Tensorflow Keras 维度不等于多个标签的错误

Question

I am trying to predict from multidimensional input to multi-dimensional output using Tensorflow 2.0.0's Keras, with the Tensorflow Datasets API.

I am using tensorflow 2.0.0 and tensorflow-datasets 1.3.0 on python 3.6.9 .

Below is my example code, I also reproduced it on [a Colab notebook] ( https://colab.research.google.com/drive/1WMccCeLOrQU4k5D2noC4S_5rMe7-krEk ) which you can run:

import tensorflow as tf
data = [[1,2],[11,22]]
label = [[3,4,5], [33,44,55]]
dataset = tf.data.Dataset.from_tensor_slices((data,label))
model = tf.keras.Sequential()
model.add(tf.keras.layers.Dense(3))
model.compile('adam','mse',metrics=['mse'])
model.fit(dataset, validation_data=dataset)

In this example code I am trying to predict [1,2]->[3,4,5] and [11,22]->[33,44,55] . However I get the error:

---------------------------------------------------------------------------
InvalidArgumentError                      Traceback (most recent call last)
/tensorflow-2.0.0/python3.6/tensorflow_core/python/framework/ops.py in _create_c_op(graph, node_def, inputs, control_inputs)
   1609   try:
-> 1610     c_op = c_api.TF_FinishOperation(op_desc)
   1611   except errors.InvalidArgumentError as e:

InvalidArgumentError: Dimensions must be equal, but are 2 and 3 for 'loss/output_1_loss/SquaredDifference' (op: 'SquaredDifference') with input shapes: [2,3], [3,1].

During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)
29 frames
/tensorflow-2.0.0/python3.6/tensorflow_core/python/framework/ops.py in _create_c_op(graph, node_def, inputs, control_inputs)
   1611   except errors.InvalidArgumentError as e:
   1612     # Convert to ValueError for backwards compatibility.
-> 1613     raise ValueError(str(e))
   1614 
   1615   return c_op

ValueError: Dimensions must be equal, but are 2 and 3 for 'loss/output_1_loss/SquaredDifference' (op: 'SquaredDifference') with input shapes: [2,3], [3,1].

Answer 1

As per thushv89's comment to the question, using batch on the dataset fixes the code. The original code was more complicated than this but using batch fixed it.

import tensorflow as tf
data = [[1,2],[11,22]]
label = [[3,4,5], [33,44,55]]
dataset = tf.data.Dataset.from_tensor_slices((data,label)).batch(2)
model = tf.keras.Sequential()
model.add(tf.keras.layers.Dense(3))
model.compile('adam','mse',metrics=['mse'])
model.fit(dataset, validation_data=dataset)