Python 我的keras.utils.Sequence返回3个数组，我可以'；不要把它放在model.fit里

正如您在标题my keras.utils.Sequence return 3数组中所读到的那样。 如何将model.fit（..）与keras.utils.Sequence对象的3个输出一起使用

    def __getitem__(self, index):
        'Generate one batch of data'
        # Generate indexes of the batch
        indexes = self.indexes[index*self.batch_size:(index+1)*self.batch_size]

        # Find list of IDs
        list_IDs_temp = [self.list_IDs[k] for k in indexes]

        # Generate data
        X,Xt,y= self.__data_generation(list_IDs_temp)

        return X,Xt,y

X是我的原始图像，Xt是变换后的图像，y是标签。 我想编译下面的代码：

model_englobe.fit(generated_image_train,batch_size=1,epochs=2)

我的模型采用两个输入X我的原始图像Xt。

生成的\u图像\u列[i]

是批次号i

generated\u image\u train[i][0]

i在这里选择所有原始图像，

generated\u image\u train[i][1]

i在这里选择所有转换后的图像，

generated\u image\u train[i][2]

i在这里选择所有标签

显示错误：

    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:805 train_function  *
        return step_function(self, iterator)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:795 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:1259 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:2730 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute_lib.py:3417 _call_for_each_replica
        return fn(*args, **kwargs)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:788 run_step  **
        outputs = model.train_step(data)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:754 train_step
        y_pred = self(x, training=True)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py:998 __call__
        input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
    /usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/input_spec.py:207 assert_input_compatibility
        ' input tensors. Inputs received: ' + str(inputs))

    ValueError: Layer model expects 2 input(s), but it received 1 input tensors. Inputs received: [<tf.Tensor 'IteratorGetNext:0' shape=(None, None, None, None) dtype=float32>]

/usr/local/lib/python3.7/dist包/tensorflow/python/keras/engine/training.py:805 train\u函数*
返回步骤_函数（self、迭代器）
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training.py:795 step_函数**
输出=模型。分配策略。运行（运行步骤，参数=（数据，）
/usr/local/lib/python3.7/dist包/tensorflow/python/distribute/distribute_lib.py:1259运行
返回self.\u扩展。为每个\u副本调用\u（fn，args=args，kwargs=kwargs）
/usr/local/lib/python3.7/dist包/tensorflow/python/distribute/distribute_lib.py:2730为每个复制副本调用
返回自我。为每个副本（fn、ARG、kwargs）调用
/usr/local/lib/python3.7/dist-packages/tensorflow/python/distribute/distribute\u-lib.py:3417\u为每个副本调用\u
返回fn（*args，**kwargs）
/usr/local/lib/python3.7/dist包/tensorflow/python/keras/engine/training.py:788运行步骤**
输出=型号列车步进（数据）
/usr/local/lib/python3.7/dist包/tensorflow/python/keras/engine/training.py:754 train\u步骤
y_pred=self（x，training=True）
/usr/local/lib/python3.7/dist包/tensorflow/python/keras/engine/base\u layer.py:998\u调用__
输入\规格.断言\输入\兼容性（self.input \规格，输入，self.name）
/usr/local/lib/python3.7/dist包/tensorflow/python/keras/engine/input\u spec.py:207断言\u输入\u兼容性
'输入张量。收到的输入：'+str（输入））
ValueError：层模型需要2个输入，但收到1个输入张量。收到的投入：[]

---

非常感谢

如果生成器返回3个变量，那么keras假设您返回的是X、y和样本权重。要传递两个输入，必须以如下列表的形式返回X和Xt：

def\uuuu getitem\uuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuuu
“生成一批数据”
#生成批处理的索引
索引=自索引[索引*自批大小：（索引+1）*自批大小]
#查找ID列表
list_id_temp=[索引中k的self.list_id[k]
#生成数据
十、 Xt，y=自身数据生成（列表ID温度）
返回[X，Xt]，y

---

有关更多信息，请检查

fit

函数中的

x

参数。

谢谢，但是我有一个错误：ValueError:in user code:/usr/local/lib/python3.7/dist packages/tensorflow/python/keras/engine/training.py:805 train_函数*return step_函数（self，iterator）：17 call*self.total[i，j].assign（tensor_sub）/usr/local/lib/python3.7/dist packages/tensorflow/python/ops/array_ops.py:1229 assign**raise ValueError（“切片赋值仅支持变量”）ValueError：切片赋值仅支持变量。你知道这是什么意思吗？也许我弄错了，你能试着返回一个列表而不是元组吗？像[X，Xt]。。我已经编辑了我的答案。由于元组不支持切片，这就是它抛出错误的原因。我有同样的错误：ValueError：切片赋值仅支持变量我认为这是我的层，根据这篇文章：我可以写：tensor_sub=tf.math.reduce_sum（tf.math.abs（tf.subtract）（in1[0，I，j，：]，in2[0，：]））如果in1，in2是张量OK非常感谢