3

I am using Microsoft custom vision service in object detection to extract the wanted objects. And I would like to make a regression test to compare the results. However, I cannot find a place to export the training picture with the bounding box that user defined by GUI.

The model training is done within the custom vision platform provided by Microsoft (https://www.customvision.ai/). Within this platform we can add the images and then tag the objects. I have tried to export the model, but I am not sure where to find the info of training pictures along with their tag(s) and bounding box(es).

I expect that in this platform, user can export the not only the trained model but also the training data (images with tags and bounding boxes.) But I was not able to find them.

Iris
  • 91
  • 6

2 Answers2

4

All the data that you are looking for is available through Custom Vision Training API. Currently the latest API is v3.0, its portal is here.

More in details, GetTaggedImages method will give you the associations of images and regions bounding box

Sample result of this method with one of my demos:

Demo

With these details, you will be able to get the image and place the boundingBox that was used for training.

Nicolas R
  • 13,812
  • 2
  • 28
  • 57
0

Please see the following link for export your model. Custom Vision Service exports compact domains. The models generated by compact domains are optimized for the constraints of real-time classification on mobile devices. If the user wants to export the user training data from the custom vision please see the following link.

Ram
  • 2,459
  • 1
  • 7
  • 14