Yoloface-500k:ultra-light real-time face detection model, 500kb

栏目: IT技术 · 发布时间: 4年前

内容简介:A darknet implementation of MobileNetv2-YOLOv3-SPP detection network*emmmm...这个懒得训练,mAP就凑合这样吧

待办

  • 开放andooid示例项目(求大佬)

MobileNetv2-YOLOv3-SPP Darknet

A darknet implementation of MobileNetv2-YOLOv3-SPP detection network

Network COCO mAP(0.5) Resolution FLOPS Weight size
MobileNetV2-YOLOv3-SPP 42.6 416 6.1BFlops 17.6MB
YOLOv4-Tiny 40.2 416 6.9BFlops 23.1MB

*emmmm...这个懒得训练,mAP就凑合这样吧

Darknet Group convolution is not well supported on some GPUs such as NVIDIA PASCAL!!! The MobileNetV2-YOLOv3-SPP inference time is 100ms at GTX1080ti, but RTX2080 inference time is 5ms!!!

MobileNetV2-YOLOv3-Lite&Nano Darknet

Mobile inference frameworks benchmark (4*ARM_CPU)

Network VOC mAP(0.5) COCO mAP(0.5) Resolution Inference time (NCNN/Kirin 990) Inference time (MNN arm82/Kirin 990) FLOPS Weight size
MobileNetV2-YOLOv3-Lite 72.61 36.57 320 31.58 ms 18 ms 1.8BFlops 8.0MB
MobileNetV2-YOLOv3-Nano 65.27 30.13 320 13 ms 5 ms 0.5BFlops 3.0MB
YOLOv3-Tiny-Prn & 33.1 416 36.6 ms & ms 3.5BFlops 18.8MB
YOLO-Nano 69.1 & 416 & ms & ms 4.57BFlops 4.0MB
  • Support mobile inference frameworks such as NCNN&MNN
  • The mnn benchmark only includes the forward inference time
  • The ncnn benchmark is the forward inference time + post-processing time(NMS...) of the convolution feature map.
  • Darknet Train Configuration: CUDA-version: 10010 (10020), cuDNN: 7.6.4,OpenCV version: 4 GPU:RTX2080ti

MobileNetV2-YOLOv3-Lite-COCO Test results

Yoloface-500k:ultra-light real-time face detection model, 500kb

MobileNetV2-YOLO-Fastest

Network Resolution VOC mAP(0.5) Inference time (DarkNet/i7-6700) Inference time (NCNN/Kirin 990) Inference time (MNN arm82/Kirin 990) FLOPS Weight size
MobileNetV2-YOLOv3-Fastest 320 46.55 26 ms 8.2 ms 2.4 ms 0.13BFlops 700KB
  • 都2.4ms了,要啥mAP :sunglasses:
  • Suitable for hardware with extremely tight computing resources
  • The mnn benchmark only includes the forward inference time
  • The ncnn benchmark is the forward inference time + post-processing time(NMS...) of the convolution feature map.
  • This model is recommended to do some simple single object detection suitable for simple application scenarios

MobileNetV2-YOLO-Fastest Test results

Yoloface-500k:ultra-light real-time face detection model, 500kb

500kb的yolo-Face-Detection

Network Resolution Inference time (NCNN/Kirin 990) Inference time (MNN arm82/Kirin 990) FLOPS Weight size
UltraFace-version-RFB 320x240 &ms 3.36ms 0.1BFlops 1.3MB
UltraFace-version-Slim 320x240 &ms 3.06ms 0.1BFlops 1.2MB
yoloface-500k 320x256 5.5ms 2.4ms 0.1BFlops 0.5MB
  • 都500k了,要啥mAP :sunglasses:
  • Inference time (DarkNet/i7-6700):13ms
  • The mnn benchmark only includes the forward inference time
  • The ncnn benchmark is the forward inference time + post-processing time(NMS...) of the convolution feature map.

