pip install mxnet-to-coreml
Currently supported
Layers
List of MXNet layers that can be converted into their CoreML equivalent:
- Activation
- Batchnorm
- Concat
- Convolution
- Deconvolution
- Dense
- Elementwise
- Flatten
- Pooling
- Reshape
- Softmax
- Transpose
mxnet_coreml_converter.py --model-prefix='resnet-50' --epoch=0 --input-shape='{"data":"3,224,224"}' --mode=classifier --pre-processing-arguments='{"image_input_names":"data"}' --class-labels synset.txt --output-file="resnet50.mlmodel"