[英]Keras LSTM Input and Output Dimension Issue
I am trying to create the LSTM model for the multi-steps prediction.我正在尝试为多步预测创建 LSTM model。 Now I am testing the model network setting but it found that it has the dimension issue on the setting.
现在我正在测试 model 网络设置,但发现它的设置存在尺寸问题。
Here is my testing dataset:这是我的测试数据集:
length = 100
df = pd.DataFrame()
df['x1'] = [i/float(length) for i in range(length)]
df['x2'] = [i**2 for i in range(length)]
df['y'] = df['x1'] + df['x2']
x_value = df.drop(columns = 'y').values
y_value = df['y'].values.reshape(-1,1)
Here is my t window data building function:这是我的 window 数据构建 function:
def build_data(x_value, y_value ,n_input, n_output):
X, Y = list(), list()
in_start = 0
data_len = len(x_value)
# step over the entire history one time step at a time
for _ in range(data_len):
# define the end of the input sequence
in_end = in_start + n_input
out_end = in_end + n_output
if out_end <= data_len:
x_input = x_value[in_start:in_end] # e.g. t0-t3
X.append(x_input)
y_output = y_value[in_end:out_end] # e.g. t4-t5
Y.append(y_output)
# move along one time step
in_start += 1
return np.array(X), np.array(Y)
X, Y = build_data(x_value, y_value, 1, 2)
The shape of X and Y X 和 Y 的形状
X.shape
### (98, 1, 2)
Y.shape
### (98, 2, 1)
For the Model Part,对于 Model 零件,
verbose, epochs, batch_size = 1, 20, 16
n_neurons = 100
n_inputs, n_features = X.shape[1], X.shape[2]
n_outputs = Y.shape[1]
model = Sequential()
model.add(LSTM(n_neurons, input_shape = (n_inputs, n_features), return_sequences=True))
model.add(TimeDistributed(Dense(1)))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(X, Y, epochs=epochs, batch_size=batch_size, verbose=verbose)
It occurred the error: ValueError: Error when checking target: expected time_distributed_41 to have shape (1, 1) but got array with shape (2, 1)
发生错误:
ValueError: Error when checking target: expected time_distributed_41 to have shape (1, 1) but got array with shape (2, 1)
If using the X, Y = build_data(x_value, y_value, 2, 2)
ie input window == output window
that will be work.如果使用
X, Y = build_data(x_value, y_value, 2, 2)
ie input window == output window
将起作用。 But I think it should not contain this constraint.但我认为它不应该包含这个约束。
How can I overcome this issue?我该如何克服这个问题? ie setting for
input window != output window
即
input window != output window
or any layer or setting I should set?或者我应该设置的任何图层或设置?
you encounter a shape mismatch when handling the temporal dimension... the temporal input dim is 1 while you are trying to predict something with a temporal dimension of 2. so you need something in your network that is able to increase from 1 to 2 temporal dimension.您在处理时间维度时遇到形状不匹配...当您尝试预测时间维度为 2 的事物时,时间输入昏暗为 1。因此您的网络中需要能够从 1 增加到 2 时间维度的东西方面。 I used the
Upsampling1D
layer, below a full example我使用了
Upsampling1D
层,下面是一个完整的例子
# create fake data
X = np.random.uniform(0,1, (98,1,2))
Y = np.random.uniform(0,1, (98,2,1))
verbose, epochs, batch_size = 1, 20, 16
n_neurons = 100
n_inputs, n_features = X.shape[1], X.shape[2]
n_outputs = Y.shape[1]
model = Sequential()
model.add(LSTM(n_neurons, input_shape = (n_inputs, n_features), return_sequences=True))
model.add(UpSampling1D(n_outputs))
model.add(TimeDistributed(Dense(1)))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(X, Y, epochs=epochs, batch_size=batch_size, verbose=verbose)
with input temporal dim > output temporal dim, you can use Lambda or Pooling operation (if the dimension match).输入时间暗淡 > output 时间暗淡,您可以使用 Lambda 或池化操作(如果尺寸匹配)。 below an example with Lambda
下面是 Lambda 的示例
X = np.random.uniform(0,1, (98,3,2))
Y = np.random.uniform(0,1, (98,2,1))
verbose, epochs, batch_size = 1, 20, 16
n_neurons = 100
n_inputs, n_features = X.shape[1], X.shape[2]
n_outputs = Y.shape[1]
model = Sequential()
model.add(LSTM(n_neurons, input_shape = (n_inputs, n_features), return_sequences=True))
model.add(Lambda(lambda x: x[:,-n_outputs:,:]))
model.add(TimeDistributed(Dense(1)))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(X, Y, epochs=epochs, batch_size=batch_size, verbose=verbose)
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.