Создаю свои собственные TFRecords, и я не могу правильно использовать наборы данных в моих моделях. Просто чтобы проверить, были ли это мои текущие файлы или что-то в коде модели, я использовал tfds с MNIST и у меня та же ошибка.
Ошибка: IndexError: tuple index out of range Полный вывод ниже. Я делаю это из записной книжки Jupyter, если она что-то меняет.
1/Unknown - 0s 47ms/step
--------------------------------------------------------------------------- IndexError Traceback (most recent call last) <ipython-input-302-f8e9089d7285> in <module>
----> 1 model.fit(dataset['train'].batch(4096))
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/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_freq, max_queue_size, workers, use_multiprocessing,
**kwargs)
817 max_queue_size=max_queue_size,
818 workers=workers,
--> 819 use_multiprocessing=use_multiprocessing)
820
821 def evaluate(self,
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py in fit(self, model, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, max_queue_size, workers, use_multiprocessing,
**kwargs)
340 mode=ModeKeys.TRAIN,
341 training_context=training_context,
--> 342 total_epochs=epochs)
343 cbks.make_logs(model, epoch_logs, training_result, ModeKeys.TRAIN)
344
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2.py in run_one_epoch(model, iterator, execution_function, dataset_size, batch_size, strategy, steps_per_epoch, num_samples, mode, training_context, total_epochs)
126 step=step, mode=mode, size=current_batch_size) as batch_logs:
127 try:
--> 128 batch_outs = execution_function(iterator)
129 except (StopIteration, errors.OutOfRangeError):
130 # TODO(kaftan): File bug about tf function and errors.OutOfRangeError?
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2_utils.py in execution_function(input_fn)
96 # `numpy` translates Tensors to values in Eager mode.
97 return nest.map_structure(_non_none_constant_value,
---> 98 distributed_function(input_fn))
99
100 return execution_function
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in __call__(self, *args, **kwds)
566 xla_context.Exit()
567 else:
--> 568 result = self._call(*args, **kwds)
569
570 if tracing_count == self._get_tracing_count():
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in _call(self, *args, **kwds)
613 # This is the first call of __call__, so we have to initialize.
614 initializers = []
--> 615 self._initialize(args, kwds, add_initializers_to=initializers)
616 finally:
617 # At this point we know that the initialization is complete (or less
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
495 self._concrete_stateful_fn = (
496 self._stateful_fn._get_concrete_function_internal_garbage_collected(
# pylint: disable=protected-access
--> 497 *args, **kwds))
498
499 def invalid_creator_scope(*unused_args, **unused_kwds):
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args,
**kwargs) 2387 args, kwargs = None, None 2388 with self._lock:
-> 2389 graph_function, _, _ = self._maybe_define_function(args, kwargs) 2390 return graph_function 2391
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _maybe_define_function(self, args, kwargs) 2701 2702 self._function_cache.missed.add(call_context_key)
-> 2703 graph_function = self._create_graph_function(args, kwargs) 2704 self._function_cache.primary[cache_key] = graph_function 2705 return graph_function, args, kwargs
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes) 2591 arg_names=arg_names, 2592 override_flat_arg_shapes=override_flat_arg_shapes,
-> 2593 capture_by_value=self._capture_by_value), 2594 self._function_attributes, 2595 # Tell the ConcreteFunction to clean up its graph once it goes out of
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/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)
976 converted_func)
977
--> 978 func_outputs = python_func(*func_args, **func_kwargs)
979
980 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in wrapped_fn(*args, **kwds)
437 # __wrapped__ allows AutoGraph to swap in a converted function. We give
438 # the function a weak reference to itself to avoid a reference cycle.
--> 439 return weak_wrapped_fn().__wrapped__(*args, **kwds)
440 weak_wrapped_fn = weakref.ref(wrapped_fn)
441
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2_utils.py in distributed_function(input_iterator)
83 args = _prepare_feed_values(model, input_iterator, mode, strategy)
84 outputs = strategy.experimental_run_v2(
---> 85 per_replica_function, args=args)
86 # Out of PerReplica outputs reduce or pick values to return.
