OpenCV Zoo and Benchmark
A zoo for models tuned for OpenCV DNN with benchmarks on different platforms.
- Install latest
python3 -m pip install opencv-python # Or upgrade to latest version python3 -m pip install --upgrade opencv-python
- Clone this repo to download all models and demo scripts:
# Install git-lfs from https://git-lfs.github.com/ git clone https://github.com/opencv/opencv_zoo && cd opencv_zoo git lfs install git lfs pull
- To run benchmarks on your hardware settings, please refer to benchmark/README.
Models & Benchmark Results
CPU-INTEL: Intel Core i7-12700K, 8 Performance-cores (3.60 GHz, turbo up to 4.90 GHz), 4 Efficient-cores (2.70 GHz, turbo up to 3.80 GHz), 20 threads.
CPU-RPI: Raspberry Pi 4B, Broadcom BCM2711, Quad core Cortex-A72 (ARM v8) 64-bit SoC @ 1.5 GHz.
CPU-RV1126: Toybrick RV1126, Rockchip RV1126 SoC with a quard-core ARM Cortex-A7 CPU and a 2.0TOPs NPU.
CPU-KVE2: Khadas Edge 2, Rockchip RK3588S SoC with a CPU of 2.25GHz Quad Core ARM Cortex-A76 + 1.8GHz Quad Core Cortex-A55, and a 6TOPS NPU.
CPU-HSX3: Horizon Sunrise X3, an SoC from Horizon Robotics with a quad-core ARM Cortex-A53 1.2GHz CPU and a 5TOPS BPU (a.k.a NPU).
CPU-AXP: MAIX-III AXera-Pi, Axera AX620A with a quad-core ARM Cortex-A7 CPU and a 3.6TOPS@int8 NPU.
GPU-JETSON: NVIDIA Jetson Nano B01, 128-core NVIDIA Maxwell GPU.
NPU-KV3: Khadas VIM3, 5TOPS Performance. Benchmarks are done using quantized models. You will need to compile OpenCV with TIM-VX following this guide to run benchmarks. The test results use the
per-tensorquantization model by default.
NPU-Ascend310: Ascend 310, 22 TOPS @ INT8. Benchmarks are done on Atlas 200 DK AI Developer Kit. Get the latest OpenCV source code and build following this guide to enable CANN backend.
CPU-D1: Allwinner D1, Xuantie C906 CPU (RISC-V, RVV 0.7.1) @ 1.0 GHz, 1 core. YuNet is supported for now. Visit here for more details.
- The data under each column of hardware setups on the above table represents the elapsed time of an inference (preprocess, forward and postprocess).
- The time data is the mean of 10 runs after some warmup runs. Different metrics may be applied to some specific models.
- Batch size is 1 for all benchmark results.
---represents the model is not availble to run on the device.
- View benchmark/config for more details on benchmarking different models.
Some examples are listed below. You can find more in the directory of each model!
OpenCV Zoo is licensed under the Apache 2.0 license. Please refer to licenses of different models.