I’m facing an issue with the train function in my neural network implementation. Below is the relevant code snippet:

        def __init__(self):

            # DO NOT CHANGE PARAMETERS
            self.input_to_hidden_weights = np.matrix('1 1; 1 1; 1 1')
            self.hidden_to_output_weights = np.matrix('1 1 1')
            self.biases = np.matrix('0; 0; 0')
            self.learning_rate = .001
            self.epochs_to_train = 10
            self.training_points = [((2,1), 10), ((3,3), 21), ((4,5), 32), ((6, 6), 42)]
            self.testing_points = [(1,1), (2,2), (3,3), (5,5), (10,10)]

        def train(self, x1, x2, y):
            ### Forward propagation ###
            input_values = np.matrix([[x1], [x2]])  # 2 by 1

            # Calculate the input and activation of the hidden layer
            hidden_layer_weighted_input = np.dot(self.input_to_hidden_weights, input_values) + self.biases
            hidden_layer_activation = np.vectorize(rectified_linear_unit)(hidden_layer_weighted_input)

            # Calculate the output
            output = np.dot(hidden_layer_activation.T, self.hidden_to_output_weights.T)

            activated_output = output_layer_activation(output)

            ### Backpropagation ###

            # Compute gradients
            output_layer_error = y - activated_output
            hidden_layer_error = np.dot(self.hidden_to_output_weights, output_layer_error) * np.vectorize(rectified_linear_unit_derivative)(hidden_layer_weighted_input)


            bias_gradients = hidden_layer_error
            hidden_to_output_weight_gradients = output_layer_error * hidden_layer_activation.T
            input_to_hidden_weight_gradients = hidden_layer_error * input_values.T

            # Use gradients to adjust weights and biases using gradient descent
            self.biases += self.learning_rate * bias_gradients
            self.input_to_hidden_weights += self.learning_rate * input_to_hidden_weight_gradients
            self.hidden_to_output_weights += self.learning_rate * hidden_to_output_weight_gradients

    def rectified_linear_unit(x):
        """ Returns the ReLU of x, or the maximum between 0 and x."""
        return max(0, x)

    def rectified_linear_unit_derivative(x):
        """ Returns the derivative of ReLU."""
        return 1 if x > 0 else 0

    def output_layer_activation(x):
        """ Linear function, returns input as is. """
        return x

    def output_layer_activation_derivative(x):
        """ Returns the derivative of a linear function: 1. """
        return 1

When I run this code, I encounter the following error:

Image of Error

Could you please help me identify the cause of this error and suggest a solution? Thank you!