Я пытаюсь использовать предварительно обученную модель tf-hub elmo, интегрировав ее в слой keras .
Слой Кераса:
class ElmoEmbeddingLayer(tf.keras.layers.Layer):
def __init__(self, **kwargs):
super(ElmoEmbeddingLayer, self).__init__(**kwargs)
self.dimensions = 1024
self.trainable = True
self.elmo = None
def build(self, input_shape):
url = 'https://tfhub.dev/google/elmo/2'
self.elmo = hub.Module(url)
self._trainable_weights += trainable_variables(
scope="^{}_module/.*".format(self.name))
super(ElmoEmbeddingLayer, self).build(input_shape)
def call(self, x, mask=None):
result = self.elmo(
x,
signature="default",
as_dict=True)["elmo"]
return result
def compute_output_shape(self, input_shape):
return input_shape[0], self.dimensions
Когда я запускаю код, я получаю следующую ошибку:
Traceback (most recent call last):
File "D:/Google Drive/Licenta/Gemini/Emotion Analysis/nn/trainer/model.py", line 170, in <module>
validation_steps=validation_dataset.size())
File "D:/Google Drive/Licenta/Gemini/Emotion Analysis/nn/trainer/model.py", line 79, in train_gpu
model = build_model(self.config, self.embeddings, self.sequence_len, self.out_classes, summary=True)
File "D:\Google Drive\Licenta\Gemini\Emotion Analysis\nn\architectures\models.py", line 8, in build_model
return my_model(embeddings, config, sequence_length, out_classes, summary)
File "D:\Google Drive\Licenta\Gemini\Emotion Analysis\nn\architectures\models.py", line 66, in my_model
inputs, embedding = resolve_inputs(embeddings, sequence_length, model_config, input_type)
File "D:\Google Drive\Licenta\Gemini\Emotion Analysis\nn\architectures\models.py", line 19, in resolve_inputs
return elmo_input(model_conf)
File "D:\Google Drive\Licenta\Gemini\Emotion Analysis\nn\architectures\models.py", line 58, in elmo_input
embedding = ElmoEmbeddingLayer()(input_text)
File "D:\Apps\Anaconda\envs\tf2.0\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 616, in __call__
self._maybe_build(inputs)
File "D:\Apps\Anaconda\envs\tf2.0\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 1966, in _maybe_build
self.build(input_shapes)
File "D:\Google Drive\Licenta\Gemini\Emotion Analysis\nn\architectures\custom_layers.py", line 21, in build
self.elmo = hub.Module(url)
File "D:\Apps\Anaconda\envs\tf2.0\lib\site-packages\tensorflow_hub\module.py", line 156, in __init__
abs_state_scope = _try_get_state_scope(name, mark_name_scope_used=False)
File "D:\Apps\Anaconda\envs\tf2.0\lib\site-packages\tensorflow_hub\module.py", line 389, in _try_get_state_scope
"name_scope was already taken." % abs_state_scope)
RuntimeError: variable_scope module/ was unused but the corresponding name_scope was already taken.
Похоже, это связано с нетерпеливым исполнением. Если я отключу активное выполнение, мне придется окружить функцию model.fit сеансом tenorflow и инициализировать переменные с помощью sess.run(global_variables_initializer())
, чтобы избежать следующей ошибки:
Traceback (most recent call last):
File "D:/Google Drive/Licenta/Gemini/Emotion Analysis/nn/trainer/model.py", line 168, in <module>
validation_steps=validation_dataset.size().eval(session=Session()))
File "D:/Google Drive/Licenta/Gemini/Emotion Analysis/nn/trainer/model.py", line 90, in train_gpu
class_weight=weighted)
File "D:\Apps\Anaconda\envs\tf2.0\lib\site-packages\tensorflow\python\keras\engine\training.py", line 643, in fit
use_multiprocessing=use_multiprocessing)
File "D:\Apps\Anaconda\envs\tf2.0\lib\site-packages\tensorflow\python\keras\engine\training_arrays.py", line 664, in fit
steps_name='steps_per_epoch')
File "D:\Apps\Anaconda\envs\tf2.0\lib\site-packages\tensorflow\python\keras\engine\training_arrays.py", line 294, in model_iteration
batch_outs = f(actual_inputs)
File "D:\Apps\Anaconda\envs\tf2.0\lib\site-packages\tensorflow\python\keras\backend.py", line 3353, in __call__
run_metadata=self.run_metadata)
File "D:\Apps\Anaconda\envs\tf2.0\lib\site-packages\tensorflow\python\client\session.py", line 1458, in __call__
run_metadata_ptr)
tensorflow.python.framework.errors_impl.FailedPreconditionError: 2 root error(s) found.
(0) Failed precondition: Error while reading resource variable module/bilm/RNN_0/RNN/MultiRNNCell/Cell1/rnn/lstm_cell/bias from Container: localhost. This could mean that the variable was uninitialized. Not found: Resource localhost/module/bilm/RNN_0/RNN/MultiRNNCell/Cell1/rnn/lstm_cell/bias/class tensorflow::Var does not exist.
[[{{node elmo_embedding_layer/module_apply_default/bilm/RNN_0/RNN/MultiRNNCell/Cell1/rnn/lstm_cell/bias/Read/ReadVariableOp}}]]
(1) Failed precondition: Error while reading resource variable module/bilm/RNN_0/RNN/MultiRNNCell/Cell1/rnn/lstm_cell/bias from Container: localhost. This could mean that the variable was uninitialized. Not found: Resource localhost/module/bilm/RNN_0/RNN/MultiRNNCell/Cell1/rnn/lstm_cell/bias/class tensorflow::Var does not exist.
[[{{node elmo_embedding_layer/module_apply_default/bilm/RNN_0/RNN/MultiRNNCell/Cell1/rnn/lstm_cell/bias/Read/ReadVariableOp}}]]
[[metrics/f1_micro/Identity/_223]]
0 successful operations.
0 derived errors ignored.
Мое решение:
with Session() as sess:
sess.run(global_variables_initializer())
history = model.fit(self.train_data.repeat(),
epochs=self.config['epochs'],
validation_data=self.validation_data.repeat(),
steps_per_epoch=steps_per_epoch,
validation_steps=validation_steps,
callbacks=self.__callbacks(monitor_metric),
class_weight=weighted)
Главный вопрос - есть ли другой способ использовать модуль elmo tf-hub в пользовательском слое keras и обучить мою модель. Другой вопрос, не влияет ли мое текущее решение на производительность обучения или выдает ошибку OOM GPU (я получаю ошибку OOM через несколько эпох с более высоким размером пакета, что, как я обнаружил, связано с незакрытыми сеансами или утечками памяти. ).