InvalidArgumentError: Received a label value of 12 which is outside the valid range of [0, 10).

报错如下

Train on 22824 samples, validate on 5706 samples
Epoch 1/20
---------------------------------------------------------------------------
InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-19-46e26c3fe07c> in <module>
      4 
      5 history = model.fit(train_images, train_labels, epochs=20, 
----> 6                     validation_data=(test_images, test_labels))

e:\python37\lib\site-packages\tensorflow\python\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, max_queue_size, workers, use_multiprocessing, **kwargs)
    878           initial_epoch=initial_epoch,
    879           steps_per_epoch=steps_per_epoch,
--> 880           validation_steps=validation_steps)
    881 
    882   def evaluate(self,

e:\python37\lib\site-packages\tensorflow\python\keras\engine\training_arrays.py in model_iteration(model, inputs, targets, sample_weights, batch_size, epochs, verbose, callbacks, val_inputs, val_targets, val_sample_weights, shuffle, initial_epoch, steps_per_epoch, validation_steps, mode, validation_in_fit, **kwargs)
    327 
    328         # Get outputs.
--> 329         batch_outs = f(ins_batch)
    330         if not isinstance(batch_outs, list):
    331           batch_outs = [batch_outs]

e:\python37\lib\site-packages\tensorflow\python\keras\backend.py in __call__(self, inputs)
   3074 
   3075     fetched = self._callable_fn(*array_vals,
-> 3076                                 run_metadata=self.run_metadata)
   3077     self._call_fetch_callbacks(fetched[-len(self._fetches):])
   3078     return nest.pack_sequence_as(self._outputs_structure,

e:\python37\lib\site-packages\tensorflow\python\client\session.py in __call__(self, *args, **kwargs)
   1437           ret = tf_session.TF_SessionRunCallable(
   1438               self._session._session, self._handle, args, status,
-> 1439               run_metadata_ptr)
   1440         if run_metadata:
   1441           proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

e:\python37\lib\site-packages\tensorflow\python\framework\errors_impl.py in __exit__(self, type_arg, value_arg, traceback_arg)
    526             None, None,
    527             compat.as_text(c_api.TF_Message(self.status.status)),
--> 528             c_api.TF_GetCode(self.status.status))
    529     # Delete the underlying status object from memory otherwise it stays alive
    530     # as there is a reference to status from this from the traceback due to

InvalidArgumentError: Received a label value of 12 which is outside the valid range of [0, 10).  Label values: 11 4 5 8 12 11 12 6 9 11 10 4 4 10 11 11 3 8 12 12 5 6 6 1 2 10 4 11 2 2 10 12
	 [[{{node loss/dense_2_loss/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits}}]]

解决方法

这是由于tensorflow的数据集标签类别数与神经网络最后输出层的神经元数不一致引起的。

将红框的地方，改为相应对应的类别数即可！
如我的数据集类别数为13，如下图所示。