forgetest5
/
PaddleOCR
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

add rec_nrtr

This commit is contained in:
Topdu 2021-08-16 11:33:15 +00:00
parent 6127aad993
commit b6f0a90366
7 changed files with 1338 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

100
configs/rec/rec_mtb_nrtr.yml Normal file
View File

@ -0,0 +1,100 @@
Global:
use_gpu: True
epoch_num: 21
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec/nrtr_final/
save_epoch_step: 1
# evaluation is run every 2000 iterations
eval_batch_step: [0, 2000]
cal_metric_during_train: True
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: False
infer_img: doc/imgs_words_en/word_10.png
# for data or label process
character_dict_path:
character_type: EN_symbol
max_text_length: 25
infer_mode: False
use_space_char: True
save_res_path: ./output/rec/predicts_nrtr.txt
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.99
clip_norm: 5.0
lr:
name: Cosine
learning_rate: 0.0005
warmup_epoch: 2
regularizer:
name: 'L2'
factor: 0.
Architecture:
model_type: rec
algorithm: NRTR
in_channels: 1
Transform:
Backbone:
name: MTB
cnn_num: 2
Head:
name: TransformerOptim
d_model: 512
num_encoder_layers: 6
beam_size: -1 # When Beam size is greater than 0, it means to use beam search when evaluation.
Loss:
name: NRTRLoss
smoothing: True
PostProcess:
name: NRTRLabelDecode
Metric:
name: RecMetric
main_indicator: acc
Train:
dataset:
name: LMDBDataSet
data_dir: /paddle/data/ocr_data/training/
transforms:
- NRTRDecodeImage: # load image
img_mode: BGR
channel_first: False
- NRTRLabelEncode: # Class handling label
- PILResize:
image_shape: [100, 32]
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: True
batch_size_per_card: 512
drop_last: True
num_workers: 8
Eval:
dataset:
name: LMDBDataSet
data_dir: /paddle/data/ocr_data/evaluation/
transforms:
- NRTRDecodeImage: # load image
img_mode: BGR
channel_first: False
- NRTRLabelEncode: # Class handling label
- PILResize:
image_shape: [100, 32]
- KeepKeys:
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
loader:
shuffle: False
drop_last: False
batch_size_per_card: 256
num_workers: 1
use_shared_memory: False

28
ppocr/data/imaug/label_ops.py
View File

@ -159,6 +159,34 @@ class BaseRecLabelEncode(object):
return text_list
class NRTRLabelEncode(BaseRecLabelEncode):
""" Convert between text-label and text-index """
def __init__(self,
max_text_length,
character_dict_path=None,
character_type='EN_symbol',
use_space_char=False,
**kwargs):
super(NRTRLabelEncode,
self).__init__(max_text_length, character_dict_path,
character_type, use_space_char)
def __call__(self, data):
text = data['label']
text = self.encode(text)
if text is None:
return None
data['length'] = np.array(len(text))
text.insert(0, 2)
text.append(3)
text = text + [0] * (self.max_text_len - len(text))
data['label'] = np.array(text)
return data
def add_special_char(self, dict_character):
dict_character = ['blank','<unk>','<s>','</s>'] + dict_character
return dict_character
class CTCLabelEncode(BaseRecLabelEncode):
""" Convert between text-label and text-index """

3
ppocr/modeling/heads/__init__.py
View File

@ -26,12 +26,13 @@ def build_head(config):
from .rec_ctc_head import CTCHead
from .rec_att_head import AttentionHead
from .rec_srn_head import SRNHead
from .rec_nrtr_optim_head import TransformerOptim
# cls head
from .cls_head import ClsHead
support_dict = [
'DBHead', 'EASTHead', 'SASTHead', 'CTCHead', 'ClsHead', 'AttentionHead',
'SRNHead', 'PGHead']
'SRNHead', 'PGHead', 'TransformerOptim']
module_name = config.pop('name')

