Блог

Код для построения модели, проблема, с которой я сталкиваюсь, заключается в том, что когда я пытаюсь загрузить модель и реализовать для тестирования набора данных, я получаю сообщение об ошибке:

 learning_rate=0.001

epochs = 10
decay_rate = learning_rate / epochs

def scheduler(epochs, lr):
    if epochs == 15:
        lr = 0.001
        return lr
    else:
        lr = lr * tensorflow.math.exp(-0.1)
        return lr

callback = keras.callbacks.LearningRateScheduler(scheduler)
    
wv_model = Sequential()
# Add embedding layer 
# No of output dimenstions is 100 as we embedded with Word2Vec 100d
Embed_Layer = Embedding(vocab_size, 100, weights=[embedding_matrix], input_length=(MAX_SEQUENCE_LENGTH,), trainable=True)

# define Inputs
review_input = Input(shape=(MAX_SEQUENCE_LENGTH,),dtype= 'int32',name = 'review_input')
review_embedding = Embed_Layer(review_input)
Flatten_Layer = Flatten()
review_flatten = Flatten_Layer(review_embedding)
output_size = 2

dense1 = Dense(100,activation='relu')(review_flatten)
dense2 = Dense(32,activation='relu')(dense1)
predict = Dense(5, activation='softmax')(dense2)

wv_model = Model(inputs=[review_input],outputs=[predict])
# wv_model.compile(optimizer='adam',loss='categorical_crossentropy',metrics=['acc'])
opt = keras.optimizers.SGD(lr = 0.01, momentum=0.8, decay=0.0)
wv_model.compile(loss='mean_squared_error', optimizer=opt, metrics=['mean_squared_error'])

tensorboard = TensorBoard(
    log_dir="logs",
    histogram_freq=1,
    write_graph=True,
    write_images=False,
    update_freq="epoch",
    profile_batch=2,
    embeddings_freq=0,
    embeddings_metadata=None)
keras_callbacks = [tensorboard]
checkpoint = ModelCheckpoint('best_model.h5', monitor='val_loss', mode='min', verbose=1, save_best_only=True)
stp = keras.callbacks.EarlyStopping(patience=4)
callbacks_list = [checkpoint,stp, tensorboard,callback]

wv_model.fit(X_train, y_train, validation_data=(X_test, y_test), 
          epochs=epochs, batch_size=256,
          verbose=1, callbacks=callbacks_list)
eval = wv_model.evaluate(X_test, y_test)[1]
print(eval)
wv_model.load_weights('./models/best_model.h5')

print(wv_model.summary())
 

Out:

 Layer (type)                 Output Shape              Param #   
=================================================================
review_input (InputLayer)    [(None, 100)]             0         
_________________________________________________________________
embedding_8 (Embedding)      (None, 100, 100)          22228800  
_________________________________________________________________
flatten_8 (Flatten)          (None, 10000)             0         
_________________________________________________________________
dense_24 (Dense)             (None, 100)               1000100   
_________________________________________________________________
dense_25 (Dense)             (None, 32)                3232      
_________________________________________________________________
dense_26 (Dense)             (None, 5)                 165       
=================================================================
Total params: 23,232,297
Trainable params: 23,232,297
Non-trainable params: 0
_________________________________________________________________
None
 

Для проверки набора данных:

 predictions = load_model('./models/best_model.h5').predict(X12_test)

print("y_test", y_test)
print("predictions", predictions)
print("validation set RMSE ", rmse2(predictions, y_test))
y_test = y_test.overall.values
 

Out:

 WARNING:tensorflow:Model was constructed with shape (None, 100) for input Tensor("review_input_13:0", shape=(None, 100), dtype=int32), but it was called on an input with incompatible shape (None, 6000).
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-80-82850281ff1c> in <module>
----> 1 predictions_o = load_model('./models/best_model.h5').predict(X12_test)
      2 
      3 print("y1_test_truth", y1_test)
      4 print("predictions_o", predictions_o)
      5 print("validation set RMSE ", rmse2(predictions_o, y1_test))

~/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py in _method_wrapper(self, *args, **kwargs)
    128       raise ValueError('{} is not supported in multi-worker mode.'.format(
    129           method.__name__))
--> 130     return method(self, *args, **kwargs)
    131 
    132   return tf_decorator.make_decorator(

~/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py in predict(self, x, batch_size, verbose, steps, callbacks, max_queue_size, workers, use_multiprocessing)
   1597           for step in data_handler.steps():
   1598             callbacks.on_predict_batch_begin(step)
-> 1599             tmp_batch_outputs = predict_function(iterator)
   1600             if data_handler.should_sync:
   1601               context.async_wait()

~/.local/lib/python3.8/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()

~/.local/lib/python3.8/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

~/.local/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
    694     self._graph_deleter = FunctionDeleter(self._lifted_initializer_graph)
    695     self._concrete_stateful_fn = (
--> 696         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
    697             *args, **kwds))
    698 

~/.local/lib/python3.8/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 

~/.local/lib/python3.8/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

~/.local/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   3063     arg_names = base_arg_names   missing_arg_names
   3064     graph_function = ConcreteFunction(
-> 3065         func_graph_module.func_graph_from_py_func(
   3066             self._name,
   3067             self._python_function,

~/.local/lib/python3.8/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,

~/.local/lib/python3.8/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 

~/.local/lib/python3.8/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:

    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:1462 predict_function  *
        return step_function(self, iterator)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:1452 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:1211 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:2585 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:2945 _call_for_each_replica
        return fn(*args, **kwargs)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:1445 run_step  **
        outputs = model.predict_step(data)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:1418 predict_step
        return self(x, training=False)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/base_layer.py:985 __call__
        outputs = call_fn(inputs, *args, **kwargs)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/functional.py:385 call
        return self._run_internal_graph(
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/functional.py:508 _run_internal_graph
        outputs = node.layer(*args, **kwargs)
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/base_layer.py:975 __call__
        input_spec.assert_input_compatibility(self.input_spec, inputs,
    /home/x/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/input_spec.py:212 assert_input_compatibility
        raise ValueError(

    ValueError: Input 0 of layer dense_24 is incompatible with the layer: expected axis -1 of input shape to have value 10000 but received input with shape [None, 600000]
 

Я пытаюсь определить, где и что мне нужно изменить, чтобы убедиться, что размеры работают правильно, однако мне не удалось определить, что именно мне нужно изменить. Любая помощь будет принята с благодарностью.

Обновления:

форма данных:

 from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(data, y, test_size=0.2, random_state = 40)

[nSamp, inpShape] = X_train.shape

print("X train shape ", X_train.shape)
print("X test shape ", X_test.shape)
print("y train shape ",y_train.shape)
print("y test shape ",y_test.shape)

print(nSamp, inpShape)
 

Out:

 X train shape  (160000, 100)
X test shape  (40000, 100)
y train shape  (160000, 5)
y test shape  (40000, 5)
160000 100
 

Из предупреждения в первой строке кажется, что X12_test имеет неправильную форму, согласно имеющемуся у вас предупреждению, ваша модель построена так, чтобы принимать входные shape (None, 100) данные во время вызова с использованием ввода shape (None, 6000)