Keras模型预测数字序列 [英] Keras model to predict number sequence

问题描述

我正在尝试训练Keras LSTM模型以预测序列中的下一个数字.

I am trying to train Keras LSTM model to predict next number in a sequence.

1. 下面的模型有什么问题，当模型不学习时如何调试
2. 如何确定要使用的图层类型
3. 在编译时应基于什么选择损失参数和优化器参数

我输入的训练数据的形状如下(16000，10)

My input training data is of shape (16000, 10) like below

[
    [14955 14956 14957 14958 14959 14960 14961 14962 14963 14964]
    [14731 14732 14733 14734 14735 14736 14737 14738 14739 14740]
    [35821 35822 35823 35824 35825 35826 35827 35828 35829 35830]
    [12379 12380 12381 12382 12383 12384 12385 12386 12387 12388]
    ...
]

相应的输出训练数据具有如下所示的形状(16000，1)

Corresponding output training data is of shape (16000, 1) like below

[[14965] [14741] [35831] [12389] ...]

由于LSTM抱怨，我重塑了训练/测试数据

As LSTM is complaining, I reshaped training/test data

X_train = X_train.reshape(X_train.shape[0], X_train.shape[1], 1)
X_test = X_test.reshape(X_test.shape[0], X_test.shape[1], 1)

这是最终的训练/测试数据形状

Here is final training/test data shape

Total Samples: 20000
X_train: (16000, 10, 1)
y_train: (16000, 1)
X_test: (4000, 10, 1)
y_test: (4000, 1)

这是我的模特

# Model configuration
epochs = 2
batch_size = 32
hidden_neurons = 100
output_size = 1

# Create the model
model = Sequential()
model.add(LSTM(hidden_neurons, input_shape=(X_train.shape[1], X_train.shape[2])))
model.add(Dense(output_size))
model.compile(loss='mean_squared_error', optimizer='rmsprop', metrics=['accuracy'])
print(model.summary())
model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size)

scores = model.evaluate(X_test, y_test, batch_size=batch_size, verbose=0)
print("Model Accuracy: %.2f%%" % (scores[1]*100))

这是我的输出

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
lstm_3 (LSTM)                (None, 100)               40800     
_________________________________________________________________
dense_3 (Dense)              (None, 1)                 101       
=================================================================
Total params: 40,901
Trainable params: 40,901
Non-trainable params: 0
_________________________________________________________________
None
Epoch 1/2
16000/16000 [==============================] - 11s - loss: 533418575.3600 - acc: 0.0000e+00    
Epoch 2/2
16000/16000 [==============================] - 10s - loss: 532474289.7280 - acc: 6.2500e-05    
Model Accuracy: 0.00%

推荐答案

尝试以下代码:

epochs = 30
batch_size = 64
hidden_neurons = 32
output_size = 1

# Create the model
model = Sequential()
model.add(LSTM(hidden_neurons, input_shape=(X_train.shape[1], X_train.shape[2])))
model.add(Dense(output_size, activation = 'elu'))

model.compile(loss='mean_squared_error', optimizer='adam', metrics=['accuracy'])
print(model.summary())
model.fit(X_train, y_train, epochs=epochs, batch_size=batch_size)

scores = model.evaluate(X_test, y_test, batch_size=batch_size, verbose=0)
print("Model Accuracy: %.2f%%" % (scores[1]*100))

一般来说，要帮助您真的很困难，因为我们需要一种可以测试的可复制示例.但是，这是我的建议:

in general, it is really hard to help you, because we need a kind of reproducible example which we can test. However, here are my advises:

使用您的NN的超参数，例如:激活函数，opt函数，层数，学习率等.

play with hyper parameters of your NN, such as: activation functions, opt function, number of layers, learning rate and so on.

更新:

强烈建议先将您的数据标准化.

It is highly advisable to normalize your data first.

这篇关于Keras模型预测数字序列的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！