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

Tuesday, July 7, 2020

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

Join GitHub today

GitHub is home to over 50 million developers working together to host and review code, manage projects, and build software together.

Files

Permalink

Failed to load latest commit information.

Type

Name

Latest commit message

Commit time

待办

MobileNetv2-YOLOv3-SPP Darknet

A darknet implementation of MobileNetv2-YOLOv3-SPP detection network

*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

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😎
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

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😎
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

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

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

Thanks

About

MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops500KB🔥🔥🔥

Topics

Resources

License

You can’t perform that action at this time.

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session.

from Hacker News https://ift.tt/2ZPt9mq

SymmetricalDataSecurity