Created by: guoshengCS

The text indicates that use act=paddle.activation.Softmax() when inferring while followed by the code using act=paddle.activation.Sigmoid()

    return paddle.layer.mixed(
          size=dict_size,
          input=paddle.layer.trans_full_matrix_projection(
              hidden_layer, param_attr=paddle.attr.Param(name="nce_w")),
          act=paddle.activation.Sigmoid(),
          bias_attr=paddle.attr.Param(name="nce_b"))