yolov2移植到android,MobileNetv2-Yolov3-Nano: MobileNetV2-YOLOv3-Nano的Darknet实现：移动终端设计的目标检测网络，计算量0.5BFlo...
2021.2.6 此项目不再更新，新项目地址: Yolo-Fastest： Faster and stronger https://github.com/dog-qiuqiu/Yolo-Fastest
此表中NCNN基准未更新最新ARM82数据，最新版本NCNN理论上ARM82会有一倍速度提升，待更新...
***Darknet Group convolution is not well supported on some GPUs such as NVIDIA PASCAL!!!
针对某些Pascal显卡例如1080ti在darknet上 训练失败/训练异常缓慢/推理速度异常 的可以采用Pytorch版yolo3框架 训练/推理
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
73.26
37.44
320
28.42 ms
18 ms
1.8BFlops
8.0MB
65.27
30.13
320
10.16 ms
5 ms
0.5BFlops
3.0MB
70.7
&
352
32.15 ms
& ms
2.44BFlops
14.4MB
72.7
&
300
26.37 ms
& ms
& BFlops
23.1MB
&
56.2
416
150.5 ms
& ms
13.2BFlops
28.1MB
&
33.1
416
36.6 ms
& ms
3.5BFlops
18.8MB
&
40.2
416
44.6 ms
& ms
6.9BFlops
23.1MB
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
Application
Ultralight-SimplePose
A ultra-lightweight human body posture key point prediction model designed for mobile devices, which can cooperate with MobileNetV2-YOLOv3-Nano to complete the human body posture estimation task
YoloFace-500k: 500kb 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
320x256
5.5ms
2.4ms
0.1BFlops
0.52MB
352x288
4.7ms
&ms
0.1BFlops
0.42MB
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-v2：The SE&CSP module is added
V2 does not support MNN temporarily
wider_face_val(ap05): yoloface-500k: 53.75 yoloface-500k-v2: 56.69
YoloFace-500k Test results(thresh 0.7)
YoloFace-500k-v2 Test results(thresh 0.7)
YoloFace-50k: Sub-millisecond face detection model
Network
Resolution
Inference time (NCNN/Kirin 990)
Inference time (MNN arm82/Kirin 990)
Inference time (DarkNet/R3-3100)
FLOPS
Weight size
56x56
0.27ms
0.31ms
0.5 ms
0.001BFlops
46kb
For the close-range face detection model in a specific scene, the recommended detection distance is 1.5m
YoloFace-50k Test results(thresh 0.7)
YoloFace50k-landmark106(Ultra lightweight 106 point face-landmark model)
Network
Resolution
Inference time (NCNN/Kirin 990)
Inference time (MNN arm82/Kirin 990)
Weight size
112x112
0.6ms
0.5ms
1.4MB
Face detection: yoloface-50k Landmark: landmark106
YoloFace50k-landmark106 Test results
Reference&Framework instructions&How to Train
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
NCNN conversion tutorial
NCNN C++ Sample
NCNN Android Sample
DarkNet2Caffe tutorial
Environmental requirements
Python2.7
python-opencv
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
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
}
}
Thanks