def test_transpose_permute(self,
minimum_ios_deployment_target='13'
): # type: () -> None
_test_single_node(
"Transpose", [(5, 3, 4, 6, 2)], [(2, 3, 4, 6, 5)],
axes=[4, 1, 2, 3, 0],
minimum_ios_deployment_target=minimum_ios_deployment_target)
def test_split_axis_0_rank_3(self,
minimum_ios_deployment_target='12'
): # type: () -> None
_test_single_node(
"Split", [(2, 1, 200)], [(1, 1, 200), (1, 1, 200)],
axes=0,
minimum_ios_deployment_target=minimum_ios_deployment_target)
def test_avg_pool(self): # type: () -> None
kernel_shape = (5, 3)
pads = (2, 1, 2, 1)
strides = (1, 2)
input_shape = (1, 3, 224, 224)
output_size = _conv_pool_output_size(input_shape, (1, 1),
kernel_shape, pads, strides)
output_shape = (1, 3, output_size[0], output_size[1])
_test_single_node(
"AveragePool",
[input_shape],
[output_shape],
test_name='test_avg_pool_1',
kernel_shape=kernel_shape,
pads=pads,
strides=strides
)
output_size = _conv_pool_output_size(input_shape, (1, 1),
kernel_shape, [0, 0, 0, 0],
strides)
output_shape = (1, 3, output_size[0], output_size[1])
_test_single_node(
"AveragePool",
[input_shape],
[output_shape],
test_name='test_avg_pool_2',
kernel_shape=kernel_shape,
strides=strides
)
def test_conv_transpose(self): # type: () -> None
kernel_shape = (3, 3)
pads = (0, 0, 0, 0)
C_in = 3
C_out = 12
H_in, W_in = 30, 30
strides = (2, 2)
input_shape = (1, C_in, H_in, W_in)
weight = from_array(_random_array((C_in, C_out, kernel_shape[0], kernel_shape[1])),
name="weight")
H_out = (H_in-1) * strides[0] + kernel_shape[0] - pads[0] - pads[2]
W_out = (W_in-1) * strides[1] + kernel_shape[1] - pads[1] - pads[3]
output_shape = (1, C_out, H_out, W_out)
_test_single_node(
"ConvTranspose",
[input_shape],
[output_shape],
initializer=[weight],
# Default values for other attributes: dilations=[1, 1], group=1
strides = strides,
kernel_shape=kernel_shape,
pads=pads,
output_padding=(0, 0)
)
def test_reshape_same_rank_infer_shape(self, disable_rank5_mapping=True): # type: () -> None
_test_single_node(
"Reshape",
[(5, 4, 3), (3,)],
[(5, 2, 6)],
disable_rank5_mapping=disable_rank5_mapping
)
def test_bn(self): # type: () -> None
scale = from_array(_random_array((3,)), name="scale")
bias = from_array(_random_array((3,)), name="bias")
mean = from_array(_random_array((3,)), name="mean")
var = from_array(_random_array((3,)), name="var")
epsilon = 1e-5
momentum = 0.001
op_types = ["BatchNormalization", "SpatialBN"]
for op_type in op_types:
_test_single_node(
"BatchNormalization",
[(1, 3, 224, 224)],
[(1, 3, 224, 224)],
initializer=[scale, bias, mean, var],
epsilon=epsilon,
momentum=momentum
)
# epsilon by default
_test_single_node(
"BatchNormalization",
[(1, 3, 224, 224)],
[(1, 3, 224, 224)],
initializer=[scale, bias, mean, var],
# epsilon=epsilon,
momentum=momentum
)
def test_max_pool(self): # type: () -> None
kernel_shape = (5, 3)
pads = (2, 1, 2, 1)
strides = (1, 2)
input_shape = (1, 3, 224, 224)
output_size = _conv_pool_output_size(input_shape, [1, 1],
kernel_shape, pads, strides)
output_shape = (1, 3, output_size[0], output_size[1])
_test_single_node(
"MaxPool",
[input_shape],
[output_shape],
kernel_shape=kernel_shape,
pads=pads,
strides=strides
)
output_size = _conv_pool_output_size(input_shape, [1, 1],
kernel_shape, [0, 0, 0, 0],
strides)
output_shape = (1, 3, output_size[0], output_size[1])
_test_single_node(
"MaxPool",
[input_shape],
[output_shape],
kernel_shape=kernel_shape,
strides=strides
)
def test_reshape_dynamic(self, disable_rank5_mapping=True): # type: () -> None
_test_single_node(
"Reshape",
[(5, 4, 3, 2), (3,)],
[(2, 3, 20)],
disable_rank5_mapping=disable_rank5_mapping
)
def test_transpose_default(self, disable_rank5_mapping=True): # type: () -> None
_test_single_node(
"Transpose",
[(5, 3, 4, 6, 2)],
[(2, 6, 4, 3, 5)],
disable_rank5_mapping=disable_rank5_mapping
)
def test_slice_axis_0_rank_2(self): # type: () -> None
_test_single_node("Slice", [(10, 2)], [(5, 2)],
onnx_coreml_input_shape_map={'input0': [3, 4]},
coreml_input_shape={'input0': [1, 10, 2]},
axes=[0],
starts=[5],
ends=[10])
def test_conv(self): # type: () -> None
kernel_shape = (3, 2)
strides = (2, 3)
pads = (4, 2, 4, 2)
dilations = (1, 2)
group = 1
weight = from_array(_random_array((16, 3, 3, 2)), name="weight")
