我正在尝试在文本分类模型中使用BERT。我在这里使用代码： https://github.com/strongio/keras-bert/blob/master/keras-bert.py
这是我正在使用的代码：
# Initialize session
sess = tf.Session()
# # Load all files from a directory in a DataFrame.
# def load_directory_data(directory):
# data = {}
# data["sentence"] = []
# data["sentiment"] = []
# for file_path in os.listdir(directory):
# with tf.gfile.GFile(os.path.join(directory, file_path), "r") as f:
# data["sentence"].append(f.read())
# data["sentiment"].append(re.match("\d+_(\d+)\.txt", file_path).group(1))
# return pd.DataFrame.from_dict(data)
# # Merge positive and negative examples, add a polarity column and shuffle.
# def load_dataset(directory):
# pos_df = load_directory_data(os.path.join(directory, "pos"))
# neg_df = load_directory_data(os.path.join(directory, "neg"))
# pos_df["polarity"] = 1
# neg_df["polarity"] = 0
# return pd.concat([pos_df, neg_df]).sample(frac=1).reset_index(drop=True)
# # Download and process the dataset files.
# def download_and_load_datasets(force_download=False):
# dataset = tf.keras.utils.get_file(
# fname="aclImdb.tar.gz",
# origin="http://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz",
# extract=True,
# )
# train_df = load_dataset(os.path.join(os.path.dirname(dataset), "aclImdb", "train"))
# test_df = load_dataset(os.path.join(os.path.dirname(dataset), "aclImdb", "test"))
# return train_df, test_df
class PaddingInputExample(object):
"""Fake example so the num input examples is a multiple of the batch size.
When running eval/predict on the TPU, we need to pad the number of examples
to be a multiple of the batch size, because the TPU requires a fixed batch
size. The alternative is to drop the last batch, which is bad because it means
the entire output data won't be generated.
We use this class instead of `None` because treating `None` as padding
battches could cause silent errors.
"""
class InputExample(object):
"""A single training/test example for simple sequence classification."""
def __init__(self, guid, text_a, text_b=None, label=None):
"""Constructs a InputExample.
Args:
guid: Unique id for the example.
text_a: string. The untokenized text of the first sequence. For single
sequence tasks, only this sequence must be specified.
text_b: (Optional) string. The untokenized text of the second sequence.
Only must be specified for sequence pair tasks.
label: (Optional) string. The label of the example. This should be
specified for train and dev examples, but not for test examples.
"""
self.guid = guid
self.text_a = text_a
self.text_b = text_b
self.label = label
def create_tokenizer_from_hub_module(bert_path):
"""Get the vocab file and casing info from the Hub module."""
bert_module = hub.Module(bert_path)
tokenization_info = bert_module(signature="tokenization_info", as_dict=True)
vocab_file, do_lower_case = sess.run(
[tokenization_info["vocab_file"], tokenization_info["do_lower_case"]]
)
return FullTokenizer(vocab_file=vocab_file, do_lower_case=do_lower_case)
def convert_single_example(tokenizer, example, max_seq_length=256):
"""Converts a single `InputExample` into a single `InputFeatures`."""
if isinstance(example, PaddingInputExample):
input_ids = [0] * max_seq_length
input_mask = [0] * max_seq_length
segment_ids = [0] * max_seq_length
label = 0
return input_ids, input_mask, segment_ids, label
tokens_a = tokenizer.tokenize(example.text_a)
if len(tokens_a) > max_seq_length - 2:
tokens_a = tokens_a[0 : (max_seq_length - 2)]
tokens = []
segment_ids = []
tokens.append("[CLS]")
segment_ids.append(0)
for token in tokens_a:
tokens.append(token)
segment_ids.append(0)
tokens.append("[SEP]")
segment_ids.append(0)
input_ids = tokenizer.convert_tokens_to_ids(tokens)
# The mask has 1 for real tokens and 0 for padding tokens. Only real
# tokens are attended to.
input_mask = [1] * len(input_ids)
# Zero-pad up to the sequence length.
while len(input_ids) < max_seq_length:
input_ids.append(0)
input_mask.append(0)
segment_ids.append(0)
assert len(input_ids) == max_seq_length
assert len(input_mask) == max_seq_length
assert len(segment_ids) == max_seq_length
return input_ids, input_mask, segment_ids, example.label
def convert_examples_to_features(tokenizer, examples, max_seq_length=256):
"""Convert a set of `InputExample`s to a list of `InputFeatures`."""
