def test_case3(self):
graph = build_graph(nodes, [('Op1', 'Op1_data'),
('Op1_data', 'result1')])
res_node_graph = Node(graph, 'Op1')
res_node_graph['name'] = 'Op1_tensor'
ResultRename().find_and_replace_pattern(graph)
res_node = Node(graph, 'result1')
self.assertTrue(res_node['name'] == 'Op1_tensor/sink_port_0')
def test_case4(self):
graph = build_graph(nodes,
[('Op1', 'Op1_data'), ('Op1_data', 'result1'),
('Op1_data', 'Op2'), ('Op2', 'Op2_data'),
('Op2_data', 'result2')])
ResultRename().find_and_replace_pattern(graph)
res1_node = Node(graph, 'result1')
res2_node = Node(graph, 'result2')
self.assertTrue(res1_node['name'] == 'Op1_tensor')
self.assertTrue(res2_node['name'] == 'Op2_tensor')
def test_case2(self):
graph = build_graph(nodes, [])
graph_ref = build_graph(nodes, [])
ResultRename().find_and_replace_pattern(graph)
(flag, resp) = compare_graphs(graph,
graph_ref,
'result1',
check_op_attrs=True)
self.assertTrue(flag, resp)
def prepare_emit_ir(graph: Graph, data_type: str, output_dir: str, output_model_name: str,
mean_data: [list, None] = None, input_names: list = None, meta_info: dict = None):
if input_names is None:
input_names = []
if meta_info is None:
meta_info = {}
graph.strict_mode = False
# convert Parameter data types
convert_data_type.convert_parameters_data_type(graph, data_type)
# convert blobs (usually weights and biases)
for sub_graph in [graph] + collect_sub_graphs(graph):
convert_data_type.convert_blobs(sub_graph, data_type)
# restore data type for specific inputs/outputs of specific ops to the data types required by nGraph
for_graph_and_each_sub_graph_recursively(graph, convert_inputs_of_specific_ops)
for_graph_and_each_sub_graph_recursively(graph, OpVersioning().find_and_replace_pattern)
# do not run the type inference in sub-graphs. It will be called automatically as part of the type inference of
# the TensorIterator nodes
type_infer(graph)
RemoveUselessConvert().find_and_replace_pattern(graph)
ResultRename().find_and_replace_pattern(graph)
for sub_graph in [graph] + collect_sub_graphs(graph):
op_order, data_order = determined_sort(get_sorted_outputs(sub_graph))
mapping = {v: u for u, v in enumerate(op_order)}
mapping.update({v: u for u, v in enumerate(data_order, start=len(sub_graph))})
relabel_nodes_inplace_safe(sub_graph, mapping)
port_renumber(sub_graph)
tensor_names.propagate_op_name_to_tensor(graph)
bin_file = os.path.join(output_dir, '{}.bin'.format(output_model_name))
serialize_constants(graph, bin_file)
mean_offset = None
mean_size = None
if mean_data:
mean_offset, mean_size = serialize_mean_image(bin_file, mean_data=mean_data)
generate_ie_ir(graph=graph,
file_name=os.path.join(output_dir, '{}.xml'.format(output_model_name)),
input_names=input_names,
mean_offset=mean_offset,
mean_size=mean_size,
meta_info=meta_info)
tensor_names.output_tensor_names_map(graph, os.path.join(output_dir, '{}.mapping'.format(output_model_name)))
def test_case1(self):
graph = build_graph(nodes, [('Op1', 'Op1_data'),
('Op1_data', 'result')])
graph_ref = build_graph(nodes, [('Op1', 'Op1_data'),
('Op1_data', 'result')])
res_node = Node(graph_ref, 'result')
res_node['name'] = 'Op1_tensor'
ResultRename().find_and_replace_pattern(graph)
(flag, resp) = compare_graphs(graph,
graph_ref,
'result',
check_op_attrs=True)
self.assertTrue(flag, resp)