def _verify_reduce(input_dim, mode, axis, ref_func, dtype="float32"):
print(input_dim, mode, axis)
a_np = np.random.uniform(size=input_dim).astype(dtype)
# translate to axis from coreml format
if axis == ReduceAxis.CHW:
np_axis = (-3, -2, -1)
elif axis == ReduceAxis.HW:
np_axis = (-2, -1)
elif axis == ReduceAxis.C:
np_axis = -3
elif axis == ReduceAxis.H:
np_axis = -2
elif axis == ReduceAxis.W:
np_axis = -1
if ref_func == np.argmax:
ref_val = np.expand_dims(ref_func(a_np, np_axis), np_axis).astype(dtype)
else:
ref_val = ref_func(a_np, np_axis, keepdims=True)
inputs = [("input", datatypes.Array(*input_dim))]
output = [("output", datatypes.Array(*ref_val.shape))]
builder = NeuralNetworkBuilder(inputs, output)
builder.add_reduce(
name=mode, input_name="input", output_name="output", axis=axis.name, mode=mode
)
model = cm.models.MLModel(builder.spec)
for target, dev in tvm.testing.enabled_targets():
out = run_tvm_graph(model, target, dev, [a_np], ["input"], ref_val.shape, dtype)
tvm.testing.assert_allclose(out, ref_val, rtol=1e-5, atol=1e-5)
def test_reduce_converter(self):
input_dim = (1, 2, 2)
output_dim = (1,)
inputs = [('input', datatypes.Array(*input_dim))]
output = [('output', datatypes.Array(*output_dim))]
builder = NeuralNetworkBuilder(inputs, output)
builder.add_reduce(name='Reduce', input_name='input', output_name='output', axis='CHW', mode='sum')
model_onnx = convert_coreml(builder.spec)
self.assertTrue(model_onnx is not None)
def test_reduce_converter(self):
input_dim = (1, 2, 2)
output_dim = (1, )
inputs = [('input', datatypes.Array(*input_dim))]
output = [('output', datatypes.Array(*output_dim))]
builder = NeuralNetworkBuilder(inputs, output)
builder.add_reduce(name='Reduce',
input_name='input',
output_name='output',
axis='CHW',
mode='sum')
context = ConvertContext()
node = ReduceLayerConverter.convert(
context, builder.spec.neuralNetwork.layers[0], ['input'],
['output'])
self.assertTrue(node is not None)
