I got a dataset composed of 432 batches of 24 points each one of them. Shape of the entire dataset: (432, 24)

To put an example, this would be one batch:

array([917, 15, 829, 87, 693, 71, 627, 359, 770, 303, 667, 367, 754, 359, 532, 39, 683, 407, 333, 551, 516, 31, 675, 39])

with shape (24,)

I am feeding a Keras model with this info. No issues. When I try to predict with new data with the same shape (24,):

array([176, 71, 152, 63, 200, 71, 120, 87, 128, 87, 216, 103, 248, 126, 144, 150, 128, 206, 192, 206, 112, 277, 216, 269])

My model:

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), ]) model.compile(optimizer='adam', loss=tf.losses.categorical_crossentropy, metrics=['accuracy'])

The error raised:

ValueError: Input 0 of layer dense_24 is incompatible with the layer: expected axis -1 of input shape to have value 24 but received input with shape (None, 1)

## Answer

Maybe try adding a dimension to your data sample and then feed your `new_data`

into your model to make a prediction:

import numpy as np new_data= np.array([176, 71, 152, 63, 200, 71, 120, 87, 128, 87, 216, 103, 248, 126, 144, 150, 128, 206, 192, 206, 112, 277, 216, 269]) new_data= np.expand_dims(new_data, axis=0) prediction = model.predict(new_data) print(prediction)