365
ppocr/modeling/heads/multiheadAttention.py Executable file
View File

@ -0,0 +1,365 @@
import paddle
from paddle import nn
import paddle.nn.functional as F
from paddle.nn import Linear
from paddle.nn.initializer import XavierUniform as xavier_uniform_
from paddle.nn.initializer import Constant as constant_
from paddle.nn.initializer import XavierNormal as xavier_normal_
zeros_ = constant_(value=0.)
ones_ = constant_(value=1.)
class MultiheadAttention(nn.Layer):
r"""Allows the model to jointly attend to information
from different representation subspaces.
See reference: Attention Is All You Need
.. math::
\text{MultiHead}(Q, K, V) = \text{Concat}(head_1,\dots,head_h)W^O
\text{where} head_i = \text{Attention}(QW_i^Q, KW_i^K, VW_i^V)
Args:
embed_dim: total dimension of the model
num_heads: parallel attention layers, or heads
Examples::
>>> multihead_attn = nn.MultiheadAttention(embed_dim, num_heads)
>>> attn_output, attn_output_weights = multihead_attn(query, key, value)
"""
def __init__(self, embed_dim, num_heads, dropout=0., bias=True, add_bias_kv=False, add_zero_attn=False):
super(MultiheadAttention, self).__init__()
self.embed_dim = embed_dim
self.num_heads = num_heads
self.dropout = dropout
self.head_dim = embed_dim // num_heads
assert self.head_dim * num_heads == self.embed_dim, "embed_dim must be divisible by num_heads"
self.scaling = self.head_dim ** -0.5
self.out_proj = Linear(embed_dim, embed_dim, bias_attr=bias)
if add_bias_kv:
self.bias_k = self.create_parameter(
shape=(1, 1, embed_dim), default_initializer=zeros_)
self.add_parameter("bias_k", self.bias_k)
self.bias_v = self.create_parameter(
shape=(1, 1, embed_dim), default_initializer=zeros_)
self.add_parameter("bias_v", self.bias_v)
else:
self.bias_k = self.bias_v = None
self.add_zero_attn = add_zero_attn
self._reset_parameters()
self.conv1 = paddle.nn.Conv2D(in_channels=embed_dim, out_channels=embed_dim, kernel_size=(1, 1))
self.conv2 = paddle.nn.Conv2D(in_channels=embed_dim, out_channels=embed_dim * 2, kernel_size=(1, 1))
self.conv3 = paddle.nn.Conv2D(in_channels=embed_dim, out_channels=embed_dim * 3, kernel_size=(1, 1))
def _reset_parameters(self):
xavier_uniform_(self.out_proj.weight)
if self.bias_k is not None:
xavier_normal_(self.bias_k)
if self.bias_v is not None:
xavier_normal_(self.bias_v)
def forward(self, query, key, value, key_padding_mask=None, incremental_state=None,
need_weights=True, static_kv=False, attn_mask=None, qkv_ = [False,False,False]):
"""
Inputs of forward function
query: [target length, batch size, embed dim]
key: [sequence length, batch size, embed dim]
value: [sequence length, batch size, embed dim]
key_padding_mask: if True, mask padding based on batch size
incremental_state: if provided, previous time steps are cashed
need_weights: output attn_output_weights
static_kv: key and value are static
Outputs of forward function
attn_output: [target length, batch size, embed dim]
attn_output_weights: [batch size, target length, sequence length]
"""
qkv_same = qkv_[0]
kv_same = qkv_[1]
tgt_len, bsz, embed_dim = query.shape
assert embed_dim == self.embed_dim
assert list(query.shape) == [tgt_len, bsz, embed_dim]
assert key.shape == value.shape
if qkv_same:
# self-attention
q, k, v = self._in_proj_qkv(query)
elif kv_same:
# encoder-decoder attention
q = self._in_proj_q(query)
if key is None:
assert value is None
k = v = None
else:
k, v = self._in_proj_kv(key)
else:
q = self._in_proj_q(query)
k = self._in_proj_k(key)
v = self._in_proj_v(value)
q *= self.scaling
if self.bias_k is not None:
assert self.bias_v is not None
self.bias_k = paddle.concat([self.bias_k for i in range(bsz)],axis=1)
self.bias_v = paddle.concat([self.bias_v for i in range(bsz)],axis=1)
k = paddle.concat([k, self.bias_k])
v = paddle.concat([v, self.bias_v])
if attn_mask is not None:
attn_mask = paddle.concat([attn_mask, paddle.zeros([attn_mask.shape[0], 1],dtype=attn_mask.dtype)], axis=1)
if key_padding_mask is not None:
key_padding_mask = paddle.concat(
[key_padding_mask,paddle.zeros([key_padding_mask.shape[0], 1],dtype=key_padding_mask.dtype)], axis=1)
q = q.reshape([tgt_len, bsz * self.num_heads, self.head_dim]).transpose([1, 0, 2])
if k is not None:
k = k.reshape([-1, bsz * self.num_heads, self.head_dim]).transpose([1, 0, 2])
if v is not None:
v = v.reshape([-1, bsz * self.num_heads, self.head_dim]).transpose([1, 0, 2])
src_len = k.shape[1]
if key_padding_mask is not None:
assert key_padding_mask.shape[0] == bsz
assert key_padding_mask.shape[1] == src_len
if self.add_zero_attn:
src_len += 1
k = paddle.concat([k, paddle.zeros((k.shape[0], 1) + k.shape[2:],dtype=k.dtype)], axis=1)
v = paddle.concat([v, paddle.zeros((v.shape[0], 1) + v.shape[2:],dtype=v.dtype)], axis=1)
if attn_mask is not None:
attn_mask = paddle.concat([attn_mask, paddle.zeros([attn_mask.shape[0], 1],dtype=attn_mask.dtype)], axis=1)
if key_padding_mask is not None:
key_padding_mask = paddle.concat(
[key_padding_mask, paddle.zeros([key_padding_mask.shape[0], 1],dtype=key_padding_mask.dtype)], axis=1)
attn_output_weights = paddle.bmm(q, k.transpose([0,2,1]))
assert list(attn_output_weights.shape) == [bsz * self.num_heads, tgt_len, src_len]
if attn_mask is not None:
attn_mask = attn_mask.unsqueeze(0)
attn_output_weights += attn_mask
if key_padding_mask is not None:
attn_output_weights = attn_output_weights.reshape([bsz, self.num_heads, tgt_len, src_len])
key = key_padding_mask.unsqueeze(1).unsqueeze(2).astype('float32')
y = paddle.full(shape=key.shape, dtype='float32', fill_value='-inf')
y = paddle.where(key==0.,key, y)
attn_output_weights += y
attn_output_weights = attn_output_weights.reshape([bsz*self.num_heads, tgt_len, src_len])
attn_output_weights = F.softmax(
attn_output_weights.astype('float32'), axis=-1,
dtype=paddle.float32 if attn_output_weights.dtype == paddle.float16 else attn_output_weights.dtype)
attn_output_weights = F.dropout(attn_output_weights, p=self.dropout, training=self.training)
attn_output = paddle.bmm(attn_output_weights, v)
assert list(attn_output.shape) == [bsz * self.num_heads, tgt_len, self.head_dim]
attn_output = attn_output.transpose([1, 0,2]).reshape([tgt_len, bsz, embed_dim])
