Python 在Keras模型中将训练数据指定为元组（x，y）的正确方法。适合多个输入和输出

我正在培训一个Keras Tensorflow模型，该模型有三个输入和两个输出：

mymodel = tf.keras.Model([X1, X2, X3], [y1, y2])

当我通过分别指定

x

和

y

数据来拟合此模型时，它工作正常，没有任何故障：

history = mymodel.fit([X1, X2, X3], [y1, y2], batch_size=128, epochs=5)

但是，为了保持与自定义数据生成器的兼容性，我希望将培训数据作为单个元组（x，y）提供。当我这样做时，它会抛出一个错误：

data = ([X1, X2, X3], [y1, y2])
history = mymodel.fit(data, batch_size=128, epochs=5)

我想我的

数据

元组格式是错误的

---

如何正确指定培训数据？

您需要的是使用生成器或

tf.data

API构建数据管道。根据培训API的文件：

参数

- x: Input data. It could be:
     A tf.data dataset. Should return a tuple of either (inputs, targets) 
     or (inputs, targets, sample_weights).

     A generator or keras.utils.Sequence returning (inputs, targets) or 
    (inputs, targets, sample_weights).

- y: If x is a dataset, generator, or keras.utils.Sequence instance, 
     y should not be specified (since targets will be obtained from x).

仅供参考，但如果数据是数组或张量（

x

），则需要提供相应的

y

。根据文件

- x: 
    A Numpy array (or array-like), or a list of arrays (in case the model has 
    multiple inputs).
    A TensorFlow tensor, or a list of tensors (in case the model has multiple inputs).

- y:
   Like the input data x, it could be either Numpy array(s) or TensorFlow tensor(s). 
   It should be consistent with x (you cannot have Numpy inputs 
   and tensor targets, or inversely).

---

如果你不明白，请告诉我。谢谢！在这种情况下，如何使用具有numpy数组（和多个输入/输出）的数据集生成器。是一篇关于keras生成器的好文章。这是tf.dataset API的教程。这些是针对dataloader的，在模型定义的情况下，请参阅本讨论。更多参考资料可供参考。

- x: Input data. It could be:
     A tf.data dataset. Should return a tuple of either (inputs, targets) 
     or (inputs, targets, sample_weights).

     A generator or keras.utils.Sequence returning (inputs, targets) or 
    (inputs, targets, sample_weights).

- y: If x is a dataset, generator, or keras.utils.Sequence instance, 
     y should not be specified (since targets will be obtained from x).

- x: 
    A Numpy array (or array-like), or a list of arrays (in case the model has 
    multiple inputs).
    A TensorFlow tensor, or a list of tensors (in case the model has multiple inputs).

- y:
   Like the input data x, it could be either Numpy array(s) or TensorFlow tensor(s). 
   It should be consistent with x (you cannot have Numpy inputs 
   and tensor targets, or inversely).