Value error after fitting my custom model

Question

I am creating an encoder on the fashion MNIST dataset. The encoder consists of three layers, Each input image is flattened into a dimensionality of 784. The three encoder layers are with output dimensionality of 128, 64, 32. But after fitting the model, it throws a value error - ValueError: Input 0 is incompatible with layer model_7: expected shape=(None, 784), found shape=(32, 28, 28)

the code:-

#Encoder
input1 = Input(shape = (784,))
hidden1 = Dense(128, activation = 'relu')(input1)
hidden2 = Dense(64, activation = 'relu')(hidden1)
hidden3 = Dense(32, activation = 'relu')(hidden2)
model = Model(inputs = input1, outputs = hidden3)

model summary:

Model: "model_7"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_17 (InputLayer)        [(None, 784)]             0         
_________________________________________________________________
dense_43 (Dense)             (None, 128)               100480    
_________________________________________________________________
dense_44 (Dense)             (None, 64)                8256      
_________________________________________________________________
dense_45 (Dense)             (None, 32)                2080      
=================================================================
Total params: 110,816
Trainable params: 110,816
Non-trainable params: 0

The error after fitting the model:-

Epoch 1/3
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-42-3295f6ac1688> in <module>
----> 1 model.fit(x_train, y_train, epochs = 3)

C:\Anaconda\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)
   1098                 _r=1):
   1099               callbacks.on_train_batch_begin(step)
-> 1100               tmp_logs = self.train_function(iterator)
   1101               if data_handler.should_sync:
   1102                 context.async_wait()

C:\Anaconda\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
    826     tracing_count = self.experimental_get_tracing_count()
    827     with trace.Trace(self._name) as tm:
--> 828       result = self._call(*args, **kwds)
    829       compiler = "xla" if self._experimental_compile else "nonXla"
    830       new_tracing_count = self.experimental_get_tracing_count()

C:\Anaconda\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
    869       # This is the first call of __call__, so we have to initialize.
    870       initializers = []
--> 871       self._initialize(args, kwds, add_initializers_to=initializers)
    872     finally:
    873       # At this point we know that the initialization is complete (or less

C:\Anaconda\lib\site-packages\tensorflow\python\eager\def_function.py in _initialize(self, args, kwds, add_initializers_to)
    723     self._graph_deleter = FunctionDeleter(self._lifted_initializer_graph)
    724     self._concrete_stateful_fn = (
--> 725         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
    726             *args, **kwds))
    727 

C:\Anaconda\lib\site-packages\tensorflow\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
   2967       args, kwargs = None, None
   2968     with self._lock:
-> 2969       graph_function, _ = self._maybe_define_function(args, kwargs)
   2970     return graph_function
   2971 

C:\Anaconda\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs)
   3359 
   3360           self._function_cache.missed.add(call_context_key)
-> 3361           graph_function = self._create_graph_function(args, kwargs)
   3362           self._function_cache.primary[cache_key] = graph_function
   3363 

C:\Anaconda\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   3194     arg_names = base_arg_names + missing_arg_names
   3195     graph_function = ConcreteFunction(
-> 3196         func_graph_module.func_graph_from_py_func(
   3197             self._name,
   3198             self._python_function,

C:\Anaconda\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)
    988         _, original_func = tf_decorator.unwrap(python_func)
    989 
--> 990       func_outputs = python_func(*func_args, **func_kwargs)
    991 
    992       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

C:\Anaconda\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds)
    632             xla_context.Exit()
    633         else:
--> 634           out = weak_wrapped_fn().__wrapped__(*args, **kwds)
    635         return out
    636 

C:\Anaconda\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs)
    975           except Exception as e:  # pylint:disable=broad-except
    976             if hasattr(e, "ag_error_metadata"):
--> 977               raise e.ag_error_metadata.to_exception(e)
    978             else:
    979               raise

ValueError: in user code:

    C:\Anaconda\lib\site-packages\tensorflow\python\keras\engine\training.py:805 train_function  *
        return step_function(self, iterator)
    C:\Anaconda\lib\site-packages\tensorflow\python\keras\engine\training.py:795 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    C:\Anaconda\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:1259 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    C:\Anaconda\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:2730 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    C:\Anaconda\lib\site-packages\tensorflow\python\distribute\distribute_lib.py:3417 _call_for_each_replica
        return fn(*args, **kwargs)
    C:\Anaconda\lib\site-packages\tensorflow\python\keras\engine\training.py:788 run_step  **
        outputs = model.train_step(data)
    C:\Anaconda\lib\site-packages\tensorflow\python\keras\engine\training.py:754 train_step
        y_pred = self(x, training=True)
    C:\Anaconda\lib\site-packages\tensorflow\python\keras\engine\base_layer.py:998 __call__
        input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
    C:\Anaconda\lib\site-packages\tensorflow\python\keras\engine\input_spec.py:271 assert_input_compatibility
        raise ValueError('Input ' + str(input_index) +

    ValueError: Input 0 is incompatible with layer model_7: expected shape=(None, 784), found shape=(32, 28, 28)

What's the meaning of this error, do I need to change the input dimension. If yes then what will be my input dimension?

Shape of the train and test data- Thnaks in advance.

so this is not flattened... you can pass (28,28,) as input_shape and then use a Flatten layer insider the network — Marco Cerliani
– Marco Cerliani, Commented May 17, 2021 at 7:26
build an AE and fit only the encoder has no sense... follow this track to build an AE on mnist: colab.research.google.com/drive/… — Marco Cerliani
– Marco Cerliani, Commented May 17, 2021 at 8:04

Susmit Agrawal · Accepted Answer · 2021-05-17 13:26:54Z

0

Your input images are 28 x 28 images, that need to converted to a vector of 784 values. While there are multiple ways to do this, the easiest would be to use the Flatten layer provided by Keras. In this case, your input to the model will be the 28 x 28 images:

input1 = Input(shape = (28, 28))
flattened_input = Flatten()(input1)
hidden1 = Dense(128, activation = 'relu')(flattened_input)
hidden2 = Dense(64, activation = 'relu')(hidden1)
hidden3 = Dense(32, activation = 'relu')(hidden2)
model = Model(inputs = input1, outputs = hidden3)

answered May 17, 2021 at 13:26

Susmit Agrawal

3,7622 gold badges15 silver badges34 bronze badges

Sign up to request clarification or add additional context in comments.

1 Comment

coding_ninza Over a year ago

ValueError: Dimensions must be equal, but are 32 and 28 for '{{node mean_squared_error/SquaredDifference}} = SquaredDifference[T=DT_FLOAT](model_3/dense_13/Relu, mean_squared_error/Cast)' with input shapes: [?,32], [?,28,28].

Collectives™ on Stack Overflow

Value error after fitting my custom model

1 Answer 1

1 Comment

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

1 Comment

Related