Mastering OpenCV 4 with Python

Linear regression in Keras

The linear_regression_keras_training.py dataset performs the training of a linear regression model. The first step is to create the data to be used for training/testing the algorithm as follows:

# Generate random data composed by 50 (N = 50) points:x = np.linspace(0, N, N)y = 3 * np.linspace(0, N, N) + np.random.uniform(-10, 10, N)

The next step is to create the model. To do so, we have created the create_model() function, as demonstrated in the following code snippet:

def create_model():    """Create the model using Sequencial model"""    # Create a sequential model:    model = Sequential()    # All we need is a single connection so we use a Dense layer with linear activation:    model.add(Dense(input_dim=1, units=1, activation ...