【发布时间】：2018-04-03 07:54:25
【问题描述】：
我已经训练了一个命名实体识别模型，在保存并加载它之后，它在同一个 IPython 会话中给出了正确的预测，但是每当我关闭会话并再次打开它时，加载的模型预测会随机。你能帮我解决这个问题吗？
我已经使用 hdf5 格式保存了模型：
Model.save("filename")
我正在使用以下方式加载它：
Model.load_model("filename")
这是我的完整代码
import pandas as pd
import numpy as np
import os
from keras.preprocessing.sequence import pad_sequences
from keras.utils import to_categorical
from sklearn.model_selection import train_test_split
from keras.models import Model, Input,load_model
from keras.layers import LSTM, Embedding, Dense, TimeDistributed, Dropout,
Bidirectional
from nltk import pos_tag, word_tokenize,sent_tokenize
data = pd.read_csv("E:\ml tut\entity recognition\exdataset.csv",
encoding="latin1")
data = data.fillna(method="ffill")
words = list(set(data["Word"].values))
words.append("ENDPAD")
n_words = len(words); n_words
tags = list(set(data["Tag"].values))
n_tags = len(tags); n_tags
class SentenceGetter(object):
def __init__(self, data):
self.n_sent = 1
self.data = data
self.empty = False
agg_func = lambda s: [((w, p), t) for w, p, t in
zip(s["Word"].values.tolist(),s["POS"].values.tolist(),
s["Tag"].values.tolist())]
self.grouped = self.data.groupby("Sentence #").apply(agg_func)
self.sentences = [s for s in self.grouped]
def get_next(self):
try:
s = self.grouped["Sentence: {}".format(self.n_sent)]
self.n_sent += 1
return s
except:
return None
getter = SentenceGetter(data)
sent = getter.get_next()
print(sent)
sentences = getter.sentences
max_len = 50
word2idx = {w: i for i, w in enumerate(words)}
tag2idx = {t: i for i, t in enumerate(tags)}
input = Input(shape=(max_len,))
model = Embedding(input_dim=n_words, output_dim=50, input_length=max_len)
(input)
model = Dropout(0.1)(model)
model = Bidirectional(LSTM(units=100, return_sequences=True,
recurrent_dropout=0.1))(model)
out = TimeDistributed(Dense(n_tags, activation="softmax"))(model)
if os.path.exists('my_model.h5'):
print("loading model")
model = load_model('my_model.h5')
else:
print("training model")
X = [[word2idx[w[0][0]] for w in s] for s in sentences]
X = pad_sequences(maxlen=max_len, sequences=X, padding="post",
value=n_words - 1)
y = [[tag2idx[w[1]] for w in s] for s in sentences]
y = pad_sequences(maxlen=max_len, sequences=y, padding="post",
value=tag2idx["O"])
y = [to_categorical(i, num_classes=n_tags) for i in y]
X_tr, X_te, y_tr, y_te = train_test_split(X, y, test_size=0.1)
model = Model(input, out)
model.compile(optimizer="rmsprop", loss="categorical_crossentropy",
metrics=["accuracy"])
model.fit(X_tr, np.array(y_tr), batch_size=32, epochs=5,
validation_split=0.1, verbose=1)
model.save('my_model.h5')
my_input="Albert Einstein is a great guy,he lives in berlin, Germany."
print("--------------")
test_sentence = word_tokenize(my_input)
x_test_sent = pad_sequences(sequences=[[word2idx.get(w, 0) for w in
test_sentence]],padding="post", value=0, maxlen=max_len)
i = 0
p = model.predict(np.array([x_test_sent[i]]))
p = np.argmax(p, axis=-1)
print("{:15}||{}".format("Word", "Prediction"))
print(30 * "=")
for w, pred in zip(test_sentence, p[0]):
if w != 0:
print("{:15}: {}".format(w, tags[pred]))
【问题讨论】：
-
请不要使用评论空间进行此类澄清 - 改为编辑和更新您的帖子
-
尝试腌制你的实用字典，并在重新启动会话并重建它们时，加载前一个会话并相互比较。很可能每个新会话都会得到不同的索引，这会破坏模型的性能——不幸的是，没有数据就无法测试它。
标签： machine-learning nlp keras