search

PINTO0309 / MobileNet-SSD-RealSense

[High Performance / MAX 30 FPS] RaspberryPi3(RaspberryPi/Raspbian Stretch) or Ubuntu + Multi Neural Compute Stick(NCS/NCS2) + RealSense D435(or USB Camera or PiCamera) + MobileNet-SSD(MobileNetSSD) + Background Multi-transparent(Simple multi-class segmentation) + FaceDetection + MultiGraph + MultiProcessing + MultiClustering
https://qiita.com/PINTO
MIT License
366 stars 127 forks source link

Could you make guide to make merge model of object detection and face detection #24

Open Qlinkcopter opened 5 years ago

Qlinkcopter commented 5 years ago

I'm in learning to use openvino and movidius1 your github example is great!!

And if you pleased, i would like to know how you merge object detection and face detection before convert to IR

Thank you

PINTO0309 commented 5 years ago

I have already released the program, so I do not know what you want to know. It only uses two different models. Also, merging is impossible. btw, OpenVINO and NCS1 can not be combined.

Qlinkwisp commented 5 years ago

may be i misunderstood

let's me explain more

i think mobilessd has 21 labels things from background to tvmonitor that can give 21 possible inference label answer

and you also can give answer of [background] and [face]

im not sure how to do this

Please point the way i can learn more

PINTO0309 commented 5 years ago

@Qlinkwisp Pascal VOC labels example

[Background]
Person
Car
Bicycle
Bus
Motorbike
Train
Aeroplane
Chair
Bottle
Dining Table
Potted Plant
TV/Monitor
Sofa
Bird
Cat
Cow
Dog
Horse
Sheep

If you want to generate a "Face" trained model, do learning with two labels as follows:

[Background]
Face

Or just carry out learning with 22 labels as shown below.

[Background]
Person
Car
Bicycle
Bus
Motorbike
Train
Aeroplane
Chair
Bottle
Dining Table
Potted Plant
TV/Monitor
Sofa
Bird
Cat
Cow
Dog
Horse
Sheep
Face
Qlinkwisp commented 5 years ago

Thank you