def extract(cls, node):
proto_layer = node.pb
param = proto_layer.prior_box_param
variance = param.variance
if len(variance) == 0:
variance = [0.1]
update_attrs = {
'width': list(param.width),
'height': list(param.height),
'flip': int(param.flip),
'clip': int(param.clip),
'variance': list(variance),
'img_size': param.img_size,
'img_h': param.img_h,
'img_w': param.img_w,
'step': param.step,
'step_h': param.step_h,
'step_w': param.step_w,
'offset': param.offset,
}
mapping_rule = merge_attrs(param, update_attrs)
mapping_rule.update(layout_attrs())
# update the attributes of the node
PriorBoxClusteredOp.update_node_stat(node, mapping_rule)
return cls.enabled
def test_tf_priorboxclustered_infer(self):
graph = build_graph(
nodes_attributes, [('node_1', 'pbc'), ('node_2', 'pbc'),
('pbc', 'node_3'), ('node_3', 'op_output')],
{
'node_3': {
'shape': None
},
'node_1': {
'shape': np.array([1, 19, 19, 384])
},
'node_2': {
'shape': np.array([1, 300, 300, 3])
},
'pbc': {
'flip': 0,
'clip': 0,
'variance': [0.1, 0.1, 0.2, 0.2],
'step': 0,
'offset': 0.5,
'width': [1., 1., 1., 1., 1., 1., 1., 1., 1.],
'height': [2., 2., 2., 2., 2., 2., 2., 2., 2.]
}
})
graph.graph['layout'] = 'NHWC'
pbc_node = Node(graph, 'pbc')
PriorBoxClusteredOp.priorbox_clustered_infer(pbc_node)
exp_shape = np.array([1, 2, 12996])
res_shape = graph.node['node_3']['shape']
for i in range(0, len(exp_shape)):
self.assertEqual(exp_shape[i], res_shape[i])
def extract(cls, node):
variance = onnx_attr(node,
'variance',
'floats',
default=[],
dst_type=lambda x: np.array(x, dtype=np.float32))
if len(variance) == 0:
variance = [0.1]
update_attrs = {
'width':
onnx_attr(node,
'width',
'floats',
dst_type=lambda x: np.array(x, dtype=np.float32)),
'height':
onnx_attr(node,
'height',
'floats',
dst_type=lambda x: np.array(x, dtype=np.float32)),
'flip':
onnx_attr(node, 'flip', 'i', default=0),
'clip':
onnx_attr(node, 'clip', 'i', default=0),
'variance':
list(variance),
'img_size':
onnx_attr(node, 'img_size', 'i', default=0),
'img_h':
onnx_attr(node, 'img_h', 'i', default=0),
'img_w':
onnx_attr(node, 'img_w', 'i', default=0),
'step':
onnx_attr(node, 'step', 'f', default=0.0),
'step_h':
onnx_attr(node, 'step_h', 'f', default=0.0),
'step_w':
onnx_attr(node, 'step_w', 'f', default=0.0),
'offset':
onnx_attr(node, 'offset', 'f', default=0.0),
}
# update the attributes of the node
PriorBoxClusteredOp.update_node_stat(node, update_attrs)
return cls.enabled
def transform_graph(self, graph: Graph, replacement_descriptions: dict):
parameter_node = graph.get_op_nodes(op='Parameter')[0]
parameter_node['data_type'] = data_type_str_to_np(
parameter_node.graph.graph['cmd_params'].data_type)
parameter_node.out_port(0).disconnect()
# remove existing Result operations to remove unsupported sub-graph
graph.remove_nodes_from(
[node.id
for node in graph.get_op_nodes(op='Result')] + ['detections'])
# determine if the op which is a input/final result of mean value and scale applying to the input tensor
# then connect it to the input of the first convolution of the model, so we remove the image pre-processing
# which includes padding and resizing from the model
preprocessing_input_node_id = replacement_descriptions[
'preprocessing_input_node']
assert preprocessing_input_node_id in graph.nodes, 'The node with name "{}" is not found in the graph. This ' \
'should be a last node before image normalization and is specified' \
