我有一个用于文本分类的LSTM代码：
class SentimentLstm(object):
# Class for Sentiment Classification using LSTM's cells
def __init__(self,x_train,y_train,x_test,y_test,len_vocab,num_lstm_units=50):
# Contructor to initialize the attributes
# Reshaping the original training images from 3D to 2D.
# Training data
self.x_train=x_train
#Normalise
# Test data
self.x_test=x_test
#Normalise
# Converting the Labels to One-hot Encoding
self.y_train=y_train
self.y_test=y_test
self.len_vocab=len_vocab
#No. of LSTM units
self.num_units=num_lstm_units
def model_param(self):
# Method to do deep learning
from keras.models import Sequential
from keras.layers import Dense, Flatten, Dropout, Activation
from keras.layers import LSTM
from keras.layers.embeddings import Embedding
from keras.initializers import TruncatedNormal
tn=TruncatedNormal(mean=0.0, stddev=1/sqrt(self.x_train.shape[1]*self.x_train.shape[1]), seed=2)
self.model = Sequential()
self.model.add(Embedding(self.len_vocab,300,input_length=self.x_train.shape[1]))
# Adding LSTM cell
self.model.add(LSTM(self.num_units,dropout=0.30,kernel_initializer=tn,name="lstm_1"))
# Adding the dense output layer for Output
self.model.add(Dense(1,activation="sigmoid",name="output_layer"))
#sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
self.model.compile(loss='binary_crossentropy',
optimizer="adam",
metrics=['accuracy'])
self.model.summary()
def fit(self):
# Training the deep learning network on the training data
# Adding the callbacks for Logging
import keras
logger_tb=keras.callbacks.TensorBoard(
log_dir="logs_sentiment_lstm",
write_graph=True,
histogram_freq=5
)
self.model.fit(self.x_train, self.y_train,validation_split=0.20,
epochs=10,
batch_size=128,callbacks=[logger_tb]
)
我的训练数据形状是：
Out[29]:
(17500, 200)
有17500个文本数据样本转换为字整数，最大序列长度为200.
我的模型摘要：
Layer (type) Output Shape Param #
=================================================================
embedding_1 (Embedding) (None, 200, 300) 22221600
_________________________________________________________________
lstm_1 (LSTM) (None, 50) 70200
_________________________________________________________________
output_layer (Dense) (None, 1) 51
=================================================================
Total params: 22,291,851
Trainable params: 22,291,851
Non-trainable params: 0
_______________________________________
但是当我运行此操作时，我收到错误invalidArgument：
/usr/local/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py in raise_exception_on_not_ok_status()
465 compat.as_text(pywrap_tensorflow.TF_Message(status)),
--> 466 pywrap_tensorflow.TF_GetCode(status))
467 finally:
InvalidArgumentError: You must feed a value for placeholder tensor 'embedding_layer_input' with dtype float
[[Node: embedding_layer_input = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/gpu:0"]()]]
[[Node: output_layer_2/bias/read/_237 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_1546_output_layer_2/bias/read", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
During handling of the above exception, another exception occurred:
编辑：
初始化SentimentLstm对象。
### Instantiting the class object
sent_lstm=SentimentLstm(x_train,y_train,x_test,y_test,len(vocab))
## Normalizing and Standarizing the data
sent_lstm.model_param()
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding_layer (Embedding) (None, 200, 300) 22221600
_________________________________________________________________
lstm_1 (LSTM) (None, 50) 70200
_________________________________________________________________
output_layer (Dense) (None, 1) 51
=================================================================
Total params: 22,291,851.0
Trainable params: 22,291,851
Non-trainable params: 0.0