input_shape = (1, 3, 224, 224)
output_size = _conv_pool_output_size(input_shape, dilations,
kernel_shape, pads, strides)
output_shape = (1, int(weight.dims[0]), output_size[0], output_size[1])
_test_single_node(
"Conv",
[input_shape],
[output_shape],
initializer=[weight],
dilations=dilations,
group=group,
kernel_shape=kernel_shape,
pads=pads,
strides=strides
)
def test_split_axis_0_rank_3(self, disable_rank5_mapping=True): # type: () -> None
_test_single_node(
"Split",
[(2, 1, 200)],
[(1, 1, 200), (1, 1, 200)],
axes=0,
disable_rank5_mapping=disable_rank5_mapping
)
def test_concat(self, disable_rank5_mapping=True): # type: () -> None
_test_single_node(
"Concat",
[(1, 2, 200), (1, 2, 200)],
[(2, 2, 200)],
axis=0,
disable_rank5_mapping=disable_rank5_mapping
)
def test_gather(self, disable_rank5_mapping=True): # type: () -> None
_test_single_node(
"Gather",
[(5, 4, 3), (3,)],
[(3, 4, 3)],
axis=0,
disable_rank5_mapping=disable_rank5_mapping
)
def test_squeeze(self, disable_rank5_mapping=True): # type: () -> None
_test_single_node(
"Squeeze",
[(5, 1, 3, 1, 1)],
[(5, 3)],
axes=[1, 3, 4],
disable_rank5_mapping=disable_rank5_mapping
)
def test_transpose_permute(self, disable_rank5_mapping=True): # type: () -> None
_test_single_node(
"Transpose",
[(5, 3, 4, 6, 2)],
[(2, 3, 4, 6, 5)],
axes=[4, 1, 2, 3, 0],
disable_rank5_mapping=disable_rank5_mapping
)
def test_unsqueeze(self, disable_rank5_mapping=True): # type: () -> None
_test_single_node(
"Unsqueeze",
[(5, 3, 4)],
[(1, 5, 1, 3, 4)],
axes=[0, 1],
disable_rank5_mapping=disable_rank5_mapping
)
def test_slice_axis_3_rank_4(self,
disable_rank5_mapping=False
): # type: () -> None
_test_single_node("Slice", [(1, 3, 224, 224)], [(1, 3, 224, 222)],
axes=[3],
starts=[1],
ends=[223],
disable_rank5_mapping=disable_rank5_mapping)
def test_slice_axis_3_rank_4(self): # type: () -> None
_test_single_node(
"Slice",
[(1, 3, 224, 224)],
[(1, 3, 224, 222)],
axes=[3],
starts=[1],
ends=[223]
)
def test_gemm(self): # type: () -> None
input_shape = (1, 2048)
output_shape = (1, 5)
W = from_array(_random_array((output_shape[1], input_shape[1])),
name="weight")
b = from_array(_random_array((output_shape[1], )), name="bias")
_test_single_node("Gemm", [input_shape], [output_shape],
initializer=[W, b],
decimal=3,
transB=1)
def test_lrn(self): # type: () -> None
_test_single_node(
"LRN",
[(1, 3, 224, 224)],
[(1, 3, 224, 224)],
alpha=9.99e-5,
beta=0.75,
bias=1.0,
size=5
)
def test_gemm_transB_off(self, target_ios='12'): # type: () -> None
input_shape = (1, 2048)
output_shape = (1, 5)
W = from_array(_random_array((input_shape[1], output_shape[1])),
name="weight")
b = from_array(_random_array((output_shape[1], )), name="bias")
_test_single_node("Gemm", [input_shape], [output_shape],
initializer=[W, b],
decimal=3,
transB=0,
target_ios=target_ios)
def test_gemm(self,
minimum_ios_deployment_target='12'): # type: () -> None
input_shape = (1, 2048)
output_shape = (1, 5)
W = from_array(_random_array((output_shape[1], input_shape[1])),
name="weight")
b = from_array(_random_array((output_shape[1], )), name="bias")
_test_single_node(
"Gemm", [input_shape], [output_shape],
initializer=[W, b],
decimal=3,
transB=1,
minimum_ios_deployment_target=minimum_ios_deployment_target)
def test_gemm_transB_off(self, disable_rank5_mapping=False): # type: () -> None
input_shape = (1, 2048)
output_shape = (1, 5)
W = from_array(
_random_array((input_shape[1], output_shape[1])), name="weight"
)
b = from_array(
_random_array((output_shape[1],)), name="bias"
)
_test_single_node(
"Gemm",
[input_shape],
[output_shape],
initializer=[W, b],
decimal=3,
transB=0,
disable_rank5_mapping=disable_rank5_mapping
)
def test_concat(self):
_test_single_node("Concat", [(1, 3, 128, 256), (1, 3, 128, 256)],
[(6, 128, 256)])
def test_sigmoid(self):
_test_single_node("Sigmoid", [(1, 3, 224, 224)], [(1, 3, 224, 224)])
def test_softmax(self):
_test_single_node("Softmax", [(1, 100, 1, 1)], [(1, 100, 1, 1)])
def test_reshape(self):
_test_single_node("Reshape", [(3, 224, 224)], [(1, 3 * 224 * 224)],
shape=(1, 3 * 224 * 224))
def test_transpose(self):
_test_single_node("Transpose", [(3, 224, 224)], [(224, 3, 224)],
perm=(1, 0, 2))
def test_transpose_default(self):
_test_single_node("Transpose", [(4, 5, 6)], [(6, 5, 4)])