input_ids, input_masks, segment_ids, labels = [], [], [], []
for example in tqdm(examples, desc="Converting examples to features"):
input_id, input_mask, segment_id, label = convert_single_example(
tokenizer, example, max_seq_length
)
input_ids.append(input_id)
input_masks.append(input_mask)
segment_ids.append(segment_id)
labels.append(label)
return (
np.array(input_ids),
np.array(input_masks),
np.array(segment_ids),
np.array(labels).reshape(-1, 1),
)
def convert_text_to_examples(texts, labels):
"""Create InputExamples"""
InputExamples = []
for text, label in zip(texts, labels):
InputExamples.append(
InputExample(guid=None, text_a=" ".join(text), text_b=None, label=label)
)
return InputExamples
class BertLayer(tf.keras.layers.Layer):
def __init__(
self,
n_fine_tune_layers=10,
pooling="mean",
bert_path="https://tfhub.dev/google/bert_uncased_L-12_H-768_A-12/1",
**kwargs,
):
self.n_fine_tune_layers = n_fine_tune_layers
self.trainable = True
self.output_size = 768
self.pooling = pooling
self.bert_path = bert_path
if self.pooling not in ["first", "mean"]:
raise NameError(
f"Undefined pooling type (must be either first or mean, but is {self.pooling}"
)
super(BertLayer, self).__init__(**kwargs)
def build(self, input_shape):
self.bert = hub.Module(
self.bert_path, trainable=self.trainable, name=f"{self.name}_module"
)
# Remove unused layers
trainable_vars = self.bert.variables
if self.pooling == "first":
trainable_vars = [var for var in trainable_vars if not "/cls/" in var.name]
trainable_layers = ["pooler/dense"]
elif self.pooling == "mean":
trainable_vars = [
var
for var in trainable_vars
if not "/cls/" in var.name and not "/pooler/" in var.name
]
trainable_layers = []
else:
raise NameError(
f"Undefined pooling type (must be either first or mean, but is {self.pooling}"
)
# Select how many layers to fine tune
for i in range(self.n_fine_tune_layers):
trainable_layers.append(f"encoder/layer_{str(11 - i)}")
# Update trainable vars to contain only the specified layers
trainable_vars = [
var
for var in trainable_vars
if any([l in var.name for l in trainable_layers])
]
# Add to trainable weights
for var in trainable_vars:
self._trainable_weights.append(var)
for var in self.bert.variables:
if var not in self._trainable_weights:
self._non_trainable_weights.append(var)
super(BertLayer, self).build(input_shape)
def call(self, inputs):
inputs = [K.cast(x, dtype="int32") for x in inputs]
input_ids, input_mask, segment_ids = inputs
bert_inputs = dict(
input_ids=input_ids, input_mask=input_mask, segment_ids=segment_ids
)
if self.pooling == "first":
pooled = self.bert(inputs=bert_inputs, signature="tokens", as_dict=True)[
"pooled_output"
]
elif self.pooling == "mean":
result = self.bert(inputs=bert_inputs, signature="tokens", as_dict=True)[
"sequence_output"
]
mul_mask = lambda x, m: x * tf.expand_dims(m, axis=-1)
masked_reduce_mean = lambda x, m: tf.reduce_sum(mul_mask(x, m), axis=1) / (
tf.reduce_sum(m, axis=1, keepdims=True) + 1e-10)
input_mask = tf.cast(input_mask, tf.float32)
pooled = masked_reduce_mean(result, input_mask)
else:
raise NameError(f"Undefined pooling type (must be either first or mean, but is {self.pooling}")
return pooled
def compute_output_shape(self, input_shape):
return (input_shape[0], self.output_size)
# Build model
def build_model(max_seq_length):
in_id = tf.keras.layers.Input(shape=(max_seq_length,), name="input_ids")
in_mask = tf.keras.layers.Input(shape=(max_seq_length,), name="input_masks")
in_segment = tf.keras.layers.Input(shape=(max_seq_length,), name="segment_ids")
bert_inputs = [in_id, in_mask, in_segment]
bert_output = BertLayer(n_fine_tune_layers=3)(bert_inputs)
dense = tf.keras.layers.Dense(256, activation="relu")(bert_output)
pred = tf.keras.layers.Dense(1, activation="sigmoid")(dense)
# embedding_size = 768
# bert_output = BertLayer(n_fine_tune_layers=3)(bert_inputs)
# # Reshape bert_output before passing it the GRU
# bert_output_ = tf.keras.layers.Reshape((max_seq_length, embedding_size))(bert_output)
# gru_out = tf.keras.layers.GRU(100, activation='sigmoid')(bert_output_)
# dense = tf.keras.layers.Dense(256, activation="relu")(gru_out)
# pred = tf.keras.layers.Dense(1, activation="sigmoid")(dense)
model = tf.keras.models.Model(inputs=bert_inputs, outputs=pred)
model.compile(loss="binary_crossentropy", optimizer="adam", metrics=["accuracy"])
model.summary()