attn_output = self.out_proj(attn_output)
if need_weights:
# average attention weights over heads
attn_output_weights = attn_output_weights.reshape([bsz, self.num_heads, tgt_len, src_len])
attn_output_weights = attn_output_weights.sum(axis=1) / self.num_heads
else:
attn_output_weights = None
return attn_output, attn_output_weights
def _in_proj_qkv(self, query):
query = query.transpose([1, 2, 0])
query = paddle.unsqueeze(query, axis=2)
res = self.conv3(query)
res = paddle.squeeze(res, axis=2)
res = res.transpose([2, 0, 1])
return res.chunk(3, axis=-1)
def _in_proj_kv(self, key):
key = key.transpose([1, 2, 0])
key = paddle.unsqueeze(key, axis=2)
res = self.conv2(key)
res = paddle.squeeze(res, axis=2)
res = res.transpose([2, 0, 1])
return res.chunk(2, axis=-1)
def _in_proj_q(self, query):
query = query.transpose([1, 2, 0])
query = paddle.unsqueeze(query, axis=2)
res = self.conv1(query)
res = paddle.squeeze(res, axis=2)
res = res.transpose([2, 0, 1])
return res
def _in_proj_k(self, key):
key = key.transpose([1, 2, 0])
key = paddle.unsqueeze(key, axis=2)
res = self.conv1(key)
res = paddle.squeeze(res, axis=2)
res = res.transpose([2, 0, 1])
return res
def _in_proj_v(self, value):
value = value.transpose([1,2,0])#(1, 2, 0)
value = paddle.unsqueeze(value, axis=2)
res = self.conv1(value)
res = paddle.squeeze(res, axis=2)
res = res.transpose([2, 0, 1])
return res
class MultiheadAttentionOptim(nn.Layer):
r"""Allows the model to jointly attend to information
from different representation subspaces.
See reference: Attention Is All You Need
.. math::
\text{MultiHead}(Q, K, V) = \text{Concat}(head_1,\dots,head_h)W^O
\text{where} head_i = \text{Attention}(QW_i^Q, KW_i^K, VW_i^V)
Args:
embed_dim: total dimension of the model
num_heads: parallel attention layers, or heads
Examples::
>>> multihead_attn = nn.MultiheadAttention(embed_dim, num_heads)
>>> attn_output, attn_output_weights = multihead_attn(query, key, value)
"""
def __init__(self, embed_dim, num_heads, dropout=0., bias=True, add_bias_kv=False, add_zero_attn=False):
super(MultiheadAttentionOptim, self).__init__()
self.embed_dim = embed_dim
self.num_heads = num_heads
self.dropout = dropout
self.head_dim = embed_dim // num_heads
assert self.head_dim * num_heads == self.embed_dim, "embed_dim must be divisible by num_heads"
self.scaling = self.head_dim ** -0.5
self.out_proj = Linear(embed_dim, embed_dim, bias_attr=bias)
self._reset_parameters()
self.conv1 = paddle.nn.Conv2D(in_channels=embed_dim, out_channels=embed_dim, kernel_size=(1, 1))
self.conv2 = paddle.nn.Conv2D(in_channels=embed_dim, out_channels=embed_dim, kernel_size=(1, 1))
self.conv3 = paddle.nn.Conv2D(in_channels=embed_dim, out_channels=embed_dim, kernel_size=(1, 1))
def _reset_parameters(self):
xavier_uniform_(self.out_proj.weight)
def forward(self, query, key, value, key_padding_mask=None, incremental_state=None,
need_weights=True, static_kv=False, attn_mask=None):
"""
Inputs of forward function
query: [target length, batch size, embed dim]
key: [sequence length, batch size, embed dim]
value: [sequence length, batch size, embed dim]
key_padding_mask: if True, mask padding based on batch size
incremental_state: if provided, previous time steps are cashed
need_weights: output attn_output_weights
static_kv: key and value are static
Outputs of forward function
attn_output: [target length, batch size, embed dim]
attn_output_weights: [batch size, target length, sequence length]
"""
tgt_len, bsz, embed_dim = query.shape
assert embed_dim == self.embed_dim
assert list(query.shape) == [tgt_len, bsz, embed_dim]
assert key.shape == value.shape
q = self._in_proj_q(query)
k = self._in_proj_k(key)
v = self._in_proj_v(value)
q *= self.scaling
q = q.reshape([tgt_len, bsz * self.num_heads, self.head_dim]).transpose([1, 0, 2])
k = k.reshape([-1, bsz * self.num_heads, self.head_dim]).transpose([1, 0, 2])
v = v.reshape([-1, bsz * self.num_heads, self.head_dim]).transpose([1, 0, 2])
src_len = k.shape[1]
if key_padding_mask is not None:
assert key_padding_mask.shape[0] == bsz
assert key_padding_mask.shape[1] == src_len
attn_output_weights = paddle.bmm(q, k.transpose([0,2,1]))
assert list(attn_output_weights.shape) == [bsz * self.num_heads, tgt_len, src_len]
if attn_mask is not None:
attn_mask = attn_mask.unsqueeze(0)
attn_output_weights += attn_mask
if key_padding_mask is not None:
attn_output_weights = attn_output_weights.reshape([bsz, self.num_heads, tgt_len, src_len])
key = key_padding_mask.unsqueeze(1).unsqueeze(2).astype('float32')
y = paddle.full(shape=key.shape, dtype='float32', fill_value='-inf')
y = paddle.where(key==0.,key, y)
attn_output_weights += y
attn_output_weights = attn_output_weights.reshape([bsz*self.num_heads, tgt_len, src_len])
attn_output_weights = F.softmax(
attn_output_weights.astype('float32'), axis=-1,
dtype=paddle.float32 if attn_output_weights.dtype == paddle.float16 else attn_output_weights.dtype)
attn_output_weights = F.dropout(attn_output_weights, p=self.dropout, training=self.training)
attn_output = paddle.bmm(attn_output_weights, v)
assert list(attn_output.shape) == [bsz * self.num_heads, tgt_len, self.head_dim]
attn_output = attn_output.transpose([1, 0,2]).reshape([tgt_len, bsz, embed_dim])
attn_output = self.out_proj(attn_output)
if need_weights:
# average attention weights over heads
attn_output_weights = attn_output_weights.reshape([bsz, self.num_heads, tgt_len, src_len])
attn_output_weights = attn_output_weights.sum(axis=1) / self.num_heads
else:
attn_output_weights = None
return attn_output, attn_output_weights
def _in_proj_q(self, query):
query = query.transpose([1, 2, 0])
query = paddle.unsqueeze(query, axis=2)
res = self.conv1(query)
res = paddle.squeeze(res, axis=2)
res = res.transpose([2, 0, 1])
return res
def _in_proj_k(self, key):
key = key.transpose([1, 2, 0])
key = paddle.unsqueeze(key, axis=2)
res = self.conv2(key)
res = paddle.squeeze(res, axis=2)
res = res.transpose([2, 0, 1])
return res
def _in_proj_v(self, value):
value = value.transpose([1,2,0])#(1, 2, 0)
value = paddle.unsqueeze(value, axis=2)
res = self.conv3(value)
res = paddle.squeeze(res, axis=2)
res = res.transpose([2, 0, 1])
return res

