【发布时间】:2018-09-29 11:32:24
【问题描述】:
我有一个二维数组(熊猫),它是时间序列,有 3180 行,每行有 8 列(数组)作为特征。我正在尝试训练 LSTM 层
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
print (X_train.shape)
classifier = Sequential()
classifier.add(LSTM(units=128, input_shape=(1, len(X_train), x.shape[1])))
如this 中所建议的那样。但是错误出现了,
ValueError: Input 0 is incompatible with layer lstm_1: expected ndim=3, found ndim=4
【问题讨论】:
标签: python machine-learning keras time-series lstm