Created by: hubu-wangpei

以下代码使用fluid.layers.softmax_with_cross_entropy(logits, label)，报错

                x_data, y_data = data
                #print(x_data,y_data)
                img = fluid.dygraph.to_variable(x_data)
                label = fluid.dygraph.to_variable(y_data)
                label=fluid.layers.cast(label,np.int64)
                label=fluid.one_hot(label,2)
                # 运行模型前向计算，得到预测值
                logits = model(img)
                print(logits)
                # 进行loss计算
                loss = fluid.layers.softmax_with_cross_entropy(logits, label)

报错信息

Error Message Summary:---------------------- InvalidArgumentError: Tensor holds the wrong type, it holds float, but desires to be int64_t. [Hint: Expected valid == true, but received valid:0 != true:1.] at (/paddle/paddle/fluid/framework/tensor_impl.h:33)

softmax_with_cross_entropy调用参数，感觉没问题啊