Keras LSTM在CPU上比GPU快吗?

本文介绍了Keras LSTM在CPU上比GPU快吗?的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！ 问题描述

我正在Keras上测试LSTM网络，并且在CPU(i2600k 16GB上为5秒/纪元)上的训练比在GPU(Nvidia 1060 6GB上为35秒)上的训练要快得多. GPU利用率大约为15％，而尝试包括Keras示例在内的其他LSTM网络时，我从来没有看到超过30％的利用率.当我运行其他类型的网络MLP和CNN时，GPU更快.我正在使用最新的theano 0.9.0dev4和keras 1.2.0

I am testing LSTM networks on Keras and I am getting much faster training on CPU (5 seconds/epoch on i2600k 16GB) than on GPU (35secs on Nvidia 1060 6GB). GPU utilisation runs at around 15%, and I never see it over 30% when trying other LSTM networks including the Keras examples. When I run other types of networks MLP and CNN the GPU is much faster. I am using the latest theano 0.9.0dev4 and keras 1.2.0

该序列具有3个输入(整数)的50,000个时间步长.

The sequence has 50,000 timesteps with 3 inputs (ints).

如果输入是降序(3,2,1)，则输出为0，如果升序，则输出为1，除非最后两个为也上升，则输出为0而不是1.

If the inputs are descending (3,2,1) the output is 0, and 1 if ascending, except if the last two were also ascending, then the output is 0 instead of 1.

250个纪元后，我获得了99.97％的准确度，但是为什么GPU这么慢?我在模型中做错了吗?我尝试了各种批处理设置，但仍然遇到相同的问题.

After 250 epochs I get 99.97% accuracy, but why is the GPU so much slower? am I doing something wrong in the model? I tried various batch settings and still had the same issue.

def generate_data(): X=[] Y=[] for i in range(50000): start=random.randint(1,100) d=random.randrange(-1,2,2) #-1 or 1 param=[(start),(start+d),(start+d+d)] X.append(np.array(param)) if d<0: Y.append([1,0]) elif len(Y)>2 and d>0 and Y[-1][1]==1 and Y[-2][1]==1: Y.append([1,0]) elif d>0: Y.append([0,1]) X=np.array(X) Y=np.array(Y) return X,Y X,Y = generate_data() X=np.asarray(X,'float32') Y=np.asarray(Y,'float32') X=np.reshape(X,(1,len(X),3)) Y=np.reshape(Y,(1,len(Y),2)) model=Sequential() model.add(LSTM(20, input_shape=(50000,3), return_sequences=True)) model.add(Dense(2)) model.add(Activation('softmax')) modelpile(loss='categorical_crossentropy', optimizer=RMSprop(), metrics=['accuracy']) history = model.fit(X, Y,batch_size=100, nb_epoch=250, verbose=2)

有什么想法吗?谢谢！

推荐答案

使用Keras的CuDNNLSTM单元在Nvidia GPU上加速计算: keras.io/layers/recurrent/#cudnnlstm

Use Keras' CuDNNLSTM cells for accelerated compute on Nvidia GPUs: keras.io/layers/recurrent/#cudnnlstm

只需将LSTM行更改为:

model.add(CuDNNLSTM(20, input_shape=(50000,3), return_sequences=True))