Is there possible to train own data-set in Tensor-flow and then detect bounding boxes objects in OpenCV?

asked 2018-01-08 02:13:06 -0500

BAHRAMUDIN ADIL gravatar image

updated 2018-01-08 07:29:47 -0500

dkurt gravatar image

I am trying to train my own dataset (e.g: dog, cat) using Tensorflow and then using OpenCV for to detect those objects in bounding boxes, I have trained the dataset by using this tutorial, but I am not able to use the trained model in OpenCV. But when I am using the command line, it is working well, but the problem is it just says that this Cat or Dog, and not say quantity and the position in the image.

edit retag flag offensive close merge delete


@dkurt can surely answer to that!

StevenPuttemans gravatar imageStevenPuttemans ( 2018-01-08 03:29:51 -0500 )edit

@StevenPuttemans, thanks for tagging! @BAHRAMUDIN ADIL, it'd be much easier to have a model reference for reproduction.

dkurt gravatar imagedkurt ( 2018-01-08 07:29:29 -0500 )edit