Failing to match the required number of dimensions for Keras LSTM model-CodePudding

I have tried to set up a bare minimum example for building a neural network. I got 5 prices for a car over 5 different dates. No matter how I rearrange my data, I get 1 out of 2 types of errors.

Either

ValueError: Input 0 of layer sequential is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: (1, 1)

ValueError: Data cardinality is ambiguous:
x sizes: 5
y sizes: 1
Make sure all arrays contain the same number of samples.

I've begun to suspect that no matter how I arrange this data, it will never work. Do I need to add another dimension (e.g. both prices and amount of tax)?

Full code:

import numpy as np
from keras.models import Sequential #, LSTM
from keras.layers.core import  Dense;
from keras.layers import LSTM
import tensorflow as tf

time_list = [ 1296000.0, 19350000.0, 29635200.0, 48294000.0, 45961200.0] # my sample data
price_list = [ 0.05260218,0.05260218,0.0,0.96769388,1.0 ]

these_dates = np.array(time_list) 
prices = np.array(price_list)

#these_dates = these_dates.reshape(-1, 1)  # ive tried every variery of dimensions, nothing works.  
#prices = prices.reshape(-1, 1)

model = Sequential()
model.add(LSTM(10 , return_sequences = True , input_shape =(len(prices) , 1) ,input_dim=2))
model.compile(optimizer = 'adam' , loss = 'mean_squared_error')
model.fit( prices ,these_dates , batch_size = 1 , epochs =1)

Specifying the input_ndim doesn't seem to help. What do I need to do to get these dimensions to match? Will it ever work?

CodePudding user response：

As explained in the keras documentation the required input shape is (batch, timesteps, features). In your case this is (5, 1, 1) since batch=5, timesteps=1 and features=1, see the example below.

import numpy as np
import tensorflow as tf
from keras.models import Sequential
from keras.layers import Dense, LSTM
tf.random.set_seed(0)

# generate the features
X = np.array([1296000.0, 19350000.0, 29635200.0, 48294000.0, 45961200.0])

# generate the target
y = np.array([0.05260218, 0.05260218, 0.0, 0.96769388, 1.0])

# rescale the features
X = (X - np.min(X)) / (np.max(X) - np.min(X))

# reshape the features
X = X.reshape(len(X), 1, 1)
print(X.shape)
# (5, 1, 1)

# define the model
model = Sequential()
model.add(LSTM(10, return_sequences=False, input_shape=(X.shape[0], X.shape[1])))
model.add(Dense(1))

# compile the model
model.compile(optimizer='adam', loss='mse')

# fit the model
model.fit(X, y, batch_size=1, epochs=10)

# generate the model predictions
model.predict(X)
# array([[0.05585098],
#        [0.0940358 ],
#        [0.11524458],
#        [0.152216  ],
#        [0.14772224]], dtype=float32)