python-3.x - Tensorflow.keras : AlreadyExistsError

Question

我正在使用 tensorflow 构建模型。我训练了我的模型，它正常工作。然后，我修改了我的代码，当我尝试训练我的模型时，我收到了 AlreadyExistError。我重新启动了 Jupyter Notebook，但仍然遇到相同的错误。我需要一些帮助。
这是我构建网络并训练它的一段代码。问题出现在最后一行。

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv1D, Dropout, Dense, Flatten, LSTM, MaxPooling1D, Bidirectional
from tensorflow.keras.optimizers import Adam
from keras.callbacks import EarlyStopping, TensorBoard

model = Sequential()

model.add(Conv1D(32, kernel_size=3, activation='elu', padding='same',
                 input_shape=(vector_size, 1)))
model.add(Conv1D(32, kernel_size=3, activation='elu', padding='same'))
model.add(Conv1D(32, kernel_size=3, activation='relu', padding='same'))
model.add(MaxPooling1D(pool_size=3))

model.add(Bidirectional(LSTM(512, dropout=0.2, recurrent_dropout=0.3)))

model.add(Dense(512, activation='sigmoid'))
model.add(Dropout(0.2))
model.add(Dense(512, activation='sigmoid'))
model.add(Dropout(0.25))
model.add(Dense(512, activation='sigmoid'))
model.add(Dropout(0.25))

model.add(Dense(2, activation='softmax'))

model.compile(loss='categorical_crossentropy', optimizer=Adam(lr=0.0001, decay=1e-6), metrics=['accuracy'])

tensorboard = TensorBoard(log_dir='logs/', histogram_freq=0, write_graph=True, write_images=True)

model.summary()
model.fit(np.array(x_train), np.array(y_train), batch_size=batch_size, epochs=no_epochs,
         validation_data=(np.array(x_test), np.array(y_test)),  callbacks=[tensorboard, EarlyStopping(min_delta=0.0001, patience=3)])

Train on 90000 samples, validate on 10000 samples Epoch 1/10
500/90000 [..............................] - ETA: 2:00:49 /anaconda3/lib/python3.7/site-packages/keras/callbacks/callbacks.py:846: RuntimeWarning: Early stopping conditioned on metric val_loss which is not available. Available metrics are: (self.monitor, ','.join(list(logs.keys()))), RuntimeWarning --------------------------------------------------------------------------- AlreadyExistsError Traceback (most recent call last) in 1 model.fit(np.array(x_train), np.array(y_train), batch_size=batch_size, epochs=no_epochs, ----> 2 validation_data=(np.array(x_test), np.array(y_test)), callbacks=[tensorboard, EarlyStopping(min_delta=0.0001, patience=3)]) 3 print('You can continue')

/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,

/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

/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?

/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

/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():

/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in _call(self, *args, **kwds) 630 # Lifting succeeded, so variables are initialized and we can run the 631 # stateless function. --> 632 return self._stateless_fn(*args, **kwds) 633 else: 634 canon_args, canon_kwds = \

/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in call(self, *args, **kwargs) 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 2365 @property

/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _filtered_call(self, args, kwargs) 1609 if isinstance(t, (ops.Tensor, 1610
resource_variable_ops.BaseResourceVariable))), -> 1611 self.captured_inputs) 1612 1613 def _call_flat(self, args, captured_inputs, cancellation_manager=None):

/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
1690 # No tape is watching; skip to running the function.
1691 return self._build_call_outputs(self._inference_function.call( -> 1692 ctx, args, cancellation_manager=cancellation_manager)) 1693
forward_backward = self._select_forward_and_backward_functions(
1694 args,

/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in call(self, ctx, args, cancellation_manager) 543 inputs=args, 544 attrs=("executor_type", executor_type, "config_proto", config), --> 545 ctx=ctx) 546 else: 547 outputs = execute.execute_with_cancellation(

/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name) 65 else: 66 message = e.message ---> 67 six.raise_from(core._status_to_exception(e.code, message), None) 68 except TypeError as e: 69 keras_symbolic_tensors = [

/anaconda3/lib/python3.7/site-packages/six.py in raise_from(value, from_value)

AlreadyExistsError: Resource __per_step_0/sequential/bidirectional/forward_lstm/while_grad/body/_429/gradients/AddN_13/tmp_var/N10tensorflow19TemporaryVariableOp6TmpVarE [[{{node sequential/bidirectional/forward_lstm/while_grad/body/_429/gradients/AddN_13/tmp_var}}]] [Op:__inference_distributed_function_12060]

Function call stack: distributed_function

Answer 1

您在训练时看到的先前运行的相同架构上一定有问题。

这应该重置 keras session :

from tensorflow.keras import backend
backend.clear_session()