ValueError:连续图层15的输入0与该图层不兼容:预期ndim = 3,找到的ndim = 2。收到的完整图形:[1000、8]

时间:2020-10-08 11:28:55

标签: python tensorflow recurrent-neural-network

使用RNN的Weatherhistory.csv ValueError:连续图层15的输入0与该图层不兼容:预期ndim = 3,找到的ndim = 2。收到的完整图形:[1000、8] 什么需要进行更改??

'

print(X_train.shape)
print(X_test.shape)
print(y_train.shape)
print(y_test.shape)

Output:
(60000, 8)
(20000, 8)
(60000,)
(20000,)

rnn_model = Sequential()

rnn_model.add(SimpleRNN(40,activation="tanh",return_sequences=True, input_shape=X_train.shape))
rnn_model.add(Dropout(0.15))

rnn_model.add(SimpleRNN(40,activation="tanh",return_sequences=True))
rnn_model.add(Dropout(0.15))

rnn_model.add(SimpleRNN(40,activation="tanh",return_sequences=False))
rnn_model.add(Dropout(0.15))

rnn_model.add(Dense(1))

rnn_model.summary()

#model compile
rnn_model.compile(optimizer="adam",loss="MSE")

#model fit
model1 = rnn_model.fit(X_train, y_train, epochs=10, batch_size=1000)'

0 个答案:

没有答案