The .tflite and .txt files generated for Image classification via Google Firebase ML kit(https://developers.google.com/ml-kit) - when replaced into the Tensorflow image classification iOS sample (https://github.com/tensorflow/examples/tree/master/lite/examples/image_classification), it is identifying the images with very low accuracy and the match % is mostly below 30%.
The same .tflite and .txt files - when integrated into the Android sample code of the same Tensorflow image classification sample, it works perfectly with very high accuracy like 99%.
Any help in pointing towards a solution worth looking for would be great at this point.
I have been reading about Quantization - and Android sample has options to provide both quantized and non-quantized models (but non-quantized crashes for me for some reason). Not sure if it has anything to do with this.
If it helps, here is a link to my TFLite file generated through Google ML Kit : https://drive.google.com/file/d/1WXdjGGyj2RQbSLTniQ60o0ZYb6nqlaUw/view?usp=sharing