ValueError：形状（无，3）和（无，16）不兼容

Question

I'm trying to build an architecture for predicting objects with 3 different classes/labels. I've tried to do one hot encoding before learning the data. This is the shape of data:

X train      X test      Y train     Y test
(585, 24)    (195, 24)   (585, 3)    (195, 3)

But it always gives me this error:

ValueError: Shapes (None, 3) and (None, 16) are incompatible

This is the full traceback:

Model: "sequential_14"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_84 (Dense)             (None, 32)                800       
_________________________________________________________________
dense_85 (Dense)             (None, 1024)              33792     
_________________________________________________________________
dense_86 (Dense)             (None, 512)               524800    
_________________________________________________________________
dense_87 (Dense)             (None, 256)               131328    
_________________________________________________________________
dense_88 (Dense)             (None, 128)               32896     
_________________________________________________________________
dense_89 (Dense)             (None, 16)                2064      
_________________________________________________________________
activation_14 (Activation)   (None, 16)                0         
=================================================================
Total params: 725,680
Trainable params: 725,680
Non-trainable params: 0
_________________________________________________________________
Epoch 1/1000
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-46-7c4cfcd2abc7> in <module>
      6 
      7 model = nn_model(max_len)
----> 8 history=check_model(model, X_train,y_train,X_test,y_test, EPOCHS, BATCH_SIZE)

<ipython-input-45-ca2dcbc233ca> in check_model(model_, x, y, x_val, y_val, epochs_, batch_size_)
     50                       epochs=epochs_,
     51                       batch_size=batch_size_,
---> 52                       validation_data=(x_val,y_val))
     53     return hist

~\Anaconda3\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\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\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\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\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\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\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\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\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\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\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\Anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:806 train_function  *
        return step_function(self, iterator)
    C:\Users\Anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:796 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    C:\Users\Anaconda3\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\Anaconda3\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\Anaconda3\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2945 _call_for_each_replica
        return fn(*args, **kwargs)
    C:\Users\Anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:789 run_step  **
        outputs = model.train_step(data)
    C:\Users\Anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py:749 train_step
        y, y_pred, sample_weight, regularization_losses=self.losses)
    C:\Users\Anaconda3\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\Anaconda3\lib\site-packages\tensorflow\python\keras\losses.py:149 __call__
        losses = ag_call(y_true, y_pred)
    C:\Users\Anaconda3\lib\site-packages\tensorflow\python\keras\losses.py:253 call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    C:\Users\Anaconda3\lib\site-packages\tensorflow\python\util\dispatch.py:201 wrapper
        return target(*args, **kwargs)
    C:\Users\Anaconda3\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\Anaconda3\lib\site-packages\tensorflow\python\util\dispatch.py:201 wrapper
        return target(*args, **kwargs)
    C:\Users\Anaconda3\lib\site-packages\tensorflow\python\keras\backend.py:4687 categorical_crossentropy
        target.shape.assert_is_compatible_with(output.shape)
    C:\Users\Anaconda3\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, 3) and (None, 16) are incompatible

This is the relevant code:

# Encode label
le = LabelEncoder()
le.fit(glcm_df["label"].values)

print("categorical label : \n", le.classes_)

Y = le.transform(glcm_df['label'].values)
Y = to_categorical(Y)

# Split dataset
X_train, X_test, y_train, y_test = \
                    train_test_split(X, 
                                     Y, 
                                     test_size=0.25, 
                                     random_state=42)

def nn_model(max_len):
    model = Sequential()
    model.add(Dense(32, 
                    activation="elu",
                    input_shape=(max_len,)))
    model.add(Dense(1024, activation="elu"))
    model.add(Dense(512, activation="elu"))
    model.add(Dense(256, activation="elu"))
    model.add(Dense(128, activation="elu"))
    model.add(Dense(16))
    model.add(Activation("sigmoid"))
    
    model.summary() 
    
    model.compile(optimizer='adam', 
                  loss='categorical_crossentropy',
                  metrics = ['accuracy', precision, recall])

    return model
def check_model(model_, x, y, x_val, y_val, epochs_, batch_size_):
    hist = model_.fit(x, 
                      y,
                      epochs=epochs_,
                      batch_size=batch_size_,
                      validation_data=(x_val,y_val))
    return hist 

# Train data
max_len = X_train.shape[1]

EPOCHS = 1000
BATCH_SIZE = 32

model = nn_model(max_len)
history=check_model(model, X_train,y_train,X_test,y_test, EPOCHS, BATCH_SIZE)

I also tried to do to_categorical for both my y_train & y_test but it always gives me a similar error (it's just the shape is different) like:

ValueError: Shapes (None, 3, 3) and (None, 16) are incompatible

EDIT 1.0:

The shape for X is (780, 24) & for Y is (780, 3):

Answer 1

The last layer of a neural network with a sigmoid activation function in a multiclass classification problem has to reflect the number of classes that are being predicted. Here 3 classes are being used so just change it from 16 to 3.

def nn_model(max_len):
    model = Sequential()
    model.add(Dense(32, 
                    activation="elu",
                    input_shape=(max_len,)))
    model.add(Dense(1024, activation="elu"))
    model.add(Dense(512, activation="elu"))
    model.add(Dense(256, activation="elu"))
    model.add(Dense(128, activation="elu"))
    model.add(Dense(3))
    model.add(Activation("sigmoid"))
    
    model.summary() 
    
    model.compile(optimizer='adam', 
                  loss='categorical_crossentropy',
                  metrics = ['accuracy', precision, recall])

    return model