65 lines
2.6 KiB
Python
65 lines
2.6 KiB
Python
# Copyright (C) 2018-2021 Intel Corporation
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
from mo.front.common.partial_infer.utils import int64_array
|
|
from mo.front.extractor import bool_to_str
|
|
from mo.graph.graph import Node, Graph
|
|
from mo.ops.op import Op
|
|
|
|
|
|
class CTCGreedyDecoderOp(Op):
|
|
op = 'CTCGreedyDecoder'
|
|
|
|
def __init__(self, graph: Graph, attrs: dict):
|
|
mandatory_props = {
|
|
'type': self.op,
|
|
'op': self.op,
|
|
'version': 'opset1',
|
|
|
|
'infer': self.infer,
|
|
'reinterp_shape': True,
|
|
|
|
'in_ports_count': 2,
|
|
'out_ports_count': 1,
|
|
|
|
'ctc_merge_repeated': True
|
|
}
|
|
super().__init__(graph, mandatory_props, attrs)
|
|
|
|
def supported_attrs(self):
|
|
return [
|
|
('ctc_merge_repeated', lambda node: bool_to_str(node, 'ctc_merge_repeated'))
|
|
]
|
|
|
|
@staticmethod
|
|
def infer(node: Node):
|
|
node_name = node.soft_get('name', node.id)
|
|
connected_in_ports = [port for port in node.in_ports().values() if not port.disconnected()]
|
|
assert len(connected_in_ports) == 2, \
|
|
"Incorrect number of inputs for {} node".format(node_name)
|
|
|
|
logits_shape = node.in_port(0).data.get_shape()
|
|
sequence_mask_shape = node.in_port(1).data.get_shape()
|
|
|
|
# check shapes of input tensors
|
|
assert len(logits_shape) == 3, \
|
|
'Incorrect rank of logits for {} node'.format(node_name)
|
|
if node.has_valid('use_mask_format') and node.use_mask_format is True:
|
|
# it is a case when CTCGreedyDecoder still uses an original format for sequence_length
|
|
assert len(sequence_mask_shape) == 1, \
|
|
'Incorrect rank of sequence length tensor for {} node'.format(node_name)
|
|
assert logits_shape[1] == sequence_mask_shape[0], \
|
|
'Batch dimensions of input tensors must be the same for {} node'.format(node_name)
|
|
else:
|
|
# it is a case when CTCGreedyDecoder uses a sequence mask
|
|
assert len(sequence_mask_shape) == 2, \
|
|
'Incorrect rank of sequence length tensor for {} node'.format(node_name)
|
|
assert logits_shape[1] == sequence_mask_shape[1], \
|
|
'Batch dimensions of input tensors must be the same for {} node'.format(node_name)
|
|
assert logits_shape[0] == sequence_mask_shape[0], \
|
|
'Time dimensions of input tensors must be the same for {} node'.format(node_name)
|
|
|
|
batch_size = logits_shape[1]
|
|
time_size = logits_shape[0]
|
|
node.out_port(0).data.set_shape(int64_array([batch_size, time_size, 1, 1]))
|