-
Notifications
You must be signed in to change notification settings - Fork 3.1k
-
Beta Was this translation helpful? Give feedback.
All reactions
Answered by
joey12300
May 20, 2021
@Wakp 我刚使用您的代码写了一版,可作参考
import paddle
import paddle.nn as nn
from paddlenlp.transformers import BertModel, BertTokenizer, ErnieModel, ErnieTokenizer
from paddlenlp.layers import crf
from paddle.static import InputSpec
import numpy as np
class MutilErnieCrf(nn.Layer):
def __init__(self, out_num=3, model_name_or_path='bert-wwm-chinese', dropout=None):
super(MutilErnieCrf, self).__init__()
self.ernie = BertModel.from_pretrained(model_name_or_path)
self.linear_to_label = nn.Linear(768, out_num)
self.crf = crf.LinearChainCrf(out_num, crf_lr=0.1, with_start_stop_tag=False)
self.crf_loss = crf.LinearChainCrfLoss(self.crf)
self.viterbi = crf.Vi...Replies: 5 comments
-
@Wakp 你好,请问一下你的padldenlp的版本是多少呢?方便提供代码吗?
Beta Was this translation helpful? Give feedback.
All reactions
0 replies
-
你好,使用的paddlenlp 2.0.0rc18c
我提供一个demo,经调试我发现可能是这个crf代码里面的一些写法在动态转静态时无法被识别和转换导致的。
比如crf.py文件中的389行: "scores, last_ids = alpha.max(1), alpha.argmax(1).numpy().tolist()" 在被转换时会被误解析成"onvert_call(alpha.argmax)(1).tolist)()",此外像python 中的常用函数"reversed()"在动转静时均会报错。
———————————————————demo———————————————————
import paddle
import paddle.nn as nn
from paddlenlp.transformers import BertModel, BertTokenizer, ErnieModel, ErnieTokenizer
from paddlenlp.layers import crf
import numpy as np
class MutilErnieCrf(nn.Layer):
def __init__(self, out_num=3, model_name_or_path='bert-wwm-chinese', dropout=None):
super(MutilErnieCrf, self).__init__()
self.ernie = BertModel.from_pretrained(model_name_or_path)
self.linear_to_label = nn.Linear(768, out_num)
self.crf = crf.LinearChainCrf(out_num, crf_lr=0.1, with_start_stop_tag=False)
self.crf_loss = crf.LinearChainCrfLoss(self.crf)
self.viterbi = crf.ViterbiDecoder(self.crf.transitions, with_start_stop_tag=False)
self.relu = nn.ReLU6()
self.dropout = nn.Dropout(dropout if dropout is not None else 0.1)
def forward(self, X, lengths):
embedding = self.ernie(X)[0]
seq_len = embedding.shape[1]
feature_drop = self.dropout(embedding)
feature_linear = self.linear_to_label(feature_drop)
res_feature = self.relu(feature_linear)
scores, path = self.viterbi(res_feature, lengths)
batch_path = list(path.numpy()) + [0] * (seq_len - len(path))
return batch_path
def compute_loss(self, inputs, lengths, labels, old_version_labels=None):
loss = self.crf_loss(inputs, lengths, labels, old_version_labels=None)
return loss
inputs = np.asarray([[1, 2, 3, 4, 5, 6, 7, 8]], dtype="int32")
lengths = np.asarray([8], dtype="int64")
labels = np.asarray([1, 2, 3, 1, 2, 3, 1, 2], dtype="int64")
inputs_tensor = paddle.to_tensor(inputs, dtype="int64")
lengths_tensor = paddle.to_tensor(lengths, dtype="int64")
labels_tensor = paddle.to_tensor(labels, dtype="int64")
model = MutilErnieCrf()
Y = model(inputs_tensor, lengths_tensor)
print(Y)
path = "example.dy_model/linear"
paddle.jit.save(
layer=model,
path=path,
input_spec=[inputs_tensor, lengths_tensor])
Beta Was this translation helpful? Give feedback.
All reactions
0 replies
-
@Wakp 您好,目前CRF已经在最新版(rc25)支持动转静。您的代码batch_path = list(path.numpy()) + [0] * (seq_len - len(path))中有numpy()的语法,动转静并不支持,可以直接使用返回的path作为batch_path。
可以尝试pip install --upgrade paddlenlp -i https://pypi.org/simple更新paddlenlp。可参考lac的模型导出示例完成动转静,注意InputSpce参数的写法。https://github.com/PaddlePaddle/PaddleNLP/blob/develop/examples/lexical_analysis/export_model.py。
Beta Was this translation helpful? Give feedback.
All reactions
0 replies
-
好的,谢谢
Beta Was this translation helpful? Give feedback.
All reactions
0 replies
-
@Wakp 我刚使用您的代码写了一版,可作参考
import paddle
import paddle.nn as nn
from paddlenlp.transformers import BertModel, BertTokenizer, ErnieModel, ErnieTokenizer
from paddlenlp.layers import crf
from paddle.static import InputSpec
import numpy as np
class MutilErnieCrf(nn.Layer):
def __init__(self, out_num=3, model_name_or_path='bert-wwm-chinese', dropout=None):
super(MutilErnieCrf, self).__init__()
self.ernie = BertModel.from_pretrained(model_name_or_path)
self.linear_to_label = nn.Linear(768, out_num)
self.crf = crf.LinearChainCrf(out_num, crf_lr=0.1, with_start_stop_tag=False)
self.crf_loss = crf.LinearChainCrfLoss(self.crf)
self.viterbi = crf.ViterbiDecoder(self.crf.transitions, with_start_stop_tag=False)
self.relu = nn.ReLU6()
self.dropout = nn.Dropout(dropout if dropout is not None else 0.1)
def forward(self, X, lengths):
embedding = self.ernie(X)[0]
seq_len = embedding.shape[1]
feature_drop = self.dropout(embedding)
feature_linear = self.linear_to_label(feature_drop)
res_feature = self.relu(feature_linear)
scores, path = self.viterbi(res_feature, lengths)
return path
def compute_loss(self, inputs, lengths, labels, old_version_labels=None):
loss = self.crf_loss(inputs, lengths, labels, old_version_labels=None)
return loss
model=MutilErnieCrf()
paddle.jit.to_static(model, input_spec=[
InputSpec(shape=[None, None], dtype="int64", name='token_ids'),
InputSpec(shape=[None], dtype="int64", name='length')])
paddle.jit.save(model, "test")
Beta Was this translation helpful? Give feedback.
All reactions
-
👍 2
0 replies
Answer selected by
ZeyuChen
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment