Keras:具有类权重的LSTM [英] Keras: LSTM with class weights

问题描述

我的问题与此问题密切相关，但也超出了此范围.

my question is quite closely related to this question but also goes beyond it.

我正在尝试在Keras其中

I am trying to implement the following LSTM in Keras where

• 时间步长为nb_tsteps=10
• 输入要素的数量为nb_feat=40
• 每个时间步的LSTM单元数为120
• LSTM层之后是TimeDistributedDense层

• the number of timesteps be nb_tsteps=10
• the number of input features is nb_feat=40
• the number of LSTM cells at each time step is 120
• the LSTM layer is followed by TimeDistributedDense layers

根据上面提到的问题，我知道我必须将输入数据表示为

From the question referenced above I understand that I have to present the input data as

nb_samples, 10, 40

通过在形状为(5932720, 40)的原始时间序列上滚动一个长度为nb_tsteps=10的窗口来得到nb_samples.因此，代码是

where I get nb_samples by rolling a window of length nb_tsteps=10 across the original timeseries of shape (5932720, 40). The code is hence

model = Sequential()
model.add(LSTM(120, input_shape=(X_train.shape[1], X_train.shape[2]), 
  return_sequences=True, consume_less='gpu'))
model.add(TimeDistributed(Dense(50, activation='relu')))
model.add(Dropout(0.2))
model.add(TimeDistributed(Dense(20, activation='relu')))
model.add(Dropout(0.2))
model.add(TimeDistributed(Dense(10, activation='relu')))
model.add(Dropout(0.2))
model.add(TimeDistributed(Dense(3, activation='relu')))
model.add(TimeDistributed(Dense(1, activation='sigmoid')))

现在是我的问题(假设以上内容是正确的): 二进制响应(0/1)严重失衡，我需要将cw = {0: 1, 1: 25}这样的class_weight字典传递给model.fit().但是我得到一个异常class_weight not supported for 3+ dimensional targets.这是因为我将响应数据显示为(nb_samples, 1, 1).如果将其整形为2D数组(nb_samples, 1)，则会出现异常Error when checking model target: expected timedistributed_5 to have 3 dimensions, but got array with shape (5932720, 1).

Now to my question (assuming the above is correct so far): The binary responses (0/1) are heavily imbalanced and I need to pass a class_weight dictionary like cw = {0: 1, 1: 25} to model.fit(). However I get an exception class_weight not supported for 3+ dimensional targets. This is because I present the response data as (nb_samples, 1, 1). If I reshape it into a 2D array (nb_samples, 1) I get the exception Error when checking model target: expected timedistributed_5 to have 3 dimensions, but got array with shape (5932720, 1).

非常感谢您的帮助！

推荐答案

我认为您应该将sample_weight与sample_weight_mode='temporal'一起使用.

I think you should use sample_weight with sample_weight_mode='temporal'.

从Keras文档中:

sample_weight:用于训练样本的权重的数字数组，用于 用于缩放损失函数(仅在训练期间).你可以 通过与输入样本长度相同的平面(1D)Numpy数组 (权重和样本之间的1:1映射)，或者在时间上 数据，您可以传递具有形状(样本，sequence_length)的2D数组， 对每个样本的每个时间步施加不同的权重.在这个 在这种情况下，您应确保在以下位置指定sample_weight_mode ="temporal" compile().

sample_weight: Numpy array of weights for the training samples, used for scaling the loss function (during training only). You can either pass a flat (1D) Numpy array with the same length as the input samples (1:1 mapping between weights and samples), or in the case of temporal data, you can pass a 2D array with shape (samples, sequence_length), to apply a different weight to every timestep of every sample. In this case you should make sure to specify sample_weight_mode="temporal" in compile().

在您的情况下，您需要提供形状与标签相同的2D阵列.

In your case you would need to supply a 2D array with the same shape as your labels.

这篇关于Keras:具有类权重的LSTM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！