779
ppocr/modeling/heads/rec_nrtr_optim_head.py Normal file
View File

@ -0,0 +1,779 @@
import math
import paddle
import copy
from paddle import nn
import paddle.nn.functional as F
from paddle.nn import LayerList
from paddle.nn.initializer import XavierNormal as xavier_uniform_
from paddle.nn import Dropout, Linear, LayerNorm, Conv2D
import numpy as np
from ppocr.modeling.heads.multiheadAttention import MultiheadAttentionOptim
from paddle.nn.initializer import Constant as constant_
from paddle.nn.initializer import XavierNormal as xavier_normal_
zeros_ = constant_(value=0.)
ones_ = constant_(value=1.)
class TransformerOptim(nn.Layer):
r"""A transformer model. User is able to modify the attributes as needed. The architechture
is based on the paper "Attention Is All You Need". Ashish Vaswani, Noam Shazeer,
Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and
Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information
Processing Systems, pages 6000-6010.
Args:
d_model: the number of expected features in the encoder/decoder inputs (default=512).
nhead: the number of heads in the multiheadattention models (default=8).
num_encoder_layers: the number of sub-encoder-layers in the encoder (default=6).
num_decoder_layers: the number of sub-decoder-layers in the decoder (default=6).
dim_feedforward: the dimension of the feedforward network model (default=2048).
dropout: the dropout value (default=0.1).
custom_encoder: custom encoder (default=None).
custom_decoder: custom decoder (default=None).
Examples::
>>> transformer_model = nn.Transformer(src_vocab, tgt_vocab)
>>> transformer_model = nn.Transformer(src_vocab, tgt_vocab, nhead=16, num_encoder_layers=12)
"""
def __init__(self, d_model=512, nhead=8, num_encoder_layers=6, beam_size=0,
num_decoder_layers=6, dim_feedforward=1024, attention_dropout_rate=0.0, residual_dropout_rate=0.1,
custom_encoder=None, custom_decoder=None,in_channels=0,out_channels=0,dst_vocab_size=99,scale_embedding=True):
super(TransformerOptim, self).__init__()
self.embedding = Embeddings(
d_model=d_model,
vocab=dst_vocab_size,
padding_idx=0,
scale_embedding=scale_embedding
)
self.positional_encoding = PositionalEncoding(
dropout=residual_dropout_rate,
dim=d_model,
)
if custom_encoder is not None:
self.encoder = custom_encoder
else:
if num_encoder_layers > 0 :
encoder_layer = TransformerEncoderLayer(d_model, nhead, dim_feedforward, attention_dropout_rate, residual_dropout_rate)
self.encoder = TransformerEncoder(encoder_layer, num_encoder_layers)
else:
self.encoder = None
if custom_decoder is not None:
self.decoder = custom_decoder
else:
decoder_layer = TransformerDecoderLayer(d_model, nhead, dim_feedforward, attention_dropout_rate, residual_dropout_rate)
self.decoder = TransformerDecoder(decoder_layer, num_decoder_layers)
self._reset_parameters()
self.beam_size = beam_size
self.d_model = d_model
self.nhead = nhead
self.tgt_word_prj = nn.Linear(d_model, dst_vocab_size, bias_attr=False)
w0 = np.random.normal(0.0, d_model**-0.5,(d_model, dst_vocab_size)).astype(np.float32)
self.tgt_word_prj.weight.set_value(w0)
self.apply(self._init_weights)
def _init_weights(self, m):
if isinstance(m, nn.Conv2D):
xavier_normal_(m.weight)
if m.bias is not None:
zeros_(m.bias)
def forward_train(self,src,tgt):
tgt = tgt[:, :-1]
tgt_key_padding_mask = self.generate_padding_mask(tgt)
tgt = self.embedding(tgt).transpose([1, 0, 2])
tgt = self.positional_encoding(tgt)
tgt_mask = self.generate_square_subsequent_mask(tgt.shape[0])
if self.encoder is not None :
src = self.positional_encoding(src.transpose([1, 0, 2]))
memory = self.encoder(src)
else:
memory = src.squeeze(2).transpose([2, 0, 1])
output = self.decoder(tgt, memory, tgt_mask=tgt_mask, memory_mask=None,
tgt_key_padding_mask=tgt_key_padding_mask,
memory_key_padding_mask=None)
output = output.transpose([1, 0, 2])
logit = self.tgt_word_prj(output)
return logit
def forward(self, src, tgt=None):
r"""Take in and process masked source/target sequences.
Args:
src: the sequence to the encoder (required).
tgt: the sequence to the decoder (required).
src_mask: the additive mask for the src sequence (optional).
tgt_mask: the additive mask for the tgt sequence (optional).
memory_mask: the additive mask for the encoder output (optional).
src_key_padding_mask: the ByteTensor mask for src keys per batch (optional).
tgt_key_padding_mask: the ByteTensor mask for tgt keys per batch (optional).
memory_key_padding_mask: the ByteTensor mask for memory keys per batch (optional).
Shape:
- src: :math:`(S, N, E)`.
- tgt: :math:`(T, N, E)`.
- src_mask: :math:`(S, S)`.
- tgt_mask: :math:`(T, T)`.
- memory_mask: :math:`(T, S)`.
- src_key_padding_mask: :math:`(N, S)`.
- tgt_key_padding_mask: :math:`(N, T)`.
- memory_key_padding_mask: :math:`(N, S)`.
Note: [src/tgt/memory]_mask should be filled with
float('-inf') for the masked positions and float(0.0) else. These masks
ensure that predictions for position i depend only on the unmasked positions
j and are applied identically for each sequence in a batch.
[src/tgt/memory]_key_padding_mask should be a ByteTensor where True values are positions
that should be masked with float('-inf') and False values will be unchanged.
This mask ensures that no information will be taken from position i if
it is masked, and has a separate mask for each sequence in a batch.
- output: :math:`(T, N, E)`.
Note: Due to the multi-head attention architecture in the transformer model,
the output sequence length of a transformer is same as the input sequence
(i.e. target) length of the decode.
where S is the source sequence length, T is the target sequence length, N is the
batch size, E is the feature number
Examples:
>>> output = transformer_model(src, tgt, src_mask=src_mask, tgt_mask=tgt_mask)
"""
if tgt is not None:
return self.forward_train(src, tgt)
else:
if self.beam_size > 0 :
return self.forward_beam(src)
else:
return self.forward_test(src)
def forward_test(self, src):
bs = src.shape[0]
if self.encoder is not None :
src = self.positional_encoding(src.transpose([1, 0, 2]))
memory = self.encoder(src)
else:
memory = src.squeeze(2).transpose([2, 0, 1])
dec_seq = paddle.full((bs,1), 2, dtype=paddle.int64)
for len_dec_seq in range(1, 25):
src_enc = memory.clone()
tgt_key_padding_mask = self.generate_padding_mask(dec_seq)
dec_seq_embed = self.embedding(dec_seq).transpose([1, 0, 2])
dec_seq_embed = self.positional_encoding(dec_seq_embed)
tgt_mask = self.generate_square_subsequent_mask(dec_seq_embed.shape[0])
output = self.decoder(dec_seq_embed, src_enc, tgt_mask=tgt_mask, memory_mask=None,
tgt_key_padding_mask=tgt_key_padding_mask,
memory_key_padding_mask=None)
dec_output = output.transpose([1, 0, 2])
dec_output = dec_output[:, -1, :] # Pick the last step: (bh * bm) * d_h
word_prob = F.log_softmax(self.tgt_word_prj(dec_output), axis=1)
word_prob = word_prob.reshape([1, bs, -1])
preds_idx = word_prob.argmax(axis=2)
