Koan-Sin Tan

> @freedomtan for further improvements should we use the saved models from your repo (MobileBert, MobileDet)? Or we can use some models from the TensorFlow hub (At least for MobileBert...

> Hi guys! So I've converted the MobileBERT using the coreMLTools version 7, TensorFlow v 2.12 to the *.mlpackage format, as well, as optimised the model using quantization technique. Currently...

@RSMNYS Please check model performance with [Xcode Performance tab and/or Core ML Instruments](https://developer.apple.com/videos/play/wwdc2022/10027/) first. For performance benchmark, it's hard to ask people to believe that we have "improved" model which...

@RSMNYS please share your forked repo or one the .mlpackage model.

> @freedomtan here is the forked repo: https://github.com/RSMNYS/mobile_models/raw/main/v3_0/CoreML/MobileBERT.mlpackage.zip Let's check something basic. 1. Did you try to open the model you converted in Xcode and run it in the Performance...

@RSMNYS I meant "CPU and ANE". "GPU and ANE" is the reason why your model is slower. > @freedomtan here is my test with the converted model: > > Sometimes...

@freedomtan to post profiling results how old coreml model work on couple devices.

@RSMNYS with the MobileBERT.mlmodel here, https://github.com/freedomtan/coreml_models_for_mlperf/tree/main/mobilebert comparing my .mlmodel and your .mlpackage in the Instruments, you can see, as I said, GPU takes much longer time than CPU. With coremltools's...

@RSMNYS I dug a bit into it over the past weekend. Some information maybe useful. - We can check graphs of both .mlmodel and .mlpackage with [netron](https://github.com/lutzroeder/netron). - for .mlmodel:...

> @freedomtan I did some more testing with MobileBERT.mlpackage. I've set different precisions for the model: Float16, and Float32 and here are the results: > > FLOAT16 > > All...