在 CNTK 中处理序列
让我们通过首先了解长短期记忆网络来了解 CNTK 中的序列。
长短期记忆网络 (LSTM)
Hochreiter & Schmidhuber 介绍了长短期记忆 (LSTM) 网络。它解决了获得一个基本的循环层来长时间记住事物的问题。LSTM 的架构如上图所示。正如我们所看到的,它具有输入神经元、记忆细胞和输出神经元。为了解决梯度消失问题,长期短期记忆网络使用显式记忆单元(存储先前的值)和以下门 -
在 CNTK 中使用序列非常容易。让我们在以下示例的帮助下查看它 -
import sys
import os
from cntk import Trainer, Axis
from cntk.io import MinibatchSource, CTFDeserializer, StreamDef, StreamDefs,\
INFINITELY_REPEAT
from cntk.learners import sgd, learning_parameter_schedule_per_sample
from cntk import input_variable, cross_entropy_with_softmax, \
classification_error, sequence
from cntk.logging import ProgressPrinter
from cntk.layers import Sequential, Embedding, Recurrence, LSTM, Dense
def create_reader(path, is_training, input_dim, label_dim):
return MinibatchSource(CTFDeserializer(path, StreamDefs(
features=StreamDef(field='x', shape=input_dim, is_sparse=True),
labels=StreamDef(field='y', shape=label_dim, is_sparse=False)
)), randomize=is_training,
max_sweeps=INFINITELY_REPEAT if is_training else 1)
def LSTM_sequence_classifier_net(input, num_output_classes, embedding_dim,
LSTM_dim, cell_dim):
lstm_classifier = Sequential([Embedding(embedding_dim),
Recurrence(LSTM(LSTM_dim, cell_dim)),
sequence.last,
Dense(num_output_classes)])
return lstm_classifier(input)
def train_sequence_classifier():
input_dim = 2000
cell_dim = 25
hidden_dim = 25
embedding_dim = 50
num_output_classes = 5
features = sequence.input_variable(shape=input_dim, is_sparse=True)
label = input_variable(num_output_classes)
classifier_output = LSTM_sequence_classifier_net(
features, num_output_classes, embedding_dim, hidden_dim, cell_dim)
ce = cross_entropy_with_softmax(classifier_output, label)
pe = classification_error(classifier_output, label)
rel_path = ("../../../Tests/EndToEndTests/Text/" +
"SequenceClassification/Data/Train.ctf")
path = os.path.join(os.path.dirname(os.path.abspath(__file__)), rel_path)
reader = create_reader(path, True, input_dim, num_output_classes)
input_map = {
features: reader.streams.features,
label: reader.streams.labels
}
lr_per_sample = learning_parameter_schedule_per_sample(0.0005)
progress_printer = ProgressPrinter(0)
trainer = Trainer(classifier_output, (ce, pe),
sgd(classifier_output.parameters, lr=lr_per_sample),progress_printer)
minibatch_size = 200
for i in range(255):
mb = reader.next_minibatch(minibatch_size, input_map=input_map)
trainer.train_minibatch(mb)
evaluation_average = float(trainer.previous_minibatch_evaluation_average)
loss_average = float(trainer.previous_minibatch_loss_average)
return evaluation_average, loss_average
if __name__ == '__main__':
error, _ = train_sequence_classifier()
print(" error: %f" % error)
average since average since examples
loss last metric last
------------------------------------------------------
1.61 1.61 0.886 0.886 44
1.61 1.6 0.714 0.629 133
1.6 1.59 0.56 0.448 316
1.57 1.55 0.479 0.41 682
1.53 1.5 0.464 0.449 1379
1.46 1.4 0.453 0.441 2813
1.37 1.28 0.45 0.447 5679
1.3 1.23 0.448 0.447 11365
error: 0.333333
上述程序的详细解释将在下一节中介绍,尤其是在我们构建递归神经网络时。