bourdakos1
commented
4 years ago If you are trying to create an object detection model, I recommend following this tutorial https://docs.annotations.ai/workshops/object-detection/
I think trimaps are used for image segmentation and regarding jpgs vs pngs, I believe the tensorflow object detection api only supports jpgs
I thought the point of having an images folder and an annotations folder was that that was all the required information for the network to train. But looking at step 6 of https://towardsdatascience.com/custom-object-detection-using-tensorflow-from-scratch-e61da2e10087
create_tf_record needs a trimaps folder as well. Also apparently create_tf_record is not compatible with jpg's? as it is only hardcoded to accept png's