Open sandeep5193 opened 4 years ago
I guess you might be skipping the pre-processing steps before feeding the image to the tflite model because of which you're facing this issue.
I also ran into this issue. The list of postprocessing steps in image_utils.py is quite long. Has anybody gotten this to work with tflite?
I have been able to export it using tf 1.15. Using it in Firebase ML kit sample, score is always between 0.6-0.7, no matter what is fed into the network.
I have also used one shared in #19 but same results.
Can you share your tflite if possible for double-check?