Skip to content

Latest commit

 

History

History
22 lines (17 loc) · 952 Bytes

README.md

File metadata and controls

22 lines (17 loc) · 952 Bytes
Raw

Create-your-own-Object-detection-model-with-openCv-and-ImageAI

  1. create model with ImageAI
  2. use that model in openCv (WEBCAM)

In first phase,

     -: If data is not labeled then use "labelimg" and label your data(this step is very important, check video on youtube               how to do that)
     -: After label you data , you will have XML of all images
     -: create folder (annotations and images) [E.g, cardDetection-:(annotations,images)]
     -: put your Images in "images" folder and it's XML in "annotations" folder
     -: "pretrained-yolov3.h5" download this from internet
     -: check version of tensorflow
     -: now, set your path and run your script

phase two,

     -: after first phase, you will have many models
     -: download the latest one
     -: set path and load the model
     -: use that model into the OpenCv
     -: we have a result