Блог

Я пытаюсь создать пользовательскую метрику точности, как предложено в документах TensorFlow, отслеживая две переменные count и total .

В методе update_state() класса CustomAccuracy мне нужен batch_size для обновления переменной total . Поскольку модель batch_size предназначена None для ввода, я получаю 'ValueError: None values not supported.'

Вот пользовательский класс метрик, который я создал:

 class CustomAccuracy(tf.keras.metrics.Metric):
    def __init__(self, name = 'custom_accuracy', **kwargs):
        super().__init__(name = name, **kwargs)
        self.count = self.add_weight(name = 'count', initializer = 'zeros')
        self.total = self.add_weight(name = 'total', initializer = 'zeros')
        self.custom_accuracy = self.add_weight(name = 'custom_acc', initializer = 'zeros')
    
    def update_state(self, y_true, y_pred, sample_weight = None): 
        correct_values = tf.reduce_sum(tf.cast(tf.argmax(y_pred, axis = 1) == tf.argmax(y_true, axis = 1), "float32"))
        self.count.assign_add(correct_values)
        self.total.assign_add(tf.constant(y_true.shape[0], dtype = "float32"))
        self.custom_accuracy.assign(self.count / self.total)
        
    def result(self):
        return self.custom_accuracy
    
    def reset_states(self):
        self.count.assign(0.0)
        self.total.assign(0.0)
        self.custom_accuracy.assign(0.0)
  

Ошибка, которую я получаю:

 Epoch 1/100
1/1 [==============================] - ETA: 0s - loss: 4.8930 - accuracy: 0.7344 - custom_accuracy: 1.0000
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-139-a286f110fac4> in <module>
      4     batch_size = 192,
      5     epochs = 100,
----> 6     validation_data = (val_data, val_labels),
      7 )

c:usersaniketdocumentsaniketlearning-mlml_envlibsite-packagestensorflowpythonkerasenginetraining.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.

c:usersaniketdocumentsaniketlearning-mlml_envlibsite-packagestensorflowpythonkerasenginetraining.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)
   1131               workers=workers,
   1132               use_multiprocessing=use_multiprocessing,
-> 1133               return_dict=True)
   1134           val_logs = {'val_'   name: val for name, val in val_logs.items()}
   1135           epoch_logs.update(val_logs)

c:usersaniketdocumentsaniketlearning-mlml_envlibsite-packagestensorflowpythonkerasenginetraining.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.

c:usersaniketdocumentsaniketlearning-mlml_envlibsite-packagestensorflowpythonkerasenginetraining.py in evaluate(self, x, y, batch_size, verbose, sample_weight, steps, callbacks, max_queue_size, workers, use_multiprocessing, return_dict)
   1377             with trace.Trace('TraceContext', graph_type='test', step_num=step):
   1378               callbacks.on_test_batch_begin(step)
-> 1379               tmp_logs = test_function(iterator)
   1380               if data_handler.should_sync:
   1381                 context.async_wait()

c:usersaniketdocumentsaniketlearning-mlml_envlibsite-packagestensorflowpythoneagerdef_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()

c:usersaniketdocumentsaniketlearning-mlml_envlibsite-packagestensorflowpythoneagerdef_function.py in _call(self, *args, **kwds)
    812       # In this case we have not created variables on the first call. So we can
    813       # run the first trace but we should fail if variables are created.
--> 814       results = self._stateful_fn(*args, **kwds)
    815       if self._created_variables:
    816         raise ValueError("Creating variables on a non-first call to a function"

c:usersaniketdocumentsaniketlearning-mlml_envlibsite-packagestensorflowpythoneagerfunction.py in __call__(self, *args, **kwargs)
   2826     """Calls a graph function specialized to the inputs."""
   2827     with self._lock:
-> 2828       graph_function, args, kwargs = self._maybe_define_function(args, kwargs)
   2829     return graph_function._filtered_call(args, kwargs)  # pylint: disable=protected-access
   2830 

c:usersaniketdocumentsaniketlearning-mlml_envlibsite-packagestensorflowpythoneagerfunction.py in _maybe_define_function(self, args, kwargs)
   3208           and self.input_signature is None
   3209           and call_context_key in self._function_cache.missed):
-> 3210         return self._define_function_with_shape_relaxation(args, kwargs)
   3211 
   3212       self._function_cache.missed.add(call_context_key)