if paddle.equal_all(preds_idx[-1],paddle.full(preds_idx[-1].shape,3,dtype='int64')):
break
preds_prob = word_prob.max(axis=2)
dec_seq = paddle.concat([dec_seq,preds_idx.reshape([-1,1])],axis=1)
return dec_seq
def forward_beam(self,images):
''' Translation work in one batch '''
def get_inst_idx_to_tensor_position_map(inst_idx_list):
''' Indicate the position of an instance in a tensor. '''
return {inst_idx: tensor_position for tensor_position, inst_idx in enumerate(inst_idx_list)}
def collect_active_part(beamed_tensor, curr_active_inst_idx, n_prev_active_inst, n_bm):
''' Collect tensor parts associated to active instances. '''
_, *d_hs = beamed_tensor.shape
n_curr_active_inst = len(curr_active_inst_idx)
new_shape = (n_curr_active_inst * n_bm, *d_hs)
beamed_tensor = beamed_tensor.reshape([n_prev_active_inst, -1])#contiguous()
beamed_tensor = beamed_tensor.index_select(paddle.to_tensor(curr_active_inst_idx),axis=0)
beamed_tensor = beamed_tensor.reshape([*new_shape])
return beamed_tensor
def collate_active_info(
src_enc, inst_idx_to_position_map, active_inst_idx_list):
# Sentences which are still active are collected,
# so the decoder will not run on completed sentences.
n_prev_active_inst = len(inst_idx_to_position_map)
active_inst_idx = [inst_idx_to_position_map[k] for k in active_inst_idx_list]
active_inst_idx = paddle.to_tensor(active_inst_idx, dtype='int64')
active_src_enc = collect_active_part(src_enc.transpose([1, 0, 2]), active_inst_idx, n_prev_active_inst, n_bm).transpose([1, 0, 2])
active_inst_idx_to_position_map = get_inst_idx_to_tensor_position_map(active_inst_idx_list)
return active_src_enc, active_inst_idx_to_position_map
def beam_decode_step(
inst_dec_beams, len_dec_seq, enc_output, inst_idx_to_position_map, n_bm, memory_key_padding_mask):
''' Decode and update beam status, and then return active beam idx '''
def prepare_beam_dec_seq(inst_dec_beams, len_dec_seq):
dec_partial_seq = [b.get_current_state() for b in inst_dec_beams if not b.done]
dec_partial_seq = paddle.stack(dec_partial_seq)
dec_partial_seq = dec_partial_seq.reshape([-1, len_dec_seq])
return dec_partial_seq
def prepare_beam_memory_key_padding_mask(inst_dec_beams, memory_key_padding_mask, n_bm):
keep = []
for idx in (memory_key_padding_mask):
if not inst_dec_beams[idx].done:
keep.append(idx)
memory_key_padding_mask = memory_key_padding_mask[paddle.to_tensor(keep)]
len_s = memory_key_padding_mask.shape[-1]
n_inst = memory_key_padding_mask.shape[0]
memory_key_padding_mask = paddle.concat([memory_key_padding_mask for i in range(n_bm)],axis=1)
memory_key_padding_mask = memory_key_padding_mask.reshape([n_inst * n_bm, len_s])#repeat(1, n_bm)
return memory_key_padding_mask
def predict_word(dec_seq, enc_output, n_active_inst, n_bm, memory_key_padding_mask):
tgt_key_padding_mask = self.generate_padding_mask(dec_seq)
dec_seq = self.embedding(dec_seq).transpose([1, 0, 2])
dec_seq = self.positional_encoding(dec_seq)
tgt_mask = self.generate_square_subsequent_mask(dec_seq.shape[0])
dec_output = self.decoder(
dec_seq, enc_output,
tgt_mask=tgt_mask,
tgt_key_padding_mask=tgt_key_padding_mask,
memory_key_padding_mask=memory_key_padding_mask,
).transpose([1, 0, 2])
dec_output = dec_output[:, -1, :] # Pick the last step: (bh * bm) * d_h
word_prob = F.log_softmax(self.tgt_word_prj(dec_output), axis=1)
word_prob = word_prob.reshape([n_active_inst, n_bm, -1])
return word_prob
def collect_active_inst_idx_list(inst_beams, word_prob, inst_idx_to_position_map):
active_inst_idx_list = []
for inst_idx, inst_position in inst_idx_to_position_map.items():
is_inst_complete = inst_beams[inst_idx].advance(word_prob[inst_position])
if not is_inst_complete:
active_inst_idx_list += [inst_idx]
return active_inst_idx_list
n_active_inst = len(inst_idx_to_position_map)
dec_seq = prepare_beam_dec_seq(inst_dec_beams, len_dec_seq)
memory_key_padding_mask = None
word_prob = predict_word(dec_seq, enc_output, n_active_inst, n_bm, memory_key_padding_mask)
# Update the beam with predicted word prob information and collect incomplete instances
active_inst_idx_list = collect_active_inst_idx_list(
inst_dec_beams, word_prob, inst_idx_to_position_map)
return active_inst_idx_list
def collect_hypothesis_and_scores(inst_dec_beams, n_best):
all_hyp, all_scores = [], []
for inst_idx in range(len(inst_dec_beams)):
scores, tail_idxs = inst_dec_beams[inst_idx].sort_scores()
all_scores += [scores[:n_best]]
hyps = [inst_dec_beams[inst_idx].get_hypothesis(i) for i in tail_idxs[:n_best]]
all_hyp += [hyps]
return all_hyp, all_scores
with paddle.no_grad():
#-- Encode
if self.encoder is not None :
src = self.positional_encoding(images.transpose([1, 0, 2]))
src_enc = self.encoder(src).transpose([1, 0, 2])
else:
src_enc = images.squeeze(2).transpose([0, 2, 1])
#-- Repeat data for beam search
n_bm = self.beam_size
n_inst, len_s, d_h = src_enc.shape
src_enc = paddle.concat([src_enc for i in range(n_bm)],axis=1)
src_enc = src_enc.reshape([n_inst * n_bm, len_s, d_h]).transpose([1, 0, 2])#repeat(1, n_bm, 1)
#-- Prepare beams
inst_dec_beams = [Beam(n_bm) for _ in range(n_inst)]
#-- Bookkeeping for active or not
active_inst_idx_list = list(range(n_inst))
inst_idx_to_position_map = get_inst_idx_to_tensor_position_map(active_inst_idx_list)
#-- Decode
for len_dec_seq in range(1, 25):
src_enc_copy = src_enc.clone()
active_inst_idx_list = beam_decode_step(
inst_dec_beams, len_dec_seq, src_enc_copy, inst_idx_to_position_map, n_bm, None)
if not active_inst_idx_list:
break # all instances have finished their path to <EOS>
src_enc, inst_idx_to_position_map = collate_active_info(
src_enc_copy, inst_idx_to_position_map, active_inst_idx_list)
batch_hyp, batch_scores = collect_hypothesis_and_scores(inst_dec_beams, 1)
result_hyp = []
for bs_hyp in batch_hyp:
bs_hyp_pad =bs_hyp[0]+[3]*(25-len(bs_hyp[0]))
result_hyp.append(bs_hyp_pad)
return paddle.to_tensor(np.array(result_hyp),dtype=paddle.int64)
def generate_square_subsequent_mask(self, sz):
r"""Generate a square mask for the sequence. The masked positions are filled with float('-inf').
Unmasked positions are filled with float(0.0).
"""
mask = paddle.zeros([sz, sz],dtype='float32')
mask_inf = paddle.triu(paddle.full(shape=[sz,sz], dtype='float32', fill_value='-inf'),diagonal=1)
mask = mask+mask_inf
return mask
def generate_padding_mask(self, x):
padding_mask = x.equal(paddle.to_tensor(0,dtype=x.dtype))
return padding_mask
def _reset_parameters(self):
r"""Initiate parameters in the transformer model."""
for p in self.parameters():
if p.dim() > 1:
xavier_uniform_(p)
class TransformerEncoder(nn.Layer):
r"""TransformerEncoder is a stack of N encoder layers
Args:
encoder_layer: an instance of the TransformerEncoderLayer() class (required).
num_layers: the number of sub-encoder-layers in the encoder (required).
norm: the layer normalization component (optional).
Examples::
