Why I cannot feed my Keras model in batches?-CodePudding

I am trying to feed a Sequential model in batches. To reproduce my example, suppose my data is:

X = np.random.rand(432,24,1)
Y = np.random.rand(432,24,1)

My goal is to feed the model in batches. 24 points at a time (24 x 1 vector), 432 times.

I built my model as:

X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.3, random_state=12)

model = keras.Sequential([
    #keras.layers.Flatten(batch_input_shape=(None, 432, 2)),
    keras.layers.Dense(64, activation=tf.nn.relu),
    keras.layers.Dense(2, activation=tf.nn.sigmoid),
])

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

history = model.fit(X_train, y_train, epochs=200, batch_size=32, validation_split=0.3)
test_loss, test_acc = model.evaluate(X_test, y_test)
print('Model loss:', test_loss, 'Model accuracy: ', test_acc)

However, I get this error:

ValueError: Input 0 of layer dense_25 is incompatible with the layer: expected axis -1 of input shape to have value 864 but received input with shape (None, 432)

CodePudding user response：

I think that there is some confusion about the dimensions of your input data. I'm going to assume that 432 is the number of points, and each data point has dimensionality 24 (i.e., 24 features). In that case, the first dimension should index the points because both scikit-learn and keras expect that way. For example,

X = np.random.rand(432, 24)
Y = np.random.rand(432, 24)

then your code should run if you correct the input shape accordingly,

model = keras.Sequential([
    keras.layers.Flatten(batch_input_shape=(None, 24)),
    keras.layers.Dense(64, activation=tf.nn.relu),
    keras.layers.Dense(2, activation=tf.nn.sigmoid),
])

CodePudding user response：

I am not really too sure what you want to do, but here is a working example:

import tensorflow as tf
from sklearn.model_selection import train_test_split

X = np.random.rand(432, 24)
Y = np.random.randint(2, size=(432, 2))

X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.3, random_state=12)

model = tf.keras.Sequential([
    tf.keras.layers.Dense(64, activation=tf.nn.relu),
    tf.keras.layers.Dense(2, activation=tf.nn.sigmoid),
])

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

history = model.fit(X_train, y_train, epochs=200, batch_size=32, validation_split=0.3)
test_loss, test_acc = model.evaluate(X_test, y_test)
print('Model loss:', test_loss, 'Model accuracy: ', test_acc)

Note that your data X has the shape (432, 24) and your labels Y has the shape (432, 2). I removed your Flatten layer as it doesn't make much sense if your data has the shape (432, 24). You can make a prediction after training your model like this:

X_new = np.random.rand(1, 24)
Y_new = model.predict(X_new)
print(Y_new)