是的。在MxNet中手动设置稠密()层参数

可以使用设置的参数创建自定义块 differentiable=False ,并通过 init 论点看到了吗 scales 下例中的参数取自 this tutorial .你也可以看到 FullyConnected 你也可以用它来制作致密层。 F 用于表示通用后端,通常是 mx.ndarray ,但杂交后,这是设置为 mx.symbol .

class NormalizationHybridLayer(gluon.HybridBlock):
    def __init__(self, hidden_units, scales):
        super(NormalizationHybridLayer, self).__init__()

        with self.name_scope():
            self.weights = self.params.get('weights',
                                           shape=(hidden_units, 0),
                                           allow_deferred_init=True)

            self.scales = self.params.get('scales',
                                      shape=scales.shape,
                                      init=mx.init.Constant(scales.asnumpy().tolist()), # Convert to regular list to make this object serializable
                                      differentiable=False)

    def hybrid_forward(self, F, x, weights, scales):
        normalized_data = F.broadcast_div(F.broadcast_sub(x, F.min(x)), (F.broadcast_sub(F.max(x), F.min(x))))
        weighted_data = F.FullyConnected(normalized_data, weights, num_hidden=self.weights.shape[0], no_bias=True)
        scaled_data = F.broadcast_mul(scales, weighted_data)
        return scaled_data