>>> encoder_layer = nn.TransformerEncoderLayer(d_model, nhead)
>>> transformer_encoder = nn.TransformerEncoder(encoder_layer, num_layers)
"""
def __init__(self, encoder_layer, num_layers):
super(TransformerEncoder, self).__init__()
self.layers = _get_clones(encoder_layer, num_layers)
self.num_layers = num_layers
def forward(self, src):
r"""Pass the input through the endocder layers in turn.
Args:
src: the sequnce to the encoder (required).
mask: the mask for the src sequence (optional).
src_key_padding_mask: the mask for the src keys per batch (optional).
Shape:
see the docs in Transformer class.
"""
output = src
for i in range(self.num_layers):
output = self.layers[i](output, src_mask=None,
src_key_padding_mask=None)
return output
class TransformerDecoder(nn.Layer):
r"""TransformerDecoder is a stack of N decoder layers
Args:
decoder_layer: an instance of the TransformerDecoderLayer() class (required).
num_layers: the number of sub-decoder-layers in the decoder (required).
norm: the layer normalization component (optional).
Examples::
>>> decoder_layer = nn.TransformerDecoderLayer(d_model, nhead)
>>> transformer_decoder = nn.TransformerDecoder(decoder_layer, num_layers)
"""
def __init__(self, decoder_layer, num_layers):
super(TransformerDecoder, self).__init__()
self.layers = _get_clones(decoder_layer, num_layers)
self.num_layers = num_layers
def forward(self, tgt, memory, tgt_mask=None,
memory_mask=None, tgt_key_padding_mask=None,
memory_key_padding_mask=None):
r"""Pass the inputs (and mask) through the decoder layer in turn.
Args:
tgt: the sequence to the decoder (required).
memory: the sequnce from the last layer of the encoder (required).
tgt_mask: the mask for the tgt sequence (optional).
memory_mask: the mask for the memory sequence (optional).
tgt_key_padding_mask: the mask for the tgt keys per batch (optional).
memory_key_padding_mask: the mask for the memory keys per batch (optional).
Shape:
see the docs in Transformer class.
"""
output = tgt
for i in range(self.num_layers):
output = self.layers[i](output, memory, tgt_mask=tgt_mask,
memory_mask=memory_mask,
tgt_key_padding_mask=tgt_key_padding_mask,
memory_key_padding_mask=memory_key_padding_mask)
return output
class TransformerEncoderLayer(nn.Layer):
r"""TransformerEncoderLayer is made up of self-attn and feedforward network.
This standard encoder layer is based on the paper "Attention Is All You Need".
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez,
Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in
Neural Information Processing Systems, pages 6000-6010. Users may modify or implement
in a different way during application.
Args:
d_model: the number of expected features in the input (required).
nhead: the number of heads in the multiheadattention models (required).
dim_feedforward: the dimension of the feedforward network model (default=2048).
dropout: the dropout value (default=0.1).
Examples::
>>> encoder_layer = nn.TransformerEncoderLayer(d_model, nhead)
"""
def __init__(self, d_model, nhead, dim_feedforward=2048, attention_dropout_rate=0.0, residual_dropout_rate=0.1):
super(TransformerEncoderLayer, self).__init__()
self.self_attn = MultiheadAttentionOptim(d_model, nhead, dropout=attention_dropout_rate)
self.conv1 = Conv2D(in_channels=d_model, out_channels=dim_feedforward, kernel_size=(1, 1))
self.conv2 = Conv2D(in_channels=dim_feedforward, out_channels=d_model, kernel_size=(1, 1))
self.norm1 = LayerNorm(d_model)
self.norm2 = LayerNorm(d_model)
self.dropout1 = Dropout(residual_dropout_rate)
self.dropout2 = Dropout(residual_dropout_rate)
def forward(self, src, src_mask=None, src_key_padding_mask=None):
r"""Pass the input through the endocder layer.
Args:
src: the sequnce to the encoder layer (required).
src_mask: the mask for the src sequence (optional).
src_key_padding_mask: the mask for the src keys per batch (optional).
Shape:
see the docs in Transformer class.
"""
src2 = self.self_attn(src, src, src, attn_mask=src_mask,
key_padding_mask=src_key_padding_mask)[0]
src = src + self.dropout1(src2)
src = self.norm1(src)
src = src.transpose([1, 2, 0])
src = paddle.unsqueeze(src, 2)
src2 = self.conv2(F.relu(self.conv1(src)))
src2 = paddle.squeeze(src2, 2)
src2 = src2.transpose([2, 0, 1])
src = paddle.squeeze(src, 2)
src = src.transpose([2, 0, 1])
src = src + self.dropout2(src2)
src = self.norm2(src)
return src
class TransformerDecoderLayer(nn.Layer):
r"""TransformerDecoderLayer is made up of self-attn, multi-head-attn and feedforward network.
This standard decoder layer is based on the paper "Attention Is All You Need".
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez,
Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in
Neural Information Processing Systems, pages 6000-6010. Users may modify or implement
in a different way during application.
Args:
d_model: the number of expected features in the input (required).
nhead: the number of heads in the multiheadattention models (required).
dim_feedforward: the dimension of the feedforward network model (default=2048).
dropout: the dropout value (default=0.1).
Examples::
>>> decoder_layer = nn.TransformerDecoderLayer(d_model, nhead)
"""
def __init__(self, d_model, nhead, dim_feedforward=2048, attention_dropout_rate=0.0, residual_dropout_rate=0.1):
super(TransformerDecoderLayer, self).__init__()
self.self_attn = MultiheadAttentionOptim(d_model, nhead, dropout=attention_dropout_rate)
self.multihead_attn = MultiheadAttentionOptim(d_model, nhead, dropout=attention_dropout_rate)
self.conv1 = Conv2D(in_channels=d_model, out_channels=dim_feedforward, kernel_size=(1, 1))
self.conv2 = Conv2D(in_channels=dim_feedforward, out_channels=d_model, kernel_size=(1, 1))
self.norm1 = LayerNorm(d_model)
self.norm2 = LayerNorm(d_model)
self.norm3 = LayerNorm(d_model)
self.dropout1 = Dropout(residual_dropout_rate)
self.dropout2 = Dropout(residual_dropout_rate)
self.dropout3 = Dropout(residual_dropout_rate)
def forward(self, tgt, memory, tgt_mask=None, memory_mask=None,
tgt_key_padding_mask=None, memory_key_padding_mask=None):
r"""Pass the inputs (and mask) through the decoder layer.
Args:
tgt: the sequence to the decoder layer (required).
memory: the sequnce from the last layer of the encoder (required).
tgt_mask: the mask for the tgt sequence (optional).
memory_mask: the mask for the memory sequence (optional).
tgt_key_padding_mask: the mask for the tgt keys per batch (optional).
memory_key_padding_mask: the mask for the memory keys per batch (optional).
Shape:
see the docs in Transformer class.
"""
tgt2 = self.self_attn(tgt, tgt, tgt, attn_mask=tgt_mask,
key_padding_mask=tgt_key_padding_mask)[0]
tgt = tgt + self.dropout1(tgt2)
tgt = self.norm1(tgt)
tgt2 = self.multihead_attn(tgt, memory, memory, attn_mask=memory_mask,
key_padding_mask=memory_key_padding_mask)[0]
tgt = tgt + self.dropout2(tgt2)
tgt = self.norm2(tgt)
# default
tgt = tgt.transpose([1, 2, 0])
