保存并继续训练 LSTM 网络

我试图让 LSTM 模型继续运行,因为它的最后一次运行停止了。在我尝试适应网络之前,一切都可以正常编译。然后它给出一个错误:


ValueError:检查目标时出错:预期dense_29具有3维,但得到形状为(672, 1)的数组


我检查了诸如this和this之类的各种文章, 但我没有看到我的代码有什么问题。


from keras import Sequential

from keras.preprocessing.sequence import pad_sequences

from sklearn.model_selection import train_test_split

from keras.models import Sequential,Model

from keras.layers import LSTM, Dense, Bidirectional, Input,Dropout,BatchNormalization

from keras import backend as K

from keras.engine.topology import Layer

from keras import initializers, regularizers, constraints


from keras.callbacks import ModelCheckpoint

from keras.models import load_model

import os.path

import os

filepath="Train-weights.best.hdf5"

act = 'relu'


model = Sequential()

model.add(BatchNormalization(input_shape=(10, 128)))

model.add(Bidirectional(LSTM(128, dropout=0.5, activation=act, return_sequences=True)))

model.add(Dense(1,activation='sigmoid'))


if (os.path.exists(filepath)):

   print("extending training of previous run")

   model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

   with open('model_architecture.json', 'r') as f:

      model = model_from_json(f.read())

   model.load_weights(filepath)

else:

   print("First run")      

   model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

   model.fit(x_train, y_train, validation_data=(x_val, y_val), epochs=100, batch_size=32, callbacks=callbacks_list, verbose=2)

   model.save_weights(filepath)

   with open('model_architecture.json', 'w') as f:

       f.write(model.to_json())


 checkpoint = ModelCheckpoint(filepath, monitor='val_acc', verbose=1, save_best_only=True, mode='max')

 callbacks_list = [checkpoint]


 model.fit(x_train, y_train, validation_data=(x_val, y_val), epochs=100, batch_size=32, callbacks=callbacks_list, verbose=0)


RISEBY
浏览 368回答 1
1回答

holdtom

尝试一下model.summary(),您会看到网络中最后一层(即 Dense 层)的输出形状是(None, 10, 1)。因此,您提供给模型的标签(即y_train)也必须具有 形状(num_samples, 10, 1)。如果输出形状(None, 10, 1)不是您想要的(例如,您想要(None, 1)作为模型的输出形状),那么您需要修改您的模型定义。实现这一目标的一个简单修改是return_sequences=True从 LSTM 层中删除参数。
打开App,查看更多内容
随时随地看视频慕课网APP

相关分类

Python