs Cuda 0.8 TFLOPs Tensor
Driver/Operator Monitoring (DSM)1.0 threads (0.7 cores)1.0 GB1.4 GB3.1 TFLOPs

Desktop Test Machine Specifications (Nvidia)

  • OS: Ubuntu 20.04
  • CPU: AMD Ryzen 9 5950X @ 3.4Ghz: 16 cores (32 threads)
  • RAM: 118GB DDR4
  • VRAM: 11GB
  • Disk: 500GB Samsung SSD 870 (read 560 MB/s, write 530 MB/s)
  • GPU: NVIDIA GeForce GTX 1080 Ti 10.6 TFLOPS

NVIDIA GPU Comparison by FP32/FP16 Performance

Graphics CardVRAM SizeFP32 (single precision)FP16 (half precision)
GTX 1080 Ti11 GB GDDR5X11 TFLOPS0.2 TFLOPS
RTX 2080 Ti11 GB GDDR613 TFLOPS26 TFLOPS
RTX 3060 Ti8 GB GDDR616 TFLOPS32 TFLOPS
RTX 3080 Ti12 GB GDDR6X34 TFLOPS68 TFLOPS
RTX 407012 GB GDDR6X22 TFLOPS58 TFLOPS
RTX 409024 GB GDDR6X82 TFLOPS165 TFLOPS

Edge (Sophgo)

Agent Configuration: CPU 0.1 cores, RAM 0.4 GB

Thread Consumption – 20–25 FPS for FP16 computation accuracy.

NameCPURAMRAM NPUNPU (FP16)
Video Decompression0.3 Cores0.05 GB0.17 GB
Passenger Counting (APC)0.6 Cores0.05 GB0.20 GB1.5 TOPS
Driver Monitoring (DSM)1.3 cores0.10 GB0.25 GB2.3 TOPS
Body Detection and Skeletal Tracking1.4 cores0.10 GB0.05 GB1.6 TOPS
Human Activity Recognition (HAR) is added to the body detector consumption.0.8 cores0.02 GB0.02 GB4.5 TOPS
UAD new objects (700×700) (10 FPS)3.5 cores0.28 GB0.09 GB5.6 TFLOPs

Edge (Sophgo) test machine specifications

  • OS: Ubuntu 20.04
  • CPU: ARM Cortex-A53 @ 2.3 GHz: 8 cores
  • RAM: 8 GB LPDDR4x
  • VRAM: 8 GB LPDDR4x
  • Disk: 64 GB eMMC
  • NPU: 16 TFLOPS (FP16)
note

Sophgo support is available for a limited set of video analytics scenarios (without support for face recognition and phone detection). Acceleration on the integrated hardware accelerator is enabled by default; CUDA and TensorRT are not supported.

note

Calculate your server needs with the server capacity calculator.

Software

Supported OS: Windows 10+ (x86_64), Ubuntu 14+ (x86_64).

caution

For stable operation of OMNI Agent, hardware resources should not be loaded above 80%.

caution

If the database exceeds 50K persons, the agent’s working directory must be located on an SSD drive.

GPU requirements

System requirements

Linux / Windows:

  • GPU Driver >= 441.22

  • CUDA Toolkit 11.8

  • cuDNN v8.8.0 for CUDA 11.x

  • TensorRT 8.6 (optional)

Hardware requirements

  • GPU with CUDA support (from NVIDIA GTX 1050 Ti up to RTX 4090 inclusive, Compute Capability 3.5–9.0).