tgt = paddle.unsqueeze(tgt, 2)
tgt2 = self.conv2(F.relu(self.conv1(tgt)))
tgt2 = paddle.squeeze(tgt2, 2)
tgt2 = tgt2.transpose([2, 0, 1])
tgt = paddle.squeeze(tgt, 2)
tgt = tgt.transpose([2, 0, 1])
tgt = tgt + self.dropout3(tgt2)
tgt = self.norm3(tgt)
return tgt
def _get_clones(module, N):
return LayerList([copy.deepcopy(module) for i in range(N)])
class PositionalEncoding(nn.Layer):
r"""Inject some information about the relative or absolute position of the tokens
in the sequence. The positional encodings have the same dimension as
the embeddings, so that the two can be summed. Here, we use sine and cosine
functions of different frequencies.
.. math::
\text{PosEncoder}(pos, 2i) = sin(pos/10000^(2i/d_model))
\text{PosEncoder}(pos, 2i+1) = cos(pos/10000^(2i/d_model))
\text{where pos is the word position and i is the embed idx)
Args:
d_model: the embed dim (required).
dropout: the dropout value (default=0.1).
max_len: the max. length of the incoming sequence (default=5000).
Examples:
>>> pos_encoder = PositionalEncoding(d_model)
"""
def __init__(self, dropout, dim, max_len=5000):
super(PositionalEncoding, self).__init__()
self.dropout = nn.Dropout(p=dropout)
pe = paddle.zeros([max_len, dim])
position = paddle.arange(0, max_len, dtype=paddle.float32).unsqueeze(1)
div_term = paddle.exp(paddle.arange(0, dim, 2).astype('float32') * (-math.log(10000.0) / dim))
pe[:, 0::2] = paddle.sin(position * div_term)
pe[:, 1::2] = paddle.cos(position * div_term)
pe = pe.unsqueeze(0)
pe = pe.transpose([1, 0, 2])
self.register_buffer('pe', pe)
def forward(self, x):
r"""Inputs of forward function
Args:
x: the sequence fed to the positional encoder model (required).
Shape:
x: [sequence length, batch size, embed dim]
output: [sequence length, batch size, embed dim]
Examples:
>>> output = pos_encoder(x)
"""
x = x + self.pe[:x.shape[0], :]
return self.dropout(x)
class PositionalEncoding_2d(nn.Layer):
r"""Inject some information about the relative or absolute position of the tokens
in the sequence. The positional encodings have the same dimension as
the embeddings, so that the two can be summed. Here, we use sine and cosine
functions of different frequencies.
.. math::
\text{PosEncoder}(pos, 2i) = sin(pos/10000^(2i/d_model))
\text{PosEncoder}(pos, 2i+1) = cos(pos/10000^(2i/d_model))
\text{where pos is the word position and i is the embed idx)
Args:
d_model: the embed dim (required).
dropout: the dropout value (default=0.1).
max_len: the max. length of the incoming sequence (default=5000).
Examples:
>>> pos_encoder = PositionalEncoding(d_model)
"""
def __init__(self, dropout, dim, max_len=5000):
super(PositionalEncoding_2d, self).__init__()
self.dropout = nn.Dropout(p=dropout)
pe = paddle.zeros([max_len, dim])
position = paddle.arange(0, max_len, dtype=paddle.float32).unsqueeze(1)
div_term = paddle.exp(paddle.arange(0, dim, 2).astype('float32') * (-math.log(10000.0) / dim))
pe[:, 0::2] = paddle.sin(position * div_term)
pe[:, 1::2] = paddle.cos(position * div_term)
pe = pe.unsqueeze(0).transpose([1, 0, 2])
self.register_buffer('pe', pe)
self.avg_pool_1 = nn.AdaptiveAvgPool2D((1, 1))
self.linear1 = nn.Linear(dim, dim)
self.linear1.weight.data.fill_(1.)
self.avg_pool_2 = nn.AdaptiveAvgPool2D((1, 1))
self.linear2 = nn.Linear(dim, dim)
self.linear2.weight.data.fill_(1.)
def forward(self, x):
r"""Inputs of forward function
Args:
x: the sequence fed to the positional encoder model (required).
Shape:
x: [sequence length, batch size, embed dim]
output: [sequence length, batch size, embed dim]
Examples:
>>> output = pos_encoder(x)
"""
w_pe = self.pe[:x.shape[-1], :]
w1 = self.linear1(self.avg_pool_1(x).squeeze()).unsqueeze(0)
w_pe = w_pe * w1
w_pe = w_pe.transpose([1, 2, 0])
w_pe = w_pe.unsqueeze(2)
h_pe = self.pe[:x.shape[-2], :]
w2 = self.linear2(self.avg_pool_2(x).squeeze()).unsqueeze(0)
h_pe = h_pe * w2
h_pe = h_pe.transpose([1, 2, 0])
h_pe = h_pe.unsqueeze(3)
x = x + w_pe + h_pe
x = x.reshape([x.shape[0], x.shape[1], x.shape[2] * x.shape[3]]).transpose([2,0,1])
return self.dropout(x)
class Embeddings(nn.Layer):
def __init__(self, d_model, vocab, padding_idx, scale_embedding):
super(Embeddings, self).__init__()
self.embedding = nn.Embedding(vocab, d_model, padding_idx=padding_idx)
w0 = np.random.normal(0.0, d_model**-0.5,(vocab, d_model)).astype(np.float32)
self.embedding.weight.set_value(w0)
self.d_model = d_model
self.scale_embedding = scale_embedding
def forward(self, x):
if self.scale_embedding:
x = self.embedding(x)
return x * math.sqrt(self.d_model)
return self.embedding(x)
class Beam():
''' Beam search '''
def __init__(self, size, device=False):
self.size = size
self._done = False
# The score for each translation on the beam.
self.scores = paddle.zeros((size,), dtype=paddle.float32)
self.all_scores = []
# The backpointers at each time-step.
self.prev_ks = []
# The outputs at each time-step.
self.next_ys = [paddle.full((size,), 0, dtype=paddle.int64)]
self.next_ys[0][0] = 2
def get_current_state(self):
"Get the outputs for the current timestep."
return self.get_tentative_hypothesis()
def get_current_origin(self):
"Get the backpointers for the current timestep."
return self.prev_ks[-1]
@property
def done(self):
return self._done
def advance(self, word_prob):
"Update beam status and check if finished or not."
num_words = word_prob.shape[1]
# Sum the previous scores.
if len(self.prev_ks) > 0:
beam_lk = word_prob + self.scores.unsqueeze(1).expand_as(word_prob)
else:
beam_lk = word_prob[0]
flat_beam_lk = beam_lk.reshape([-1])
best_scores, best_scores_id = flat_beam_lk.topk(self.size, 0, True, True) # 1st sort
self.all_scores.append(self.scores)
self.scores = best_scores
# bestScoresId is flattened as a (beam x word) array,
# so we need to calculate which word and beam each score came from
prev_k = best_scores_id // num_words
self.prev_ks.append(prev_k)
self.next_ys.append(best_scores_id - prev_k * num_words)
# End condition is when top-of-beam is EOS.
if self.next_ys[-1][0] == 3 :
self._done = True
self.all_scores.append(self.scores)
return self._done
def sort_scores(self):
"Sort the scores."
return self.scores, paddle.to_tensor([i for i in range(self.scores.shape[0])],dtype='int32')
def get_the_best_score_and_idx(self):
"Get the score of the best in the beam."
scores, ids = self.sort_scores()
return scores[1], ids[1]
def get_tentative_hypothesis(self):
"Get the decoded sequence for the current timestep."
if len(self.next_ys) == 1:
dec_seq = self.next_ys[0].unsqueeze(1)
else:
_, keys = self.sort_scores()
hyps = [self.get_hypothesis(k) for k in keys]
hyps = [[2] + h for h in hyps]
dec_seq = paddle.to_tensor(hyps, dtype='int64')
return dec_seq
def get_hypothesis(self, k):
""" Walk back to construct the full hypothesis. """
hyp = []
for j in range(len(self.prev_ks) - 1, -1, -1):
hyp.append(self.next_ys[j+1][k])
k = self.prev_ks[j][k]
return list(map(lambda x: x.item(), hyp[::-1]))

