Converting a matrix into a single value in Keras

I’m trying to train a Keras model where the input is a matrix, and I want the output to be a single value. However, I’m encountering an issue with the code where it throws an error related to the number of samples in the input and output arrays.

Here’s a simplified version of my code:

import numpy as np
from keras.models import Sequential
from keras.layers import Dense

# Input (matrix)
X = np.array([[1, 2, 3, 4],
              [2, 3, 4, 5],
              [3, 4, 5, 6],
              [4, 5, 6, 7],
              [5, 6, 7, 8]])

# Output (single value)
Y = np.array([-1])

# Creating model
model = Sequential()
model.add(Dense(10, input_dim=4, activation='relu'))
model.add(Dense(1, activation='linear'))

# Compiling
model.compile(loss='mean_squared_error', optimizer='adam')

# Training
model.fit(X, Y, epochs=10, batch_size=1, verbose=1)

# Predictions
new_data = np.array([[6, 7, 8, 9]])
pred = model.predict(new_data)
print("Prediction:", pred)

I’m receiving the following error message: "x sizes: 5, y sizes: 1. Make sure all arrays contain the same number of samples." I understand that the issue is related to the number of samples in the input and output arrays.

My goal is to convert the matrix input into a single value as the output. How can I modify the code to achieve this?

Any help or guidance would be greatly appreciated. Thank you!

>Solution :

like this?

import numpy as np
from keras.models import Sequential
from keras.layers import Dense

# Input (matrix)
X = np.array([[[1, 2, 3, 4],
               [2, 3, 4, 5],
               [3, 4, 5, 6],
               [4, 5, 6, 7],
               [5, 6, 7, 8]],

              [[4, 7, 3, 4],
               [2, 4, 5, 2],
               [6, 1, 3, 9],
               [1, 2, 5, 3],
               [9, 4, 2, 1]]])

# Output (single value)
Y = np.array([1, 3])  # Adjust the output shape to (num_samples,)

# Creating model
model = Sequential()
model.add(Dense(10, input_shape=(5, 4), activation='relu'))  # Adjust input_shape
model.add(Dense(1, activation='linear'))

# Compiling
model.compile(loss='mean_squared_error', optimizer='adam')

# Training
model.fit(X, Y, epochs=10, batch_size=1, verbose=1)

# Predictions
new_data = np.array([[[6, 7, 8, 9],
                      [9, 8, 7, 6],
                      [5, 4, 3, 2],
                      [2, 3, 4, 5],
                      [1, 1, 1, 1]]])
pred = model.predict(new_data)
print("Prediction:", pred)

X is a 3-dimensional array with shape (num_samples, 5, 4), and Y is a 1-dimensional array with shape (num_samples,).
output is:

Prediction: [[[0.85670656]
  [1.1437894 ]
  [0.555161  ]
  [0.3494279 ]
  [0.20106974]]]