Wider Face Val

Model Easy Set Medium Set Hard Set
libfacedetection v1(caffe) 0.65 0.5 0.233
libfacedetection v2(caffe) 0.714 0.585 0.306
Retinaface-Mobilenet-0.25 (Mxnet) 0.745 0.553 0.232
version-slim-320 0.77 0.671 0.395
version-RFB-320 0.787 0.698 0.438
yoloface-500k-320 0.728 0.682 0.431

YoloFace-500k Test results

Yoloface-500k:ultra-light real-time face detection model, 500kb

Reference&Framework instructions&How to Train

  • https://github.com/AlexeyAB/darknet
  • You must use a pre-trained model to train your own data set. You can make a pre-trained model based on the weights of COCO training in this project to initialize the network parameters
  • 交流qq群:1062122604

About model selection

  • MobileNetV2-YOLOv3-SPP: Nvidia Jeston, Intel Movidius, TensorRT,NPU,OPENVINO...High-performance embedded side
  • MobileNetV2-YOLOv3-Lite: High Performance ARM-CPU,Qualcomm Adreno GPU, ARM82...High-performance mobile
  • MobileNetV2-YOLOv3-NANO: ARM-CPU...Computing resources are limited
  • MobileNetV2-YOLOv3-Fastest: ....... Can you do personal face detection???It’s better than nothing

DarkNet2Caffe tutorial

Environmental requirements

  • Python2.7
  • python-opencv
  • Caffe(add upsample layer https://github.com/dog-qiuqiu/caffe )
  • You have to compile cpu version of caffe!!!
    cd darknet2caffe/
      python darknet2caffe.py MobileNetV2-YOLOv3-Nano-voc.cfg MobileNetV2-YOLOv3-Nano-voc.weights MobileNetV2-YOLOv3-Nano-voc.prototxt MobileNetV2-YOLOv3-Nano-voc.caffemodel
      cp MobileNetV2-YOLOv3-Nano-voc.prototxt sample
      cp MobileNetV2-YOLOv3-Nano-voc.caffemodel sample
      cd sample
      python detector.py

MNN conversion tutorial

  • Benchmark: https://www.yuque.com/mnn/cn/tool_benchmark
  • Convert darknet model to caffemodel through darknet2caffe
  • Manually replace the upsample layer in prototxt with the interp layer
  • Take the modification of MobileNetV2-YOLOv3-Nano-voc.prototxt as an example
#layer {
	#    bottom: "layer71-route"
	#    top: "layer72-upsample"
	#    name: "layer72-upsample"
	#    type: "Upsample"
	#    upsample_param {
	#        scale: 2
	#    }
	#}
	layer {
	    bottom: "layer71-route"
	    top: "layer72-upsample"
	    name: "layer72-upsample"
	    type: "Interp"
	    interp_param {
		height:20  #upsample h size
		width:20   #upsample w size
	    }
	}

NCNN conversion tutorial

NCNN Android Sample

  • 白嫖中....

Thanks


以上就是本文的全部内容,希望本文的内容对大家的学习或者工作能带来一定的帮助,也希望大家多多支持 码农网

查看所有标签

猜你喜欢:

本站部分资源来源于网络,本站转载出于传递更多信息之目的,版权归原作者或者来源机构所有,如转载稿涉及版权问题,请联系我们

区块链与人工智能:数字经济新时代

区块链与人工智能:数字经济新时代

高航、俞学劢、王毛路 / 电子工业出版社 / 2018-7-23 / 80

《区块链与人工智能》是畅销书《区块链与新经济:数字货币2.0时代》全新修订升级版。本书是市场上为数不多的系统阐述区块链、人工智能技术与产业的入门级系统教程。从比特币到各类数字货币(代币),从基础原理到应用探讨,全景式呈现区块链与人工智能的发展脉络,既有历史的厚重感也有科技的未来感。本书的另一个亮点是系统整理了区块链创业地图,是一本关于区块链创业、应用、媒体的学习指南,以太坊创始人Vitalik专门......一起来看看 《区块链与人工智能:数字经济新时代》 这本书的介绍吧!

在线进制转换器
在线进制转换器

各进制数互转换器

正则表达式在线测试
正则表达式在线测试

正则表达式在线测试

HSV CMYK 转换工具
HSV CMYK 转换工具

HSV CMYK互换工具