Skip to content

CARS API Performance#

Test Server Configuration#

The efficiency of recognition of vehicle or LP attributes depends on the parameters of the input image:

  • Image size;
  • Number of bits per color.

Input data:

  • Image resolution for few vehicles (query /detector: cars): 1920×1080 px;
  • Image resolution for one vehicle (query /detector: grz): 500x439 px;
  • LP image resolution: 117x33 px;
  • Format of the original image: jpeg.

The test server parameters are shown in Table 31.

Table 31. Test Server Options

№ Resource Values
1 CPU Model name: Intel(R) Xeon(R) Gold 6240R CPU @ 2.40GHz, Thread(s) per core: 2, Core(s) per socket: 24
2 GPU Tesla T4
3 CPU frequency 2.40GHz
4 RAM 755Gb
5 Memory 240GB INTEL SSDSC2KB24
6 Video memory 16Gb
7 Operation system CentOS 8

CARS API performance measurements are presented for several architectures (Table 32).

Table 32. Tests

Name Description
AVX2 Running the CARS API on a server with a CPU with support for AVX2 instructions
GPU Running the CARS API on a server with GPU

The measured values are the average of at least 100 experiments.

All available CPU and GPU cores were used in the experiments to determine the attributes of vehicles and LPs, listed in the tables below.

Performance test results#

Testing was conducted using the following classifiers:

  • car_brand_model_v2;
  • vehicle_color;
  • vehicle_type;
  • vehicle_emergency_type;
  • public_transport_type;
  • special_transport_type;
  • grz_all_countries;
  • vehicle_axles;
  • vehicle_descriptor_v2.

Request /classify for classifiers#

Table 33. Results

Parameter

AVX2

GPU

CPU usage (%)

24,03

7,79

CPU memory (Mb)

4713

5528

GPU usage (%)

94,75

GPU memory (Gb)

2,26

RPS (transactions/s)

21,09

31,93

Response time (ms)

484

322

Request /detector with the parameters cars and grz#

Table 34. Results

+--------------------------------------+----------+---------+
| Parameter                         | AVX2 | GPU |
+--------------------------------------+----------+---------+
| CPU usage (%)                        | 24,2     | 9,37    |
+--------------------------------------+----------+---------+
| CPU memory (Mb)                      | 5430     | 6218    |
+--------------------------------------+----------+---------+
| GPU usage (%)                        |          | 95,5    |
+--------------------------------------+----------+---------+
| GPU memory (Gb)                      |          | 2,62    |
+--------------------------------------+----------+---------+
| RPS (transactions/s)                 | 14,27    | 23,79   |
+--------------------------------------+----------+---------+
| Response time (ms) for requests: |          |         |
+--------------------------------------+----------+---------+
| /detector: cars                      | 375      | 217     |
+--------------------------------------+----------+---------+
| /detector: grz                       | 309,3    | 161     |
+--------------------------------------+----------+---------+
| /detector: classify                  | 561      | 322     |
+--------------------------------------+----------+---------+