optimizers.py 文件源码

def sgd_momentum(w, dw, config=None):
    """
    Performs stochastic gradient descent with momentum.

    config format:
    - learning_rate: Scalar learning rate.
    - momentum: Scalar between 0 and 1 giving the momentum value.
      Setting momentum = 0 reduces to sgd.
    - velocity: A numpy array of the same shape as w and dw used to store a moving
      average of the gradients.

    """
    v = config.get('velocity', np.zeros_like(w))
    next_v = config['momentum'] * v - config['learning_rate'] * dw
    next_w = w + next_v
    config['velocity'] = next_v

    return next_w, config