def make_graph():
graph, _ = toposort_multi_tier_output_graph()
graph.outputs.pop()
# Deep copy should work with empty tensors
graph.nodes[0].inputs.append(Variable.empty())
graph.nodes[0].outputs.append(Variable.empty())
return graph
def check_tensor(name: str):
if name not in tensor_map:
if name:
G_LOGGER.debug(
"Tensor: {:} was not generated during shape inference, or shape inference was not run on this model. Creating a new Tensor."
.format(name))
tensor_map[name] = Variable(name)
else:
# Empty tensors are not tracked by the graph, as these represent optional inputs/outputs that have been omitted.
G_LOGGER.verbose("Generating empty tensor")
return Variable.empty()
return tensor_map[name]
def lstm_model():
path = os.path.join(TEST_ROOT, "models", "lstm.onnx")
model = onnx.load(path)
onnx_graph = model.graph
def load_initializer(index: int) -> np.ndarray:
return onnx.numpy_helper.to_array(onnx_graph.initializer[index])
# Optional inputs are represented by empty tensors
X = Variable(name="X", dtype=np.float32, shape=(4, 3, 6))
W = Constant(name="W", values=load_initializer(0))
R = Constant(name="R", values=load_initializer(1))
B = Constant(name="B", values=load_initializer(2))
initial_c = Constant(name="initial_c", values=load_initializer(3))
Y = Variable(name="Y", dtype=np.float32, shape=(4, 1, 3, 5))
Y_h = Variable(name="Y_h", dtype=np.float32, shape=(1, 3, 5))
Y_c = Variable(name="Y_c", dtype=np.float32, shape=(1, 3, 5))
attrs = OrderedDict()
attrs["direction"] = "forward"
attrs["hidden_size"] = 5
node = Node(
op="LSTM",
attrs=attrs,
inputs=[X, W, R, B,
Variable.empty(),
Variable.empty(), initial_c],
outputs=[Y, Y_h, Y_c],
)
# Initializers will not be included in the graph inputs.
return Model(
path,
inputs=[X],
outputs=[Y, Y_h, Y_c],
nodes=[node],
opset=OnnxImporter.get_opset(model),
)
def get_tensor(name: str, check_outer_graph=True):
# Prioritize the subgraph even if check_outer_graph is set
if name in subgraph_tensor_map:
return subgraph_tensor_map[name]
if check_outer_graph and name in tensor_map:
return tensor_map[name]
if not name:
# Empty tensors are not tracked by the graph, as these represent optional inputs/outputs that have been omitted.
G_LOGGER.verbose("Generating empty tensor")
return Variable.empty()
G_LOGGER.verbose("Tensor: {:} was not generated during shape inference, or shape inference was not run on this model. Creating a new Tensor.".format(name))
subgraph_tensor_map[name] = Variable(name)
return subgraph_tensor_map[name]
def get_tensor(name):
if not name:
return Variable.empty()
return local_tensor_copies[name]
def get_tensor(name):
if not name:
return Variable.empty()
return tensor_map[name]