def map_inner_product(cls, node):
#TODO: Axis
assert node.parameters.axis == 1
#TODO: Unbiased
shape = TensorShape()
dim = shape.dim.add()
dim.size = -1
dim = shape.dim.add()
dim.size = 1
for i in node.output_shape[1:]:
dim.size *= i
kwargs = {
'use_bias': node.parameters.bias_term,
'units': node.parameters.num_output,
'_output_shapes': [shape]
}
# check if need the Flatten layer
parent, _ = node.get_only_parent()
ret = []
# if parent.output_shape.height > 1 or parent.output_shape.width > 1:
ret.append(cls._add_flatten_layer(parent))
ret.append(Node.create('FullyConnected', **kwargs))
return ret
def _add_flatten_layer(cls, node):
shape = TensorShape()
dim = shape.dim.add()
dim.size = -1
dim = shape.dim.add()
dim.size = 1
for i in node.output_shape[1:]:
dim.size *= i
kwargs = {'_output_shapes': [shape]}
return Node.create('Flatten', **kwargs)
def map_data(cls, node):
# TODO: We need to identify whether this is 4D image data, otherwise we shouldn't change the dimension order
shape = TensorShape()
dim = shape.dim.add()
dim.size = -1
for i in node.output_shape[2:]:
dim = shape.dim.add()
dim.size = i
dim = shape.dim.add()
dim.size = node.output_shape.channels
kwargs = {'shape': shape} # Ignore the dimension of batch size
cls._convert_output_shape(kwargs, node)
return Node.create('DataInput', **kwargs)
def _convert_output_shape(cls, kwargs, node):
shape = TensorShape()
dim = shape.dim.add()
dim.size = -1
if len(node.output_shape) > 2:
for i in node.output_shape[2:]:
dim = shape.dim.add()
dim.size = i
dim = shape.dim.add()
dim.size = node.output_shape.channels
else:
dim = shape.dim.add()
dim.size = node.output_shape[1]
kwargs['_output_shapes'] = [shape]
