How can I fix the value error issue tensorflow?

Question

I am getting a value error when using model.fit(), I can't understand what is the mistake. I had done all the process correctly i think.

This is my model,

model = Sequential()

model.add(Dense(42,activation='relu'))   # Input layer
model.add(Dropout(0.25))

model.add(Dense(21,activation='relu'))   # Hidden layer
model.add(Dropout(0.25))

model.add(Dense(10,activation='relu'))   # Hidden layer
model.add(Dropout(0.25))

model.add(Dense(5,activation='relu'))    # Hidden layer
model.add(Dropout(0.25))

model.add(Dense(11,activation='softmax'))   # Output layer

model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

Epoch 1/100
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-26-9dd45f56d29e> in <module>
----> 1 model.fit(x=scaled_x_train, y=y_train, validation_data=(scaled_x_test, y_test), epochs=100)

~\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\keras\engine\training.py in _method_wrapper(self, *args, **kwargs)
    106   def _method_wrapper(self, *args, **kwargs):
    107     if not self._in_multi_worker_mode():  # pylint: disable=protected-access
--> 108       return method(self, *args, **kwargs)
    109 
    110     # Running inside `run_distribute_coordinator` already.

~\anaconda3\envs\tensorflow\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, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
   1096                 batch_size=batch_size):
   1097               callbacks.on_train_batch_begin(step)
-> 1098               tmp_logs = train_function(iterator)
   1099               if data_handler.should_sync:
   1100                 context.async_wait()

~\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
    778       else:
    779         compiler = "nonXla"
--> 780         result = self._call(*args, **kwds)
    781 
    782       new_tracing_count = self._get_tracing_count()

~\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
    821       # This is the first call of __call__, so we have to initialize.
    822       initializers = []
--> 823       self._initialize(args, kwds, add_initializers_to=initializers)
    824     finally:
    825       # At this point we know that the initialization is complete (or less

~\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\eager\def_function.py in _initialize(self, args, kwds, add_initializers_to)
    695     self._concrete_stateful_fn = (
    696         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
--> 697             *args, **kwds))
    698 
    699     def invalid_creator_scope(*unused_args, **unused_kwds):

~\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
   2853       args, kwargs = None, None
   2854     with self._lock:
-> 2855       graph_function, _, _ = self._maybe_define_function(args, kwargs)
   2856     return graph_function
   2857 

~\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs)
   3211 
   3212       self._function_cache.missed.add(call_context_key)
-> 3213       graph_function = self._create_graph_function(args, kwargs)
   3214       self._function_cache.primary[cache_key] = graph_function
   3215       return graph_function, args, kwargs

~\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   3073             arg_names=arg_names,
   3074             override_flat_arg_shapes=override_flat_arg_shapes,
-> 3075             capture_by_value=self._capture_by_value),
   3076         self._function_attributes,
   3077         function_spec=self.function_spec,

~\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\framework\func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
    984         _, original_func = tf_decorator.unwrap(python_func)
    985 
--> 986       func_outputs = python_func(*func_args, **func_kwargs)
    987 
    988       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

~\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds)
    598         # __wrapped__ allows AutoGraph to swap in a converted function. We give
    599         # the function a weak reference to itself to avoid a reference cycle.
--> 600         return weak_wrapped_fn().__wrapped__(*args, **kwds)
    601     weak_wrapped_fn = weakref.ref(wrapped_fn)
    602 

~\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs)
    971           except Exception as e:  # pylint:disable=broad-except
    972             if hasattr(e, "ag_error_metadata"):
--> 973               raise e.ag_error_metadata.to_exception(e)
    974             else:
    975               raise

ValueError: in user code:

    C:\Users\psiva\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\keras\engine\training.py:806 train_function  *
        return step_function(self, iterator)
    C:\Users\psiva\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\keras\engine\training.py:796 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    C:\Users\psiva\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1211 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    C:\Users\psiva\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2585 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    C:\Users\psiva\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2945 _call_for_each_replica
        return fn(*args, **kwargs)
    C:\Users\psiva\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\keras\engine\training.py:789 run_step  **
        outputs = model.train_step(data)
    C:\Users\psiva\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\keras\engine\training.py:749 train_step
        y, y_pred, sample_weight, regularization_losses=self.losses)
    C:\Users\psiva\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\keras\engine\compile_utils.py:204 __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    C:\Users\psiva\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\keras\losses.py:149 __call__
        losses = ag_call(y_true, y_pred)
    C:\Users\psiva\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\keras\losses.py:253 call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    C:\Users\psiva\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\util\dispatch.py:201 wrapper
        return target(*args, **kwargs)
    C:\Users\psiva\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\keras\losses.py:1535 categorical_crossentropy
        return K.categorical_crossentropy(y_true, y_pred, from_logits=from_logits)
    C:\Users\psiva\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\util\dispatch.py:201 wrapper
        return target(*args, **kwargs)
    C:\Users\psiva\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\keras\backend.py:4687 categorical_crossentropy
        target.shape.assert_is_compatible_with(output.shape)
    C:\Users\psiva\anaconda3\envs\tensorflow\lib\site-packages\tensorflow\python\framework\tensor_shape.py:1134 assert_is_compatible_with
        raise ValueError("Shapes %s and %s are incompatible" % (self, other))

    ValueError: Shapes (None, 1) and (None, 11) are incompatible

please help me regarding this issue. This code I had written is according to the tensorflow 2.0 and python 3.7. Tell me the fixes I want to make in this code. My features are 42 and the output target variable has 11 classes.

Answer 1

Did you specify the input shape anywhere? You can specify it by making the code below the first line in the model. Documentation is here.

   model.add(tf.keras.Input(shape=None,batch_size=None,name=None,dtype=None,sparse=False,
    tensor=None,  ragged=False, **kwargs)
#alternatively you can specify it in the first dense layer with
model.add(layers.Dense(21, activation="relu", input_shape=(put your input dimensions here)))

Also check the training and test data labels. The dimensions for the labels have to match the number of neurons (11) in your final layer. Since you are using categorical cross entropy these labels need to be one hot encoded. If your labels are integer encoded use sparse categorical cross entropy. Documentation is here.

Answer 2

You need to make sure your labels are one-hot encoded. Try:

y_train = tf.keras.utils.to_categorical(y_train, 11)
y_test= tf.keras.utils.to_categorical(y_test, 11)

Be absolutely sure that the number of neurons in your final layer is the number of columns in your labels.

assert model.layers[-1].units == y_train.shape[-1] == y_test.shape[-1]

Answer 3

I think the error might be caused by misstating the labels' shape. meaning: ( , 1) should change to ( , 11). I believe this code might help you.

from sklearn.preprocessing import OneHotEncoder
onehot_encoder = OneHotEncoder(sparse=False)
labels_i = onehot_encoder.fit_transform(np.reshape(labels, (-1, 1)))

this code onehots your labels. if you have 11 different classes, convert your labels` shape (_, 11).