Keras:ValueError:检查输入时出错

Question

我的pandas数据帧长度为7499042,如下所示:

'X'          'y'
[0.1,0.2...] 0.2
[0.3,0.4,..] 0.3
.
.

pandas dataframe中的每个值都是长度为50的numpy数组.现在我将它解压缩如下:

input = df['X'].values

我有这样的图层:

main_input = Input(shape=(50,1), name='main_input')    
lstm_out=LSTM(32,activation='tanh',recurrent_activation='sigmoid',return_sequences=True)
mean_pooling=AveragePooling1D(pool_size=2,strides=2,padding='valid')

但是当我在训练时传递我的意见时.它显示错误:

ValueError: Error when checking input: expected main_input to have 3 dimensions, but got array with shape (7499042, 1)

它显示的输入形状是(7499042,).请帮我解决这个问题.