Convert Torch7 models into Apple CoreML format.

Short tutorial

This tool helps convert Torch7 models into Apple CoreML format which can then be run on Apple devices.

Installation

pip install -U torch2coreml

In order to use this tool you need to have these installed:

Xcode 9
python 2.7

If you want to run tests, you need MacOS High Sierra 10.13 installed.

Dependencies

coremltools (0.6.2+)
PyTorch

How to use

Using this library you can implement converter for your own model types. An example of such a converter is located at "example/fast-neural-style/convert-fast-neural-style.py". To implement converters you should use single function "convert" from torch2coreml:

from torch2coreml import convert

This function is simple enough to be self-describing:

def convert(model,            input_shapes,            input_names=['input'],            output_names=['output'],            mode=None,            image_input_names=[],            preprocessing_args={},            image_output_names=[],            deprocessing_args={},            class_labels=None,            predicted_feature_name='classLabel',            unknown_layer_converter_fn=None)

Parameters

model: Torch7 model (loaded with PyTorch) | str
A trained Torch7 model loaded in python using PyTorch or path to file with model (*.t7).

input_shapes: list of tuples Shapes of the input tensors.

mode: str ('classifier', 'regressor' or None)
Mode of the converted coreml model:
'classifier', a NeuralNetworkClassifier spec will be constructed.
'regressor', a NeuralNetworkRegressor spec will be constructed.

preprocessing_args: dict
'is_bgr', 'red_bias', 'green_bias', 'blue_bias', 'gray_bias', 'image_scale' keys with the same meaning as https://apple.github.io/coremltools/generated/coremltools.models.neural_network.html#coremltools.models.neural_network.NeuralNetworkBuilder.set_pre_processing_parameters

deprocessing_args: dict
Same as 'preprocessing_args' but for deprocessing.

class_labels: A string or list of strings.
As a string it represents the name of the file which contains the classification labels (one per line). As a list of strings it represents a list of categories that map the index of the output of a neural network to labels in a classifier.

predicted_feature_name: str
Name of the output feature for the class labels exposed in the Core ML model (applies to classifiers only). Defaults to 'classLabel'

unknown_layer_converter_fn: function with signature:
(builder, name, layer, input_names, output_names)
builder: object - instance of NeuralNetworkBuilder class
name: str - generated layer name
layer: object - PyTorch (python) object for corresponding layer
input_names: list of strings
output_names: list of strings
Returns: list of strings for layer output names
Callback function to handle unknown for torch2coreml layers