3

我一直在尝试实现一个基于 LSTM 的分类器来对离散语音进行分类。我用 13 mfcc 创建了特征向量。对于给定的文件，具有 [99, 13] 的 2D 向量。在遵循 mnist_irnn 示例之后，我可以设置单层 RNN 来分类我的语音文件。但现在我想向网络添加更多层。因此，我一直在尝试用两个 LSTM 层和 softmax 层作为输出层来实现网络。在这里浏览了许多帖子后，我可以按如下方式设置网络，在模型构建期间它不会抛出任何异常。

from __future__ import print_function
import numpy as np

from keras.optimizers import SGD
from keras.utils.visualize_util import plot

np.random.seed(1337)  # for reproducibility
from keras.preprocessing import sequence
from keras.utils import np_utils
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, TimeDistributedDense
from keras.layers.recurrent import LSTM
from SpeechResearch import loadData

batch_size = 5
hidden_units = 100
nb_classes = 10
print('Loading data...')
(X_train, y_train), (X_test, y_test) = loadData.load_mfcc(10, 2)

print(len(X_train), 'train sequences')
print(len(X_test), 'test sequences')
print('X_train shape:', X_train.shape)
print('X_test shape:', X_test.shape)
print('y_train shape:', y_train.shape)
print('y_test shape:', y_test.shape)
print('Build model...')

Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)
print(batch_size, 99, X_train.shape[2])
print(X_train.shape[1:])
print(X_train.shape[2])
model = Sequential()

model.add(LSTM(output_dim=hidden_units, init='uniform', inner_init='uniform',
               forget_bias_init='one', activation='tanh', inner_activation='sigmoid', return_sequences=True,
               stateful=True, batch_input_shape=(batch_size, 99, X_train.shape[2])))
# model.add(Dropout(0.5))
model.add(LSTM(output_dim=hidden_units, init='uniform', inner_init='uniform',
               forget_bias_init='one', activation='tanh', inner_activation='sigmoid', return_sequences=True,
               stateful=True, input_length=X_train.shape[2]))

model.add(TimeDistributedDense(input_dim=hidden_units, output_dim=nb_classes))
model.add(Activation('softmax'))

# try using different optimizers and different optimizer configs
sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd)

print("Train...")
model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=3, validation_data=(X_test, Y_test), show_accuracy=True)
score, acc = model.evaluate(X_test, Y_test,
                            batch_size=batch_size,
                            show_accuracy=True)
print('Test score:', score)
print('Test accuracy:', acc)

我一直在不同的点尝试不同的价值观。（目前我一直在尝试使用小样本，因此值非常小）但是，现在它在训练期间抛出异常。一些尺寸不匹配。

Using Theano backend.
Loading data...
100 train sequences
20 test sequences
X_train shape: (100, 99, 13)
X_test shape: (20, 99, 13)
y_train shape: (100,)
y_test shape: (20,)
Build model...
5 99 13
(99, 13)
13
Train...
Train on 100 samples, validate on 20 samples
Epoch 1/3

Traceback (most recent call last):
  File "/home/udani/PycharmProjects/testResearch/SpeechResearch/lstmNetwork.py", line 54, in <module>
    model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=3, validation_data=(X_test, Y_test), show_accuracy=True)
  File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 581, in fit
    shuffle=shuffle, metrics=metrics)
  File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 239, in _fit
    outs = f(ins_batch)
  File "/usr/local/lib/python2.7/dist-packages/keras/backend/theano_backend.py", line 365, in __call__
    return self.function(*inputs)
  File "/home/udani/Documents/ResearchSW/Theano/theano/compile/function_module.py", line 786, in __call__
    allow_downcast=s.allow_downcast)
  File "/home/udani/Documents/ResearchSW/Theano/theano/tensor/type.py", line 177, in filter
    data.shape))
TypeError: ('Bad input argument to theano function with name "/usr/local/lib/python2.7/dist-packages/keras/backend/theano_backend.py:362"  at index 1(0-based)', 'Wrong number of dimensions: expected 3, got 2 with shape (5, 10).')

我想知道我在这里做错了什么。我整天都在浏览代码，但我仍然无法找出尺寸不匹配的原因。

此外，如果有人能解释 output_dim 的含义，我将非常感激。（当我们在给定层中有n个节点时，是单个节点输出的向量的形状吗？它应该等于下一层的节点数吗？）

4

1 回答 1

1

您的维度有问题Y，输出应该类似于(100, 99, 10)，即一组输出序列，与特征相同，输出中只有 1 个。看来你的Y向量是不同的。方法to_categorical并不真正适用于序列，它需要一个向量。

或者，您可以输出单个向量并将其输入最后一个 LSTM 层中的密集层return_sequences=False

您也不需要有状态的网络。

于 2016-01-23T21:11:20.663 回答