' in the json file.'.format(preprocessing_input_node_id)
preprocessing_input_node = Node(graph, preprocessing_input_node_id)
consumer_node = preprocessing_input_node.out_port(
0).get_connection().get_destination().node
consumer_node.in_port(0).get_connection().set_source(
parameter_node.out_port(0))
preprocessing_output_node_id = replacement_descriptions[
'preprocessing_output_node']
assert preprocessing_output_node_id in graph.nodes, 'The node with name "{}" is not found in the graph. This ' \
'node should provide scaled image output and is specified' \
' in the json file.'.format(preprocessing_output_node_id)
preprocessing_output_node = Node(graph, preprocessing_output_node_id)
preprocessing_output_node.out_port(0).disconnect()
convolution_nodes = [
n for n in graph.pseudo_topological_sort()
if n.soft_get('type') == 'Convolution'
]
convolution_nodes[0].in_port(0).get_connection().set_source(
preprocessing_output_node.out_port(0))
# create prior boxes (anchors) generator
aspect_ratios = replacement_descriptions['aspect_ratios']
assert len(aspect_ratios) % 2 == 0
aspect_ratios = list(zip(aspect_ratios[::2], aspect_ratios[1::2]))
priors_generator = self.AnchorGenerator(
min_level=int(replacement_descriptions['min_level']),
aspect_ratios=aspect_ratios,
num_scales=int(replacement_descriptions['num_scales']),
anchor_scale=replacement_descriptions['anchor_scale'])
prior_boxes = []
for i in range(100):
inp_name = 'box_net/box-predict{}/BiasAdd'.format('_%d' %
i if i else '')
if inp_name not in graph:
break
widths, heights = priors_generator.get(i)
prior_box_op = PriorBoxClusteredOp(
graph, {
'width': np.array(widths),
'height': np.array(heights),
'clip': 0,
'flip': 0,
'variance': replacement_descriptions['variance'],
'offset': 0.5
})
prior_boxes.append(
prior_box_op.create_node(
[Node(graph, inp_name), parameter_node]))
# concatenate prior box operations
concat_prior_boxes = Concat(graph, {'axis': -1}).create_node()
for idx, node in enumerate(prior_boxes):
concat_prior_boxes.add_input_port(idx)
concat_prior_boxes.in_port(idx).connect(node.out_port(0))
conf = Sigmoid(graph, dict(name='concat/sigmoid')).create_node(
[Node(graph, 'concat')])
reshape_size_node = Const(graph, {
'value': int64_array([0, -1])
}).create_node([])
logits = Reshape(graph, dict(name=conf.name + '/Flatten')).create_node(
[conf, reshape_size_node])
deltas = Reshape(graph, dict(name='concat_1/Flatten')).create_node(
[Node(graph, 'concat_1'), reshape_size_node])
# revert convolution boxes prediction weights from yxYX to xyXY (convolutions share weights and bias)
weights = Node(graph, 'box_net/box-predict/pointwise_kernel')
weights.value = weights.value.reshape(-1, 4)[:, [1, 0, 3, 2]].reshape(
weights.shape)
bias = Node(graph, 'box_net/box-predict/bias')
bias.value = bias.value.reshape(-1,
4)[:, [1, 0, 3, 2]].reshape(bias.shape)
detection_output_node = DetectionOutput(
graph,
dict(
name='detections',
num_classes=int(replacement_descriptions['num_classes']),
share_location=1,
background_label_id=int(
replacement_descriptions['num_classes']) + 1,
nms_threshold=replacement_descriptions['nms_threshold'],
confidence_threshold=replacement_descriptions[
'confidence_threshold'],
top_k=100,
keep_top_k=100,
code_type='caffe.PriorBoxParameter.CENTER_SIZE',
)).create_node([deltas, logits, concat_prior_boxes])
output_op = Result(graph, dict(name='output'))
output_op.create_node([detection_output_node])