63
ppocr/postprocess/rec_postprocess.py
View File

@ -156,6 +156,69 @@ class DistillationCTCLabelDecode(CTCLabelDecode):
return output
class NRTRLabelDecode(BaseRecLabelDecode):
""" Convert between text-label and text-index """
def __init__(self,
character_dict_path=None,
character_type='EN_symbol',
use_space_char=True,
**kwargs):
super(NRTRLabelDecode, self).__init__(character_dict_path,
character_type, use_space_char)
def __call__(self, preds, label=None, *args, **kwargs):
if preds.dtype == paddle.int64:
if isinstance(preds, paddle.Tensor):
preds = preds.numpy()
if preds[0][0]==2:
preds_idx = preds[:,1:]
else:
preds_idx = preds
text = self.decode(preds_idx)
if label is None:
return text
label = self.decode(label[:,1:])
else:
if isinstance(preds, paddle.Tensor):
preds = preds.numpy()
preds_idx = preds.argmax(axis=2)
preds_prob = preds.max(axis=2)
text = self.decode(preds_idx, preds_prob, is_remove_duplicate=False)
if label is None:
return text
label = self.decode(label[:,1:])
return text, label
def add_special_char(self, dict_character):
dict_character = ['blank','<unk>','<s>','</s>'] + dict_character
return dict_character
def decode(self, text_index, text_prob=None, is_remove_duplicate=False):
""" convert text-index into text-label. """
result_list = []
batch_size = len(text_index)
for batch_idx in range(batch_size):
char_list = []
conf_list = []
for idx in range(len(text_index[batch_idx])):
if text_index[batch_idx][idx] == 3: # end
break
try:
char_list.append(self.character[int(text_index[batch_idx][idx])])
except:
continue
if text_prob is not None:
conf_list.append(text_prob[batch_idx][idx])
else:
conf_list.append(1)
text = ''.join(char_list)
result_list.append((text.lower(), np.mean(conf_list)))
return result_list
class AttnLabelDecode(BaseRecLabelDecode):
""" Convert between text-label and text-index """

2
tools/eval.py
View File

@ -22,7 +22,6 @@ import sys
__dir__ = os.path.dirname(os.path.abspath(__file__))
sys.path.append(__dir__)
sys.path.append(os.path.abspath(os.path.join(__dir__, '..')))
from ppocr.data import build_dataloader
from ppocr.modeling.architectures import build_model
from ppocr.postprocess import build_post_process
@ -31,7 +30,6 @@ from ppocr.utils.save_load import init_model
from ppocr.utils.utility import print_dict
import tools.program as program
def main():
global_config = config['Global']
# build dataloader