def test_batchnorm_converter(self):
input_dim = (3, )
output_dim = (3, )
input = [('input', datatypes.Array(*input_dim))]
output = [('output', datatypes.Array(*output_dim))]
builder = NeuralNetworkBuilder(input, output)
gamma = numpy.ndarray(shape=(3, ))
gamma[:] = [-1, 0, 1]
beta = numpy.ndarray(shape=(3, ))
beta[:] = [10, 20, 30]
mean = numpy.ndarray(shape=(3, ))
mean[:] = [0, 0, 0]
variance = numpy.ndarray(shape=(3, ))
variance[:] = [1, 1, 1]
builder.add_batchnorm(name='BatchNormalize',
channels=3,
gamma=gamma,
beta=beta,
mean=mean,
variance=variance,
input_name='input',
output_name='output')
context = ConvertContext()
node = BatchnormLayerConverter.convert(
context, builder.spec.neuralNetwork.layers[0], ['input'],
['output'])
self.assertTrue(node is not None)
def get_custom_model_spec():
from coremltools.models.neural_network import NeuralNetworkBuilder
from coremltools.models.datatypes import Array, Dictionary, String
input_name = 'output1'
input_length = self._feature_extractor.output_length
builder = NeuralNetworkBuilder(
[(input_name, Array(input_length, ))],
[(prob_name, Dictionary(String))], 'classifier')
ctx = _mxnet_utils.get_mxnet_context()[0]
input_name, output_name = input_name, 0
import mxnet as _mx
for i, cur_layer in enumerate(self._custom_classifier):
output_name = str(i)
if type(cur_layer) == _mx.gluon.nn.basic_layers.Dense:
W = cur_layer.weight.data(ctx).asnumpy()
nC, nB = W.shape
Wb = cur_layer.bias.data(ctx).asnumpy()
builder.add_inner_product(name='inner_product_' + str(i),
W=W,
b=Wb,
input_channels=nB,
output_channels=nC,
has_bias=True,
input_name=input_name,
output_name='inner_product_' +
output_name)
if cur_layer.act:
builder.add_activation("activation" + str(i), 'RELU',
'inner_product_' + output_name,
output_name)
elif type(cur_layer) == _mx.gluon.nn.basic_layers.BatchNorm:
zeros = _np.zeros(nC)
ones = _np.ones(nC)
builder.add_batchnorm(name='bn_layer_' + str(i),
channels=nC,
gamma=ones,
beta=zeros,
mean=zeros,
variance=ones,
input_name=input_name,
output_name=output_name)
elif type(cur_layer) == _mx.gluon.nn.basic_layers.Dropout:
continue
input_name = output_name
last_output = builder.spec.neuralNetworkClassifier.layers[
-1].output[0]
builder.add_softmax('softmax', last_output, self.target)
builder.set_class_labels(self.classes)
builder.set_input([input_name], [(input_length, )])
builder.set_output([self.target], [(self.num_classes, )])
return builder.spec
def test_batchnorm_converter(self):
input_dim = (3,)
output_dim = (3,)
input = [('input', datatypes.Array(*input_dim))]
output = [('output', datatypes.Array(*output_dim))]
builder = NeuralNetworkBuilder(input, output)
gamma = numpy.ndarray(shape=(3,))
gamma[:] = [-1, 0, 1]
beta = numpy.ndarray(shape=(3,))
beta[:] = [10, 20, 30]
mean = numpy.ndarray(shape=(3,))
mean[:] = [0, 0, 0]
variance = numpy.ndarray(shape=(3,))
variance[:] = [1, 1, 1]
builder.add_batchnorm(name='BatchNormalize', channels=3, gamma=gamma, beta=beta, mean=mean, variance=variance,
input_name='input', output_name='output')
model_onnx = convert_coreml(builder.spec)
self.assertTrue(model_onnx is not None)
