died / yolo3-with-opencvsharp4 Goto Github PK

Hi
I try this guider , I got weight file.
https://github.com/AlexeyAB/darknet/wiki/Train-Classifier-on-ImageNet-(ILSVRC2012)
the cmd of darknet: to predict
./darknet classifier predict cfg/imagenet1k.data cfg/csdarknet53-omega.cfg backup/csdarknet53-omega_last.weights dog.jpg

How to implement code c# similar to 'classifier predict' it with opencvsharp
Tks in advance

Hello, I use the CPU recognition speed is 400ms, may I ask how to use GPU acceleration

Hi. thanks for the response and sorry for asking so many questions.
I am now trying this repository and I get the following error :
System.TypeInitializationException: 'The type initializer for 'OpenCvSharpYolo3.Program' threw an exception.'
Inner Exception:
DirectoryNotFoundException: Could not find a part of the path 'C:\Users\V\YOLO3-With-OpenCvSharp4\YOLO3-With-OpenCvSharp4\OpenCvSharpYolo3\bin\Content\coco.names'.

I checked and coco does exist in the file. I'm not sure if I'm missing something very obvious mistake.
thank you for your help and support.

I will be very grateful for your advice.

Sorry to ask such a question but do you think you can use this program with opencv for unity. I'm asking this because I have to run this application on a unity package.
Thanks for your help

Hey zhangyufei1995!

Thank you for sharing this, I really appreciate it and its save me huge amount of time, but how do we restrict on faces only? As I am working with face recognition and emgucv was a bit slow, so I'm looking for face detection using yolo and for facial recognition using opencvsharp is this possible? also real time face detection ?

Once again thank you very much for sharing

Best Regards

John

How can I convert C#code into VB.net code?

Hello, cvdnn.readnetfromdarknet doesn't support loading the Gaussian_yolov3 training model and the Gaussian_yolov3_bdd.cfg network

hi
hi “ net.Forward(outs, outNames); “ i run your code in video stream but very slow.
"net.Forward(outs, outNames); " 2 seconds per frame. Is there any way to speed it up?
thank you very much