Core ML Beta 5 Release Notes

Question

(including Beta 4 changes)
Neural Networks:

Additional neural network layers: linear option in upsampling, reduction with axis mode, slice, spaces to depth, depth to spaces
Separate preprocessing (channel bias and mean image subtraction) for multiple input images is now fully supported

API:

New API to optionally constrain computation to use the CPU only: see MLModel.prediction(from:options:)
New API to compile models on device: see MLModel.compileModel(at: )
Additional API to query for details about the model inputs and outputs: see Additional Feature Constraints in MLFeatureDescription documentation

Model Validation:

The model compiler (and Xcode viewer) now requires validated models with all type information filled in.
You may see errors in Xcode or from the compiler with statements such as:
"validator error: Description of multiarray feature '__feature_vector__' has invalid or unspecified dataType. It must be specified as DOUBLE, FLOAT32 or INT32"
If you see this or a similar validation error you must update your model. You can do this by either
- Re-converting the model from its source using the latest coremltools 0.5.1
- Try running the following on the macOS 10.13 command line:
  xcrun coremlcompiler repair <path/to/invalid.mlmodel>

Xcode:

Generated code now includes availability macros
Known Bug: Availability for macOS/OSX is incorrect (13.0 instead of 10.13). This will be fixed in an upcoming release

Fixes:

Removed memory leaks when a model outputs an image.
Removed memory leaks in SVM models.
Fixes to allow the use of pipeline classifiers where the class labels were integers.
Fixes to input and output layer selection in neural networks.
Float32 input and output MLMultiArrays for Neural Networks now fully supported

Coremltools - 0.5.1

The new permanent home for the documentation is https://apple.github.io/coremltools/. The old documentation links on PyPI have been removed.
Keras 2 converter now supports dilated convolution, depth-wise and separable convolution.
Keras 1.2 converter now supports atrous convolution.
Image outputs now supported in the Python bindings for model prediction.
Fixes to the 'add' operator in the neural network builder.

Core ML

3k

Posted by

Frameworks Engineer

Reply

Add a Comment

Answer 1

How can I convert the model so that the input output MLMultiArray would accept Float32 data type?

Currently, the mlmodel only accepts double data type.

Posted by

Guohui Wang

Add a Comment

Answer 2

coremltools defaults to using Double as the dataType for MLMultiArrays.

You can manually change this for neural networks after the conversion is done by modifying the feature descriptions in the resulting spec or .mlmodel file.

For example, here is a script that takes a path to a .mlmodel file, sets any multidimensional array input and output features to have dataType be Float32, and then saves the result to a supplied output model path.

import coremltools
import sys

def update_multiarray_to_float32(feature):
    if feature.type.HasField('multiArrayType'):
        import coremltools.proto.FeatureTypes_pb2 as _ft
        feature.type.multiArrayType.dataType = _ft.ArrayFeatureType.FLOAT32

if __name__ == "__main__":
    if len(sys.argv) != 3:
        print "USAGE: %s <input_model_path> <output_model_path>" % sys.argv[0]
        sys.exit(1)

    input_model_path = sys.argv[1]
    output_model_path = sys.argv[2]

    spec = coremltools.utils.load_spec(input_model_path)

    for input_feature in spec.description.input:
        update_multiarray_to_float32(input_feature)

    for output_feature in spec.description.output:
        update_multiarray_to_float32(output_feature)

    coremltools.utils.save_spec(spec, output_model_path)

Posted by

Frameworks Engineer

Add a Comment

Core ML Beta 5 Release Notes

Replies