CODEWITHSUNDEEP
pythontensorflowkeras
Ahmad
Ahmad

Reputation: 742

Received a label value of 17 which is outside the valid range of [0, 12) - Keras Python

Keras is unfamiliar to me. I'm attempting to put some programming into action.

The data shape is as follows:

Train shape X: (249951, 5, 52)  y  (249951,)
Test shape X: (263343, 5, 52)  y  (263343,)  # Do not confuse with the distribution, it is juts toy example

My date contains twelve labels. The keras CNN architecture is as follows:

def get_compiled_model():
    # Make a simple 2-layer densely-connected neural network.
    inputs = keras.Input(shape=(260,))
    x = keras.layers.Dense(256, activation="relu")(inputs)
    x = keras.layers.Dense(256, activation="relu")(x)
    outputs = keras.layers.Dense(12)(x)    # 12  classes
    model = keras.Model(inputs, outputs)
    model.compile(
        optimizer=keras.optimizers.Adam(),
        loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
        metrics=[keras.metrics.SparseCategoricalAccuracy()],
    )
    return model

Now, I feed 12 neuron to the output layer, as my data contains 12 classes. However, the following error message is displayed:

    Use `tf.data.Iterator.get_next_as_optional()` instead.
2255/7811 [=======>......................] - ETA: 18s - loss: 0.1109 - sparse_categorical_accuracy: 0.99452021-04-19 16:32:33.591493: W tensorflow/core/framework/op_kernel.cc:1767] OP_REQUIRES failed at sparse_xent_op.cc:90 : Invalid argument: Received a label value of 17 which is outside the valid range of [0, 12).  Label values: 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 17 17 17 17 17
Traceback (most recent call last):
  File "C:\Users\Nafees Ahmed\AppData\Local\Programs\Python\Python38\lib\contextlib.py", line 131, in __exit__
    self.gen.throw(type, value, traceback)
  File "C:\Users\Nafees Ahmed\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\ops\variable_scope.py", line 2804, in variable_creator_scope
    yield
  File "C:\Users\Nafees Ahmed\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\keras\engine\training.py", line 1098, in fit
    tmp_logs = train_function(iterator)
  File "C:\Users\Nafees Ahmed\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\eager\def_function.py", line 780, in __call__
    result = self._call(*args, **kwds)
  File "C:\Users\Nafees Ahmed\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\eager\def_function.py", line 807, in _call
    return self._stateless_fn(*args, **kwds)  # pylint: disable=not-callable
  File "C:\Users\Nafees Ahmed\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\eager\function.py", line 2829, in __call__
    return graph_function._filtered_call(args, kwargs)  # pylint: disable=protected-access
  File "C:\Users\Nafees Ahmed\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\eager\function.py", line 1843, in _filtered_call
    return self._call_flat(
  File "C:\Users\Nafees Ahmed\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\eager\function.py", line 1923, in _call_flat
    return self._build_call_outputs(self._inference_function.call(
  File "C:\Users\Nafees Ahmed\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\eager\function.py", line 545, in call
    outputs = execute.execute(
  File "C:\Users\Nafees Ahmed\AppData\Local\Programs\Python\Python38\lib\site-packages\tensorflow\python\eager\execute.py", line 59, in quick_execute
    tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
tensorflow.python.framework.errors_impl.InvalidArgumentError:  Received a label value of 17 which is outside the valid range of [0, 12).  Label values: 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 17 17 17 17 17
     [[node sparse_categorical_crossentropy/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits (defined at Users\Nafees Ahmed\AppData\Local\Programs\Python\Python38\lib\threading.py:932) ]] [Op:__inference_train_function_846]
Function call stack:
train_function

Main Error: tensorflow.python.framework.errors_impl.InvalidArgumentError: Received a label value of 17 which is outside the valid range of [0, 12). Label values: 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 17 17 17 17 17

Upvotes: 1

Views: 2375

Answers (1)

Ihmon
Ihmon

Reputation: 343

If your label(y) is numeric, it will not work. You need to convert it to binary data, since it is multiclass binary problem. Maybe you can use below to do so.

y_train = np_utils.to_categorical(y_train, num_classes)
y_test = np_utils.to_categorical(y_test, num_classes)

num_classes is 12, in your case. However, 12 classes sound too many for me. Is this really multiclass, rather than multilabel?

Upvotes: 1

Related Questions