[Python] Why does my Keras model show 4 parameters instead of 2?

I'm training a simple Keras model with one Dense layer, but when I call model.summary(), it shows 4 parameters instead of 2.

import tensorflow as tf
import numpy as np

# Generate dummy data
X_train = np.random.rand(40) # Shape (40,)
y_train = np.random.rand(40)

# Define a simple model
model = tf.keras.Sequential([
tf.keras.layers.Dense(1)
])

# Compile the model
model.compile(loss=tf.keras.losses.mae,
optimizer=tf.keras.optimizers.SGD(),
metrics=["mae"])

# Train the model
model.fit(tf.expand_dims(X_train, axis=-1), y_train, epochs=100)

# Check model summary
model.summary()


Since Dense(1) should have 1 weight + 1 bias, I expected 2 parameters, not 4.

Why does passing a 1D input (shape=(40,)) cause Keras to use 4 parameters instead of 2? Is Keras automatically handling the input shape in a way that duplicates the parameters?

this is the result:



Continue reading...