Версия Tensorflow: 2.0.0
gpu: nvidia 2080ti
cuda: 10.1
cudnn: 7.6.5
Я использую keras как tenorflow.keras
Я использую модель Conv-LSTM
inputs = Input(shape=(480,3))
conv1 = Conv1D(16, 8, strides =1 , padding='same', activation='relu')(inputs)
conv2 = Conv1D(32, 8, strides =1 , padding='same', activation='relu')(conv1)
conv3 = Conv1D(64, 8, strides =1 , padding='same', activation='relu')(conv2)
lstm1 = LSTM(32)(conv3)
output = Dense(1,activation='sigmoid')(lstm1)
model = Model(inputs=inputs,outputs= output)
скомпилировать и запустить:
model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['binary_accuracy'])
#checkpoint = ModelCheckpoint('weight_seden.h5', monitor='binary_accuracy',save_best_only=True,mode='max')
earlystop = EarlyStopping(monitor = 'val_binary_accuracy',patience =4,mode = 'max')
history = model.fit(X_train, Y_train,batch_size=15,validation_data=(X_val,Y_val),class_weight=train_weights,epochs=50,callbacks=[earlystop])
вывод:
Train on 58271 samples, validate on 10284 samples
Epoch 1/50
1/58271 [..............................] - ETA: 37:12:15WARNING:tensorflow:Early stopping conditioned on metric `val_binary_accuracy` which is not available. Available metrics are:
Ошибка:
---------------------------------------------------------------------------
UnknownError Traceback (most recent call last)
<ipython-input-15-269f98dc1caf> in <module>
3 earlystop = EarlyStopping(monitor = 'val_binary_accuracy',patience =4,mode = 'max')
4 #history = model.fit(X_train, Y_train,batch_size=15,validation_data=(X_val,Y_val),class_weight=train_weights,epochs=50,callbacks=[earlystop])
----> 5 history = model.fit(X_train, Y_train,batch_size=1,validation_split=0.15,class_weight=train_weights,epochs=50,callbacks=[earlystop])
~/anaconda3/envs/tf/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)
726 max_queue_size=max_queue_size,
727 workers=workers,
--> 728 use_multiprocessing=use_multiprocessing)
729
730 def evaluate(self,
~/anaconda3/envs/tf/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, **kwargs)
322 mode=ModeKeys.TRAIN,
323 training_context=training_context,
--> 324 total_epochs=epochs)
325 cbks.make_logs(model, epoch_logs, training_result, ModeKeys.TRAIN)
326
~/anaconda3/envs/tf/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)
121 step=step, mode=mode, size=current_batch_size) as batch_logs:
122 try:
--> 123 batch_outs = execution_function(iterator)
124 except (StopIteration, errors.OutOfRangeError):
125 # TODO(kaftan): File bug about tf function and errors.OutOfRangeError?
~/anaconda3/envs/tf/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2_utils.py in execution_function(input_fn)
84 # `numpy` translates Tensors to values in Eager mode.
85 return nest.map_structure(_non_none_constant_value,
---> 86 distributed_function(input_fn))
87
88 return execution_function
~/anaconda3/envs/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in __call__(self, *args, **kwds)
455
456 tracing_count = self._get_tracing_count()
--> 457 result = self._call(*args, **kwds)
458 if tracing_count == self._get_tracing_count():
459 self._call_counter.called_without_tracing()
~/anaconda3/envs/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in _call(self, *args, **kwds)
518 # Lifting succeeded, so variables are initialized and we can run the
519 # stateless function.
--> 520 return self._stateless_fn(*args, **kwds)
521 else:
522 canon_args, canon_kwds = \
~/anaconda3/envs/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in __call__(self, *args, **kwargs)
1821 """Calls a graph function specialized to the inputs."""
1822 graph_function, args, kwargs = self._maybe_define_function(args, kwargs)
-> 1823 return graph_function._filtered_call(args, kwargs) # pylint: disable=protected-access
1824
1825 @property
~/anaconda3/envs/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _filtered_call(self, args, kwargs)
1139 if isinstance(t, (ops.Tensor,
1140 resource_variable_ops.BaseResourceVariable))),
-> 1141 self.captured_inputs)
1142
1143 def _call_flat(self, args, captured_inputs, cancellation_manager=None):
~/anaconda3/envs/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
1222 if executing_eagerly:
1223 flat_outputs = forward_function.call(
-> 1224 ctx, args, cancellation_manager=cancellation_manager)
1225 else:
1226 gradient_name = self._delayed_rewrite_functions.register()
~/anaconda3/envs/tf/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in call(self, ctx, args, cancellation_manager)
509 inputs=args,
510 attrs=("executor_type", executor_type, "config_proto", config),
--> 511 ctx=ctx)
512 else:
513 outputs = execute.execute_with_cancellation(
~/anaconda3/envs/tf/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/envs/tf/lib/python3.7/site-packages/six.py in raise_from(value, from_value)
UnknownError: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.
[[node model/conv1d/conv1d (defined at /home/subhashnerella/anaconda3/envs/tf/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py:1751) ]] [Op:__inference_distributed_function_3609]
Function call stack:
distributed_function
Я нашел похожий вопрос , как эта проблема, с которой я сталкиваюсь. Решение состоит в том, что проверочный набор не равен нулю. Я убедился, что мой набор проверки не равен нулю. Это также можно увидеть в эпоху выше. Этот точный код работал несколько дней назад. Я ничего не изменил, но я сталкиваюсь с этой проблемой. Я пытался уменьшить размер партии, что не помогло. Как я могу это исправить?