def generate_onnx_graph(dim, nbnode, input_name='X1'):
i1 = input_name
scale = list(np.ones((1, dim)).ravel())
for i in range(nbnode - 1):
i2 = list(
map(float,
np.ones((1, dim)).astype(np.float32).ravel()))
node = OnnxScaler(i1, offset=i2, scale=scale)
i1 = node
i2 = list(map(float, np.ones((1, dim)).astype(np.float32).ravel()))
node = OnnxScaler(i1, offset=i2, scale=scale, output_names=['Y'])
onx = node.to_onnx([(input_name, FloatTensorType((None, dim)))],
outputs=[('Y', FloatTensorType((None, dim)))])
return onx
def generate_onnx_graph(dim, nbnode, input_name='X1'):
matrices = []
scale = list(numpy.ones((1, dim)).ravel())
i1 = input_name
for i in range(nbnode - 1):
i2 = list(rand(1, dim).ravel())
matrices.append(i2)
node = OnnxScaler(i1, offset=i2, scale=scale)
i1 = node
i2 = list(rand(1, dim).ravel())
matrices.append(i2)
node = OnnxScaler(i1, offset=i2, scale=scale, output_names=['Y'])
onx = node.to_onnx([(input_name, FloatTensorType((1, dim)))],
outputs=[('Y', FloatTensorType((1, dim)))])
return onx, matrices
def generate_onnx_graph(dim, nbnode, input_name='X1'):
"""Generates a series of consecutive scalers."""
matrices = []
scale = list(numpy.ones((1, dim)).ravel())
i1 = input_name
for i in range(nbnode - 1):
i2 = list(-random_binary_classification(1, dim)[0].ravel())
matrices.append(i2)
node = OnnxScaler(i1, offset=i2, scale=scale)
i1 = node
i2 = list(-random_binary_classification(1, dim)[0].ravel())
matrices.append(i2)
node = OnnxScaler(i1, offset=i2, scale=scale, output_names=['Y'])
onx = node.to_onnx([(input_name, FloatTensorType((None, dim)))],
outputs=[('Y', FloatTensorType((None, dim)))])
onx.ir_version = get_ir_version(__max_supported_opset__)
return onx, matrices