Mini-batch gradient descent

train_batch.py

def train_batch(X, Y, nn_architecture, epochs, learning_rate, batch_size = 64, verbose=False, callback=None):
    params_values = init_layers(nn_architecture, 2)
    cost_history = []
    accuracy_history = []
    
    # Beginning of additional code snippet
    batch_number = X.shape[1] // batch_size
    # Ending of additional code snippet
    
    for i in range(epochs):
        # Beginning of additional code snippet
        batch_idx = epochs % batch_number
        X_batch = X[:, batch_idx * batch_size : (batch_idx + 1) * batch_size]
        Y_batch = Y[:, batch_idx * batch_size : (batch_idx + 1) * batch_size]
        # Ending of additional code snippet
        
        Y_hat, cashe = full_forward_propagation(X_batch, params_values, nn_architecture)        
        grads_values = full_backward_propagation(Y_hat, Y_batch, cashe, params_values, nn_architecture)
        params_values = update(params_values, grads_values, nn_architecture, learning_rate)
                    
    return params_values