quantization not working on newer versions of tflite

tensorflow / tflite-micro

Infrastructure to enable deployment of ML models to low-power resource-constrained embedded targets (including microcontrollers and digital signal processors).

Apache License 2.0

1.94k stars 831 forks source link

quantization not working on newer versions of tflite #2735

Open SuranjanKTH opened 1 month ago

SuranjanKTH commented 1 month ago

Hi,

I ran the hello world example quantization script and it seems to increase the model size. This does not occue with pete wardens original notebook. He uses tensorflow 2.0.0. Using the 2.18.0 in the current example cause the quantization to increase the model size. Can the code be modified to still quantize properly with newer version of tensorflowlite to the same level as pete wardens work?

github-actions[bot] commented 4 days ago

"This issue is being marked as stale due to inactivity. Remove label or comment to prevent closure in 5 days."