def insert_do(graph: Graph, replacement_descriptions: dict):
do_outputs = replacement_descriptions['do_outputs']
prior_boxes_node = Node(graph, 'ROIFeatureExtractor_2')
num_classes = 81
box_regressions_input_node = Node(
graph, replacement_descriptions['box_regressions_input_node'])
box_regressions_node = create_op_node_with_second_input(
graph, Reshape, int64_array([-1, 4 * num_classes]),
dict(name='box_regressions'), box_regressions_input_node)
class_predicitons_node = Node(
graph, replacement_descriptions['class_predicitons_node'])
im_info_node = Parameter(graph, {
"name": 'im_info',
'shape': int64_array([1, 3])
}).create_node()
do_node = ExperimentalDetectronDetectionOutput(
graph, {
'name':
'DetectionOutput',
'class_agnostic_box_regression':
0,
'deltas_weights':
np.array([10.0, 10.0, 5.0, 5.0]),
'max_delta_log_wh':
replacement_descriptions['max_delta_log_wh'],
'nms_threshold':
replacement_descriptions['nms_threshold'],
'score_threshold':
replacement_descriptions['score_threshold'],
'num_classes':
num_classes,
'max_detections_per_image':
replacement_descriptions['max_detections_per_image'],
'post_nms_count':
replacement_descriptions['post_nms_count']
}).create_node()
prior_boxes_node.out_port(1).connect(do_node.in_port(0))
box_regressions_node.out_port(0).connect(do_node.in_port(1))
class_predicitons_node.out_port(0).connect(do_node.in_port(2))
im_info_node.out_port(0).connect(do_node.in_port(3))
do_output_ports = [
do_node.out_port(0),
do_node.out_port(1),
do_node.out_port(2)
]
old_do_output_nodes = [Node(graph, node_id) for node_id in do_outputs]
for old_node, new_port in zip(old_do_output_nodes, do_output_ports):
old_node.out_port(0).get_connection().set_source(new_port)
# the consumer of the second output port of the ExperimentalDetectronDetectionOutput is the Mul node which second
# input is of type int64 so it is necessary to insert Cast to have data types match
do_node.out_port(1).get_connection().insert_node(
Cast(graph, {
'dst_type': np.int64
}).create_node())
def extract(cls, node):
attrs = dict(class_agnostic_box_regression=onnx_attr(
node, 'class_agnostic_box_regression', 'i', 0),
max_detections_per_image=onnx_attr(
node, 'max_detections_per_image', 'i', 100),
nms_threshold=onnx_attr(node, 'nms_threshold', 'f', 0.5),
num_classes=onnx_attr(node, 'num_classes', 'i', 81),
post_nms_count=onnx_attr(node, 'post_nms_count', 'i',
2000),
score_threshold=onnx_attr(node, 'score_threshold', 'f',
0.05),
max_delta_log_wh=onnx_attr(node, 'max_delta_log_wh', 'f',
log(1000. / 16.)),
deltas_weights=np.array(onnx_attr(node, 'deltas_weights',
'floats',
[10., 10., 5., 5.]),
dtype=np.float32))
ExperimentalDetectronDetectionOutput.update_node_stat(node, attrs)
return cls.enabled
def insert_do(graph: Graph, replacement_descriptions):
do_outputs = ['6530', '6532', '6534']
prior_boxes_node = Node(graph, 'ROIFeatureExtractor_2')
num_classes = 81
box_regressions_node = create_op_node_with_second_input(
graph, Reshape, int64_array([-1, 4 * num_classes]),
dict(name='box_regressions'), Node(graph, '2773'))
class_predicitons_node = Node(graph, '2774')
im_info_node = Parameter(graph, {
"name": 'im_info',
'shape': int64_array([1, 3])
}).create_node()
do_node = ExperimentalDetectronDetectionOutput(
graph, {
'name':
'DetectionOutput',
'class_agnostic_box_regression':
0,
'deltas_weights':
np.array([10.0, 10.0, 5.0, 5.0]),
'max_delta_log_wh':
replacement_descriptions['max_delta_log_wh'],
'nms_threshold':
replacement_descriptions['nms_threshold'],
'score_threshold':
replacement_descriptions['score_threshold'],
'num_classes':
num_classes,
'max_detections_per_image':
replacement_descriptions['max_detections_per_image'],
'post_nms_count':
replacement_descriptions['post_nms_count']
}).create_node()
prior_boxes_node.out_port(1).connect(do_node.in_port(0))
box_regressions_node.out_port(0).connect(do_node.in_port(1))
class_predicitons_node.out_port(0).connect(do_node.in_port(2))
im_info_node.out_port(0).connect(do_node.in_port(3))
do_output_ports = [
do_node.out_port(0),
do_node.out_port(1),
do_node.out_port(2)
]
old_do_output_nodes = [Node(graph, node_id) for node_id in do_outputs]
for old_node, new_port in zip(old_do_output_nodes, do_output_ports):
old_node.out_port(0).get_connection().set_source(new_port)