How to use a TensorFlow Lite Model trained using Microsoft Custom Vision with Tensorflow Task Library

Question

Im trying to use a TensorFlow Lite Model I trained using Microsoft Custom Vision with Tensorflow Task Library to run object detection inference on an Android app. However when I try run the model I get this error:

"Error occurred when initializing ObjectDetector: Mobile SSD models are expected to have exactly 4 outputs, found 3"

Ive inspected the model and compared it to models I have created using TFLite_model_maker and the custom vision model has 3 outputs compared to the 4 that the TFLite_model_maker has. The custom vision model has 'number of detections' missing.

Is there a way I can add the extra output to the custom vision model?

Or is there any other way anyone can recommend getting this to work?