mxnet-coreml-converter 0.1.0a6

Tool to convert MXNet models into Apple CoreML model format.

This tool helps convert MXNet models into Apple CoreML format which can then be run on Apple devices. Find more information here.

Prerequisites

This package can only be installed on MacOS X since it relies on Apple’s CoreML SDK. This tool can be run on MacOS 10.12 or higher to convert the model though for running inferences on the converted model MacOS 10.13 or higher is needed (or for phones, iOS 11 or above).

Installation

To install:

pip install mxnet-coreml-converter

Sample Usage

In order to convert, say a Squeezenet model, with labels from synset.txt, execute this

mxnet_coreml_converter.py --model-prefix='squeezenet_v1.1' \
--epoch=0 --input-shape='{"data":"3,227,227"}' \
--mode=classifier --pre-processing-arguments='{"image_input_names":"data"}'\
--class-labels synset.txt --output-file="squeezenetv11.mlmodel"