def test_proposal_infer_one_output(self):
graph = build_graph(nodes_attributes,
[('proposal_input', 'proposal'),
('proposal', 'proposal_out_data_1'),
('proposal_out_data_1', 'op_output')
],
{'proposal_input': {'shape': int64_array([1, 3, 227, 227])},
'proposal': {'post_nms_topn': 2, **layout_attrs()}
})
proposal_node = Node(graph, 'proposal')
ProposalOp.proposal_infer(proposal_node)
self.assertListEqual([1 * 2, 5], list(graph.node['proposal_out_data_1']['shape']))
def test_proposal_infer(self):
graph = build_graph(nodes_attributes,
[('node_1', 'proposal'),
('proposal', 'node_3')],
{'node_3': {'is_output': True, 'shape': None},
'node_1': {'shape': np.array([1, 3, 227, 227])},
'proposal': {'post_nms_topn': 2, **layout_attrs()}
})
proposal_node = Node(graph, 'proposal')
ProposalOp.proposal_infer(proposal_node)
exp_shape = np.array([1 * 2, 5])
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):
proto_layer = node.pb
param = proto_layer.proposal_param
update_attrs = {
'feat_stride': param.feat_stride,
'base_size': param.base_size,
'min_size': param.min_size,
'ratio': np.array(param.ratio),
'scale': np.array(param.scale),
'pre_nms_topn': param.pre_nms_topn,
'post_nms_topn': param.post_nms_topn,
'nms_thresh': param.nms_thresh
}
mapping_rule = merge_attrs(param, update_attrs)
# update the attributes of the node
ProposalOp.update_node_stat(node, mapping_rule)
return cls.enabled
def extract(self, node):
attrs = get_mxnet_layer_attrs(node.symbol_dict)
feat_stride = attrs.int("feat_stride", 16)
ratio = attrs.tuple("ratios", float, (0.5, 1, 2))
scale = attrs.tuple("scales", int, (4, 8, 16, 32))
min_size = attrs.int("rpn_min_size", 16)
pre_nms_topn = attrs.int("rpn_pre_nms_top_n", 6000)
post_nms_topn = attrs.int("rpn_post_nms_top_n", 300)
nms_thresh = attrs.float("threshold", 0.7)
node_attrs = {
'feat_stride': feat_stride,
'base_size': 0,
'min_size': min_size,
'ratio': np.array(ratio),
'scale': np.array(scale),
'pre_nms_topn': pre_nms_topn,
'post_nms_topn': post_nms_topn,
'nms_thresh': nms_thresh,
}
ProposalOp.update_node_stat(node, node_attrs)
return (True, node_attrs)
def extract_proposal_params(node, defaults):
param = node.pb.python_param
attrs = CaffePythonFrontExtractorOp.parse_param_str(param.param_str)
update_attrs = defaults
if 'ratios' in attrs and 'ratio' in attrs:
log.error(
'Both ratios and ratio found, value of ratios will be used',
extra={'is_warning': True})
if 'scales' in attrs and 'scale' in attrs:
log.error(
'Both scales and scale found, value of scales will be used',
extra={'is_warning': True})
if 'ratios' in attrs:
attrs['ratio'] = attrs['ratios']
del attrs['ratios']
if 'scales' in attrs:
attrs['scale'] = attrs['scales']
del attrs['scales']
update_attrs.update(attrs)
CaffePythonFrontExtractorOp.check_param(ProposalOp, update_attrs)
ProposalOp.update_node_stat(node, update_attrs)
def extract(cls, node):
attrs = get_mxnet_layer_attrs(node.symbol_dict)
pre_nms_topn = attrs.int('rpn_pre_nms_top_n', 6000)
post_nms_topn = attrs.int('rpn_post_nms_top_n', 300)
nms_thresh = attrs.float('threshold', 0.7)
min_size = attrs.int('rpn_min_size', 16)
scale = attrs.tuple("scales", float, (4, 8, 16, 32))
ratio = attrs.tuple("ratios", float, (0.5, 1, 2))
feat_stride = attrs.int('feature_stride', 16)
update_attrs = {
'feat_stride': feat_stride,
'ratio': np.array(ratio),
'min_size': min_size,
'scale': np.array(scale),
'pre_nms_topn': pre_nms_topn,
'post_nms_topn': post_nms_topn,
'nms_thresh': nms_thresh,
'base_size': feat_stride
}
# update the attributes of the node
ProposalOp.update_node_stat(node, update_attrs)
return cls.enabled