c:usersaniketdocumentsaniketlearning-mlml_envlibsite-packagestensorflowpythoneagerfunction.py in _define_function_with_shape_relaxation(self, args, kwargs)
   3140 
   3141     graph_function = self._create_graph_function(
-> 3142         args, kwargs, override_flat_arg_shapes=relaxed_arg_shapes)
   3143     self._function_cache.arg_relaxed[rank_only_cache_key] = graph_function
   3144 

c:usersaniketdocumentsaniketlearning-mlml_envlibsite-packagestensorflowpythoneagerfunction.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,

c:usersaniketdocumentsaniketlearning-mlml_envlibsite-packagestensorflowpythonframeworkfunc_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,

c:usersaniketdocumentsaniketlearning-mlml_envlibsite-packagestensorflowpythoneagerdef_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 

c:usersaniketdocumentsaniketlearning-mlml_envlibsite-packagestensorflowpythonframeworkfunc_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:usersaniketdocumentsaniketlearning-mlml_envlibsite-packagestensorflowpythonkerasenginetraining.py:1224 test_function  *
        return step_function(self, iterator)
    <ipython-input-135-4207cf41498c>:12 update_state  *
        self.total.assign_add(tf.constant(y_true.shape[0], dtype = "float32"))
    c:usersaniketdocumentsaniketlearning-mlml_envlibsite-packagestensorflowpythonframeworkconstant_op.py:264 constant  **
        allow_broadcast=True)
    c:usersaniketdocumentsaniketlearning-mlml_envlibsite-packagestensorflowpythonframeworkconstant_op.py:282 _constant_impl
        allow_broadcast=allow_broadcast))
    c:usersaniketdocumentsaniketlearning-mlml_envlibsite-packagestensorflowpythonframeworktensor_util.py:444 make_tensor_proto
        raise ValueError("None values not supported.")

    ValueError: None values not supported.
  

Вот минимальный пример кода, который воспроизводит вышеупомянутую проблему:

 import tensorflow as tf
import numpy as np


# Creating Custom Metric
class CustomAccuracy(tf.keras.metrics.Metric):
    def __init__(self, name = 'custom_accuracy', **kwargs):
        super().__init__(name = name, **kwargs)
        self.count = self.add_weight(name = 'count', initializer = 'zeros')
        self.total = self.add_weight(name = 'total', initializer = 'zeros')
        self.custom_accuracy = self.add_weight(name = 'custom_acc', initializer = 'zeros')
    
    def update_state(self, y_true, y_pred, sample_weight = None): 
        correct_values = tf.reduce_sum(tf.cast(tf.argmax(y_pred, axis = 1) == tf.argmax(y_true, axis = 1), "float32"))
        self.count.assign_add(correct_values)
        self.total.assign_add(tf.constant(y_true.shape[0], dtype = "float32"))
        self.custom_accuracy.assign(self.count / self.total)
        
    def result(self):
        return self.custom_accuracy
    
    def reset_states(self):
        self.count.assign(0.0)
        self.total.assign(0.0)
        self.custom_accuracy.assign(0.0)

        
def create_model():
    input1 = tf.keras.Input(shape=(13,))
    hidden1 = tf.keras.layers.Dense(units = 12, activation='relu')(input1)
    hidden2 = tf.keras.layers.Dense(units = 6, activation='relu')(hidden1)
    output1 = tf.keras.layers.Dense(units = 2, activation='sigmoid')(hidden2)
    
    model = tf.keras.models.Model(inputs = input1, outputs = output1, name= "functional1")
    
    
    model.compile(optimizer='adam',
                  loss= 'binary_crossentropy',
                  metrics=['accuracy',CustomAccuracy()])
    return model
model = create_model()

x1 = np.random.randint(0,10, size = (240,13))
y1 = np.random.randint(0,2, size = (240,2))

history = model.fit(
    x = x1, 
    y = y1,
    batch_size = 32,
    epochs = 100,
    validation_split = 0.2,
)
  

Все это работает, если я передаю run_eagerly = True метод компиляции, но мне нужно решение без его использования.