def test_pad_conv_fusion(self):
Cin = 3
Cout = 5
K = 9
Hin = 32
Win = 18
Xin = np.random.rand(Cin, Hin, Win)
# Test for several combinations of (pad,stride)
params = [(5, 2), (4, 3), (6, 3), (5, 1), (5, 2), (6, 2), (3, 2),
(1, 1), (2, 3)]
for param in params:
pad, stride = param
input_features = [('data', datatypes.Array(*(Cin, Hin, Win)))]
output_features = [('output', None)]
builder = neural_network.NeuralNetworkBuilder(
input_features, output_features)
builder.add_padding(name='pad',
left=pad,
right=pad,
top=pad,
bottom=pad,
input_name='data',
output_name='pad_out')
builder.add_convolution(name='conv',
kernel_channels=Cin,
output_channels=Cout,
height=K,
width=K,
stride_height=stride,
stride_width=stride,
border_mode='valid',
groups=1,
W=np.random.rand(K, K, Cin, Cout),
b=None,
has_bias=False,
input_name='pad_out',
output_name='output')
#get unoptimized model
original_spec = builder.spec
model = coremltools.models.utils._get_model(original_spec)
#get optimized model
spec_copy = copy.deepcopy(original_spec)
tfcoreml.optimize_nn_spec(spec_copy)
model_opt = coremltools.models.utils._get_model(spec_copy)
n_layers_original_model = len(
model.get_spec().neuralNetwork.layers)
n_layers_opt_model = len(model_opt.get_spec().neuralNetwork.layers)
self.assertEqual(n_layers_original_model, 2)
self.assertEqual(n_layers_opt_model, 1)
original_model_out = model.predict({'data': Xin})['output']
opt_model_out = model_opt.predict({'data': Xin})['output']
self._compare_outputs(opt_model_out, original_model_out)
input_tensor = "tower_0/images"
output_tensors = ["tower_0/cls_output"]
centernet_model = tfcoreml.convert(
tf_model_path='./model/shufflenet.pb',
mlmodel_path='./model/shufflenet.mlmodel',
#image_input_names=input_tensor,
output_feature_names=output_tensors,
input_name_shape_dict={
'tower_0/images': [1, cfg.MODEL.hin, cfg.MODEL.win, 3]
}, # map from input tensor name (placeholder op in the graph) to shape
minimum_ios_deployment_target='13',
is_bgr=False)
spec = centernet_model.get_spec()
tfcoreml.optimize_nn_spec(spec)
#
#####clean the name of the model
print(spec.description)
spec.description.input[0].name = "image"
spec.description.input[0].shortDescription = "Input image"
spec.description.output[0].name = "category"
spec.description.output[0].shortDescription = "Predicted category"
#
# # #
# # #
# ##rename the tensor name
for i in range(len(spec.neuralNetwork.layers)):
try: