OpenCV Zoo and Benchmark

A zoo for models tuned for OpenCV DNN with benchmarks on different platforms.

Guidelines:

Install latest opencv-python:

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

Models & Benchmark Results

Model	Task	Input Size	CPU-INTEL (ms)	CPU-RPI (ms)	GPU-JETSON (ms)	NPU-KV3 (ms)	NPU-Ascend310 (ms)	CPU-D1 (ms)
YuNet	Face Detection	160x120	0.72	5.43	12.18	4.04	2.24	86.69
SFace	Face Recognition	112x112	6.04	78.83	24.88	46.25	2.66	---
FER	Facial Expression Recognition	112x112	3.16	32.53	31.07	29.80	2.19	---
LPD-YuNet	License Plate Detection	320x240	8.63	167.70	56.12	29.53	7.63	---
YOLOX	Object Detection	640x640	141.20	1805.87	388.95	420.98	28.59	---
NanoDet	Object Detection	416x416	66.03	225.10	64.94	116.64	20.62	---
DB-IC15 (EN)	Text Detection	640x480	71.03	1862.75	208.41	---	17.15	---
DB-TD500 (EN&CN)	Text Detection	640x480	72.31	1878.45	210.51	---	17.95	---
CRNN-EN	Text Recognition	100x32	20.16	278.11	196.15	125.30	---	---
CRNN-CN	Text Recognition	100x32	23.07	297.48	239.76	166.79	---	---
PP-ResNet	Image Classification	224x224	34.71	463.93	98.64	75.45	6.99	---
MobileNet-V1	Image Classification	224x224	5.90	72.33	33.18	145.66*	5.15	---
MobileNet-V2	Image Classification	224x224	5.97	66.56	31.92	146.31*	5.41	---
PP-HumanSeg	Human Segmentation	192x192	8.81	73.13	67.97	74.77	6.94	---
WeChatQRCode	QR Code Detection and Parsing	100x100	1.29	5.71	---	---	---	---
DaSiamRPN	Object Tracking	1280x720	29.05	712.94	76.82	---	---	---
YoutuReID	Person Re-Identification	128x256	30.39	625.56	90.07	44.61	5.58	---
MP-PalmDet	Palm Detection	192x192	6.29	86.83	83.20	33.81	5.17	---
MP-HandPose	Hand Pose Estimation	224x224	4.68	43.57	40.10	19.47	6.27	---

*: Models are quantized in per-channel mode, which run slower than per-tensor quantized models on NPU.

Hardware Setup:

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.
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-tensor quantization 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.

Important Notes:

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.

Name		Name	Last commit message	Last commit date
Latest commit History 91 Commits
benchmark		benchmark
models		models
tools		tools
.gitattributes		.gitattributes
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md