InvalidArgumentError：拟合模型时的错误

如何解决InvalidArgumentError：拟合模型时的错误

我正在使用带有 keras 的 多层感知器 进行疾病分类，并在过程描述下方， 将数据集拆分为train_x、train_y、test_x、test_y：

from sklearn.utils import shuffle
from sklearn.model_selection import train_test_split

images,y = shuffle(images,y,random_state=1)
train_x,test_x,train_y,test_y = train_test_split(images,test_size=0.10,random_state = 415)

使用 tensorflow nad kears 开发序列模型

import keras
import tensorflow as tf

model = keras.Sequential([keras.layers.Flatten(input_shape=(300,300,3)),keras.layers.Dense(256,activation=tf.nn.tanh),keras.layers.Dense(3,activation=tf.nn.softmax)
                         ])

编译模型

model.compile(optimizer=tf.optimizers.Adam(),loss='sparse_categorical_crossentropy',metrics=['accuracy'])

** 用 30 个 epochs 训练模型**

model.fit(train_x,epochs=30)   #I faced the error here

在错误下方，请关注帮助我：

Epoch 1/30
---------------------------------------------------------------------------
InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-32-7830734727c4> in <module>
      1 # Train the model with 30 epochs
----> 2 model.fit(train_x,epochs=30)

~/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py in _method_wrapper(self,*args,**kwargs)
     64   def _method_wrapper(self,**kwargs):
     65     if not self._in_multi_worker_mode():  # pylint: disable=protected-access
---> 66       return method(self,**kwargs)
     67 
     68     # Running inside `run_distribute_coordinator` already.

~/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py in fit(self,x,batch_size,epochs,verbose,callbacks,validation_split,validation_data,shuffle,class_weight,sample_weight,initial_epoch,steps_per_epoch,validation_steps,validation_batch_size,validation_freq,max_queue_size,workers,use_multiprocessing)
    846                 batch_size=batch_size):
    847               callbacks.on_train_batch_begin(step)
--> 848               tmp_logs = train_function(iterator)
    849               # Catch OutOfRangeError for Datasets of unknown size.
    850               # This blocks until the batch has finished executing.

~/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in __call__(self,**kwds)
    578         xla_context.Exit()
    579     else:
--> 580       result = self._call(*args,**kwds)
    581 
    582     if tracing_count == self._get_tracing_count():

~/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in _call(self,**kwds)
    609       # In this case we have created variables on the first call,so we run the
    610       # defunned version which is guaranteed to never create variables.
--> 611       return self._stateless_fn(*args,**kwds)  # pylint: disable=not-callable
    612     elif self._stateful_fn is not None:
    613       # Release the lock early so that multiple threads can perform the call

~/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in __call__(self,**kwargs)
   2418     with self._lock:
   2419       graph_function,args,kwargs = self._maybe_define_function(args,kwargs)
-> 2420     return graph_function._filtered_call(args,kwargs)  # pylint: disable=protected-access
   2421 
   2422   @property

~/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _filtered_call(self,kwargs)
   1659       `args` and `kwargs`.
   1660     """
-> 1661     return self._call_flat(
   1662         (t for t in nest.flatten((args,kwargs),expand_composites=True)
   1663          if isinstance(t,(ops.Tensor,~/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _call_flat(self,captured_inputs,cancellation_manager)
   1743         and executing_eagerly):
   1744       # No tape is watching; skip to running the function.
-> 1745       return self._build_call_outputs(self._inference_function.call(
   1746           ctx,cancellation_manager=cancellation_manager))
   1747     forward_backward = self._select_forward_and_backward_functions(

~/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in call(self,ctx,cancellation_manager)
    591       with _InterpolateFunctionError(self):
    592         if cancellation_manager is None:
--> 593           outputs = execute.execute(
    594               str(self.signature.name),595               num_outputs=self._num_outputs,~/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/execute.py in quick_execute(op_name,num_outputs,inputs,attrs,name)
     57   try:
     58     ctx.ensure_initialized()
---> 59     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle,device_name,op_name,60                                         inputs,num_outputs)
     61   except core._NotOkStatusException as e:

InvalidArgumentError:  Received a label value of 3 which is outside the valid range of [0,3).  Label values: 1 1 1 2 2 0 0 2 1 1 1 3 3 3 2 1 3 2 1 0 3 3 1 1 3 3 1 1 1 3 3 3
     [[node sparse_categorical_crossentropy/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits (defined at <ipython-input-28-7830734727c4>:2) ]] [Op:__inference_train_function_549]

Function call stack:
train_function

解决方法

您的标签 (train_y) 包含 0 到 3（含）之间的值：

接收到超出有效范围 [0,3) 的标签值 3。标签值：1 1 1 2 2 0 0 2 1 1 1 3 3 3 2 1 3 2 1 0 3 3 1 1 3 3 1 1 1 3 3 3

这意味着有 4 个不同的标签（0、1、2、3）。

因此你的模型最后一层的维度应该等于4而不是3：

model = keras.Sequential([keras.layers.Flatten(input_shape=(300,300,3)),keras.layers.Dense(256,activation=tf.nn.tanh),keras.layers.Dense(4,activation=tf.nn.softmax)
                         ])