File size: 4,748 Bytes
a89d9fd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 |
# copyright (c) 2022 PaddlePaddle Authors. All Rights Reserve.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
This code is refer from:
https://github.com/hikopensource/DAVAR-Lab-OCR/davarocr/davar_rcg/models/sequence_heads/att_head.py
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import paddle
import paddle.nn as nn
import paddle.nn.functional as F
class SPINAttentionHead(nn.Layer):
def __init__(self, in_channels, out_channels, hidden_size, **kwargs):
super(SPINAttentionHead, self).__init__()
self.input_size = in_channels
self.hidden_size = hidden_size
self.num_classes = out_channels
self.attention_cell = AttentionLSTMCell(
in_channels, hidden_size, out_channels, use_gru=False)
self.generator = nn.Linear(hidden_size, out_channels)
def _char_to_onehot(self, input_char, onehot_dim):
input_ont_hot = F.one_hot(input_char, onehot_dim)
return input_ont_hot
def forward(self, inputs, targets=None, batch_max_length=25):
batch_size = paddle.shape(inputs)[0]
num_steps = batch_max_length + 1 # +1 for [sos] at end of sentence
hidden = (paddle.zeros((batch_size, self.hidden_size)),
paddle.zeros((batch_size, self.hidden_size)))
output_hiddens = []
if self.training: # for train
targets = targets[0]
for i in range(num_steps):
char_onehots = self._char_to_onehot(
targets[:, i], onehot_dim=self.num_classes)
(outputs, hidden), alpha = self.attention_cell(hidden, inputs,
char_onehots)
output_hiddens.append(paddle.unsqueeze(outputs, axis=1))
output = paddle.concat(output_hiddens, axis=1)
probs = self.generator(output)
else:
targets = paddle.zeros(shape=[batch_size], dtype="int32")
probs = None
char_onehots = None
outputs = None
alpha = None
for i in range(num_steps):
char_onehots = self._char_to_onehot(
targets, onehot_dim=self.num_classes)
(outputs, hidden), alpha = self.attention_cell(hidden, inputs,
char_onehots)
probs_step = self.generator(outputs)
if probs is None:
probs = paddle.unsqueeze(probs_step, axis=1)
else:
probs = paddle.concat(
[probs, paddle.unsqueeze(
probs_step, axis=1)], axis=1)
next_input = probs_step.argmax(axis=1)
targets = next_input
if not self.training:
probs = paddle.nn.functional.softmax(probs, axis=2)
return probs
class AttentionLSTMCell(nn.Layer):
def __init__(self, input_size, hidden_size, num_embeddings, use_gru=False):
super(AttentionLSTMCell, self).__init__()
self.i2h = nn.Linear(input_size, hidden_size, bias_attr=False)
self.h2h = nn.Linear(hidden_size, hidden_size)
self.score = nn.Linear(hidden_size, 1, bias_attr=False)
if not use_gru:
self.rnn = nn.LSTMCell(
input_size=input_size + num_embeddings, hidden_size=hidden_size)
else:
self.rnn = nn.GRUCell(
input_size=input_size + num_embeddings, hidden_size=hidden_size)
self.hidden_size = hidden_size
def forward(self, prev_hidden, batch_H, char_onehots):
batch_H_proj = self.i2h(batch_H)
prev_hidden_proj = paddle.unsqueeze(self.h2h(prev_hidden[0]), axis=1)
res = paddle.add(batch_H_proj, prev_hidden_proj)
res = paddle.tanh(res)
e = self.score(res)
alpha = F.softmax(e, axis=1)
alpha = paddle.transpose(alpha, [0, 2, 1])
context = paddle.squeeze(paddle.mm(alpha, batch_H), axis=1)
concat_context = paddle.concat([context, char_onehots], 1)
cur_hidden = self.rnn(concat_context, prev_hidden)
return cur_hidden, alpha
|