def test_gru_converter(self):
input_dim = (1, 8)
output_dim = (1, 2)
inputs = [('input', datatypes.Array(*input_dim))]
outputs = [('output', datatypes.Array(*output_dim))]
builder = NeuralNetworkBuilder(inputs, outputs)
W_h = [
numpy.random.rand(2, 2),
numpy.random.rand(2, 2),
numpy.random.rand(2, 2)
]
W_x = [
numpy.random.rand(2, 8),
numpy.random.rand(2, 8),
numpy.random.rand(2, 8)
]
b = [
numpy.random.rand(2, 1),
numpy.random.rand(2, 1),
numpy.random.rand(2, 1)
]
builder.add_gru(name='GRU',
W_h=W_h,
W_x=W_x,
b=b,
hidden_size=2,
input_size=8,
input_names=['input'],
output_names=['output'],
activation='TANH',
inner_activation='SIGMOID_HARD',
output_all=False,
reverse_input=False)
model_onnx = convert_coreml(builder.spec)
self.assertTrue(model_onnx is not None)
def test_gru_converter(self):
input_dim = (1, 8)
output_dim = (1, 2)
inputs = [('input', datatypes.Array(*input_dim))]
outputs = [('output', datatypes.Array(*output_dim))]
builder = NeuralNetworkBuilder(inputs, outputs)
W_h = [
numpy.random.rand(2, 2),
numpy.random.rand(2, 2),
numpy.random.rand(2, 2)
]
W_x = [
numpy.random.rand(2, 8),
numpy.random.rand(2, 8),
numpy.random.rand(2, 8)
]
b = [
numpy.random.rand(2, 1),
numpy.random.rand(2, 1),
numpy.random.rand(2, 1)
]
builder.add_gru(name='GRU',
W_h=W_h,
W_x=W_x,
b=b,
hidden_size=2,
input_size=8,
input_names=['input'],
output_names=['output'],
activation='TANH',
inner_activation='SIGMOID_HARD',
output_all=False,
reverse_input=False)
context = ConvertContext()
node = GRULayerConverter.convert(context,
builder.spec.neuralNetwork.layers[0],
['input', 'h_init'], ['output', 'h'])
self.assertTrue(node is not None)
