NumPy-neural-net-7.py

def get_loss(y, y_hat, metric='mse'):
    if metric == 'mse':
        individual_loss = 0.5 * (y_hat - y) ** 2
        return np.mean([np.linalg.norm(individual_loss[:,col], 2) for col in range(individual_loss.shape[1])])
    else:
        raise Exception('Loss metric is not defined.')

def get_dZ_from_loss(y, y_hat, metric):
    if metric == 'mse':
        return y_hat - y
    else:
        raise Exception('Loss metric is not defined.')

def get_dactivation(A, act_func):
    if act_func == 'relu':
        return np.maximum(np.sign(A), np.zeros(A.shape)) # 1 if backward input >0, 0 otherwise; then diaganolize
    elif act_func == 'linear':
        return np.ones(A.shape)
    else:
        raise Exception('Activation function is not defined.')
        
        
def backward_prop(y, y_hat, metric='mse', layers_dim=layers_dim, neural_net=neural_net, num_train_datum=num_train_datum):
    for layer_index in range(len(layers_dim)-1,0,-1):
        if layer_index+1 == len(layers_dim): # if output layer
            dZ = get_dZ_from_loss(y, y_hat, metric)
        else: 
            dZ = np.multiply(np.dot(neural_net[layer_index+1].W.T, dZ), 
                             get_dactivation(neural_net[layer_index].A, neural_net[layer_index].activation))
        dW = np.dot(dZ, neural_net[layer_index-1].A.T) / num_train_datum
        db = np.sum(dZ, axis=1, keepdims=True) / num_train_datum
        
        neural_net[layer_index].dW = dW
        neural_net[layer_index].db = db