python - IndexError：在 Tensorflow 训练期间列出超出范围的索引
问题描述
我有一个简单的模型训练如下：
simple_lstm_model = tf.keras.models.Sequential([
tf.keras.layers.LSTM(8, input_shape=x_train.shape[-2:]),
tf.keras.layers.Dense(1)
])
simple_lstm_model.compile(optimizer='adam', loss='mae')
simple_lstm_model.summary()
epochs = 10
history = simple_lstm_model.fit(
(x_train, y_train),
epochs=epochs,
validation_data=(x_test, y_test),
validation_steps=50
)
这是我得到的错误：
Train on 494797 samples, validate on 164933 samples
Epoch 1/10
32/494797 [..............................] - ETA: 1:22:12
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
<ipython-input-24-36add9c522be> in <module>
16 epochs=epochs,
17 validation_data=(X_test, y_test),
---> 18 validation_steps=50
19 )
~/opt/anaconda3/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,
~/opt/anaconda3/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
~/opt/anaconda3/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?
~/opt/anaconda3/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
~/opt/anaconda3/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():
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in _call(self, *args, **kwds)
604 # In this case we have not created variables on the first call. So we can
605 # run the first trace but we should fail if variables are created.
--> 606 results = self._stateful_fn(*args, **kwds)
607 if self._created_variables:
608 raise ValueError("Creating variables on a non-first call to a function"
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in __call__(self, *args, **kwargs)
2360 """Calls a graph function specialized to the inputs."""
2361 with self._lock:
-> 2362 graph_function, args, kwargs = self._maybe_define_function(args, kwargs)
2363 return graph_function._filtered_call(args, kwargs) # pylint: disable=protected-access
2364
~/opt/anaconda3/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
~/opt/anaconda3/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
~/opt/anaconda3/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,
~/opt/anaconda3/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
~/opt/anaconda3/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(
~/opt/anaconda3/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):
~/opt/anaconda3/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):
~/opt/anaconda3/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):
~/opt/anaconda3/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):
~/opt/anaconda3/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)
431 y,
432 sample_weights=sample_weights,
--> 433 output_loss_metrics=model._output_loss_metrics)
434
435 if reset_metrics:
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_eager.py in train_on_batch(model, inputs, targets, sample_weights, output_loss_metrics)
310 sample_weights=sample_weights,
311 training=True,
--> 312 output_loss_metrics=output_loss_metrics))
313 if not isinstance(outs, list):
314 outs = [outs]
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_eager.py in _process_single_batch(model, inputs, targets, output_loss_metrics, sample_weights, training)
251 output_loss_metrics=output_loss_metrics,
252 sample_weights=sample_weights,
--> 253 training=training))
254 if total_loss is None:
255 raise ValueError('The model cannot be run '
~/opt/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_eager.py in _model_loss(model, inputs, targets, output_loss_metrics, sample_weights, training)
165
166 if hasattr(loss_fn, 'reduction'):
--> 167 per_sample_losses = loss_fn.call(targets[i], outs[i])
168 weighted_losses = losses_utils.compute_weighted_loss(
169 per_sample_losses,
IndexError: list index out of range
我所有的数据集似乎都是正确的，所以在这一点上，我不知道我的问题出在哪里。
以下是我的数据集中的一些样本（全长为 494797 个样本）：
# x_train variable (each sample has 10 float numbers)
[[[ 831.259198 832.184729 832.85326538 833.14926758 833.21054993
833.55166626 835.30004883 835.31390381 833.2000885 829.34616394]]
[[ 826.76694946 826.03945923 827.20136719 827.67208862 826.49060669
848.25384216 884.94091492 873.46332703 855.76559143 843.89425354]]
[[ 839.61763 831.93538818 826.70728149 829.41572266 830.15981445
829.41616211 829.06277466 828.33288574 829.6803772 829.8375061 ]]]
# y_train variable (only "0" or "1" values)
[[1]
[1]
[0]]
解决方案
您致电的格式Sequential.fit不正确；前两个参数应该是xand y，而不是 tuple (x, y)，即：
history = simple_lstm_model.fit(
x_train, y_train,
epochs=epochs,
validation_data=(x_test, y_test),
validation_steps=50
)