Python ValueError：输入 0 与层 lstm_13 不兼容：预期 ndim=3，发现 ndim=4
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/44583254/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
ValueError: Input 0 is incompatible with layer lstm_13: expected ndim=3, found ndim=4
提问by Urja Pawar
I am trying for multi-class classification and here are the details of my training input and output:
我正在尝试多类分类，这里是我的训练输入和输出的详细信息：
train_input.shape= (1, 95000, 360) (95000 length input array with each element being an array of 360 length)
train_output.shape = (1, 95000, 22) (22 Classes are there)
train_input.shape= (1, 95000, 360) （95000 长度的输入数组，每个元素都是 360 长度的数组）
train_output.shape = (1, 95000, 22) （有 22 个类）
model = Sequential()
model.add(LSTM(22, input_shape=(1, 95000,360)))
model.add(Dense(22, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())
model.fit(train_input, train_output, epochs=2, batch_size=500)
The error is:
错误是：
ValueError: Input 0 is incompatible with layer lstm_13: expected ndim=3, found ndim=4 in line: model.add(LSTM(22, input_shape=(1, 95000,360)))
ValueError: Input 0 is incompatible with layer lstm_13: expected ndim=3, found ndim=4 in line: model.add(LSTM(22, input_shape=(1, 95000,360)))
Please help me out, I am not able to solve it through other answers.
请帮帮我，我无法通过其他答案解决。
采纳答案by Urja Pawar
I solved the problem by making
我通过制作解决了这个问题
input size: (95000,360,1) and output size: (95000,22)
输入大小：（95000,360,1）和输出大小：（95000,22）
and changed the input shape to (360,1)in the code where model is defined:
并在定义模型的代码中将输入形状更改为 (360,1)：
model = Sequential()
model.add(LSTM(22, input_shape=(360,1)))
model.add(Dense(22, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())
model.fit(ml2_train_input, ml2_train_output_enc, epochs=2, batch_size=500)
回答by Michele Tonutti
input_shape is supposed to be (timesteps, n_features). Remove the first dimension.
input_shape 应该是（时间步长，n_features）。删除第一个维度。
input_shape = (95000,360)
Same for the output.
输出也一样。
回答by Shobhit Srivastava
Well, I think the main problem out there is with the return_sequencesparameter in the network.This hyper parameter should be set to Falsefor the last layerand truefor the other previous layers.
嗯，我认为主要的问题是return_sequences网络中的参数。应该False为最后一层和true其他前一层设置这个超参数。