87 all_outputs = dist_utils.unwrap_output_dict(
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/distribute/distribute_lib.py in experimental_run_v2(self, fn, args, kwargs)
761 fn = autograph.tf_convert(fn, ag_ctx.control_status_ctx(),
762 convert_by_default=False)
--> 763 return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
764
765 def reduce(self, reduce_op, value, axis):
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/distribute/distribute_lib.py in call_for_each_replica(self, fn, args, kwargs) 1817 kwargs
= {} 1818 with self._container_strategy().scope():
-> 1819 return self._call_for_each_replica(fn, args, kwargs) 1820 1821 def _call_for_each_replica(self, fn, args, kwargs):
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/distribute/distribute_lib.py in _call_for_each_replica(self, fn, args, kwargs) 2162 self._container_strategy(), 2163 replica_id_in_sync_group=constant_op.constant(0, dtypes.int32)):
-> 2164 return fn(*args, **kwargs) 2165 2166 def _reduce_to(self, reduce_op, value, destinations):
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/autograph/impl/api.py in wrapper(*args, **kwargs)
290 def wrapper(*args, **kwargs):
291 with ag_ctx.ControlStatusCtx(status=ag_ctx.Status.DISABLED):
--> 292 return func(*args, **kwargs)
293
294 if inspect.isfunction(func) or inspect.ismethod(func):
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2_utils.py in train_on_batch(model, x, y, sample_weight, class_weight, reset_metrics, standalone)
414 x, y, sample_weights = model._standardize_user_data(
415 x, y, sample_weight=sample_weight, class_weight=class_weight,
--> 416 extract_tensors_from_dataset=True)
417 batch_size = array_ops.shape(nest.flatten(x, expand_composites=True)[0])[0]
418 # If `model._distribution_strategy` is True, then we are in a replica context
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, batch_size, check_steps, steps_name, steps, validation_split, shuffle, extract_tensors_from_dataset) 2381 is_dataset=is_dataset, 2382 class_weight=class_weight,
-> 2383 batch_size=batch_size) 2384 2385 def _standardize_tensors(self, x, y, sample_weight, run_eagerly, dict_inputs,
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py in _standardize_tensors(self, x, y, sample_weight, run_eagerly, dict_inputs, is_dataset, class_weight, batch_size) 2467 shapes=None, 2468 check_batch_axis=False, # Don't enforce the batch size.
-> 2469 exception_prefix='target') 2470 2471 # Generate sample-wise weight values given the `sample_weight` and
~/miniconda3/envs/keras/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
510 'for each key in: ' + str(names))
511 elif isinstance(data, (list, tuple)):
--> 512 if isinstance(data[0], (list, tuple)):
513 data = [np.asarray(d) for d in data]
514 elif len(names) == 1 and isinstance(data[0], (float, int)):
IndexError: tuple index out of range
Минимальный код для воспроизведения этого:
from tensorflow.keras.layers import Dense, Embedding, Flatten, Lambda, Subtract, Input, Concatenate, Average, Reshape, GlobalAveragePooling1D, Dot, Dropout
from tensorflow.keras.models import Model, Sequential
from tensorflow.keras.utils import Sequence
from tensorflow.keras import initializers
import tensorflow_datasets as tfds
tfds.list_builders()
dataset, info = tfds.load("mnist", with_info=True)
inputs = Input((28, 28, 1), name="image")
First = Dense(128, activation="relu")
Second = Dropout(0.2)
Third = Dense(10, activation="softmax", name="label")
first = First(inputs)
second = Second(first)
third = Third(second)
model = Model(inputs=[inputs], outputs=[third])
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
model.fit(dataset['train'].batch(4096))
Могу поспорить, что что-то упустил в документах, но Я не могу понять это и пытаюсь разобраться с этим несколько часов. Модель хорошо тренируется от генератора, но по мере увеличения наборов данных я хочу переключиться.