return model
def initialize_vars(sess):
sess.run(tf.local_variables_initializer())
sess.run(tf.global_variables_initializer())
sess.run(tf.tables_initializer())
K.set_session(sess)
def main():
# Params for bert model and tokenization
bert_path = "https://tfhub.dev/google/bert_uncased_L-12_H-768_A-12/1"
max_seq_length = 256
train_df, test_df = master_df[:round(len(master_df)*.8)], master_df[round(len(master_df)*.8):]
# Create datasets (Only take up to max_seq_length words for memory)
train_text = train_df["words"].tolist()
train_text = [" ".join(t.split()[0:max_seq_length]) for t in train_text]
train_text = np.array(train_text, dtype=object)[:, np.newaxis]
train_label = train_df["new_grouping"].tolist()
test_text = test_df["words"].tolist()
test_text = [" ".join(t.split()[0:max_seq_length]) for t in test_text]
test_text = np.array(test_text, dtype=object)[:, np.newaxis]
test_label = test_df["new_grouping"].tolist()
# Instantiate tokenizer
tokenizer = create_tokenizer_from_hub_module(bert_path)
# Convert data to InputExample format
train_examples = convert_text_to_examples(train_text, train_label)
test_examples = convert_text_to_examples(test_text, test_label)
# Convert to features
(
train_input_ids,
train_input_masks,
train_segment_ids,
train_labels,
) = convert_examples_to_features(
tokenizer, train_examples, max_seq_length=max_seq_length
)
(
test_input_ids,
test_input_masks,
test_segment_ids,
test_labels,
) = convert_examples_to_features(
tokenizer, test_examples, max_seq_length=max_seq_length
)
model = build_model(max_seq_length)
# Instantiate variables
initialize_vars(sess)
checkpoint_path = "bert_dir/cp.ckpt"
checkpoint_dir = os.path.dirname('checkpoint_path')
# Create a callback that saves the model's weights
cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_path,
save_weights_only=True,
verbose=1)
history = model.fit(
[train_input_ids, train_input_masks, train_segment_ids],
train_labels,
validation_data=(
[test_input_ids, test_input_masks, test_segment_ids],
test_labels,
),
epochs=1,
batch_size=32,
callbacks=[cp_callback]
)
model.save('bert_1.h5')
return history
if __name__ == "__main__":
history = main()
我正在尝试保存模型/权重，以便以后可以再次加载并预测新数据。但是，我不断收到此错误：
---------------------------------------------------------------------------
NotImplementedError Traceback (most recent call last)
<ipython-input-7-94557d31eb21> in <module>()
353
354 if __name__ == "__main__":
--> 355 history = main()
7 frames
<ipython-input-7-94557d31eb21> in main()
347 )
348
--> 349 model.save('bert_1.h5')
350
351
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/network.py in save(self, filepath, overwrite, include_optimizer, save_format, signatures)
1169 """
1170 saving.save_model(self, filepath, overwrite, include_optimizer, save_format,
-> 1171 signatures)
1172
1173 def save_weights(self, filepath, overwrite=True, save_format=None):
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/saving/save.py in save_model(model, filepath, overwrite, include_optimizer, save_format, signatures)
107 'or using `save_weights`.')
108 hdf5_format.save_model_to_hdf5(
--> 109 model, filepath, overwrite, include_optimizer)
110 else:
111 saved_model_save.save(model, filepath, overwrite, include_optimizer,
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/saving/hdf5_format.py in save_model_to_hdf5(model, filepath, overwrite, include_optimizer)
91
92 try:
---> 93 model_metadata = saving_utils.model_metadata(model, include_optimizer)
94 for k, v in model_metadata.items():
95 if isinstance(v, (dict, list, tuple)):
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/saving/saving_utils.py in model_metadata(model, include_optimizer, require_config)
158 except NotImplementedError as e:
159 if require_config:
--> 160 raise e
161
162 metadata = dict(
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/saving/saving_utils.py in model_metadata(model, include_optimizer, require_config)
155 model_config = {'class_name': model.__class__.__name__}
156 try:
--> 157 model_config['config'] = model.get_config()
158 except NotImplementedError as e:
159 if require_config:
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/network.py in get_config(self)
884 for layer in self.layers: # From the earliest layers on.
885 layer_class_name = layer.__class__.__name__
--> 886 layer_config = layer.get_config()
887
888 filtered_inbound_nodes = []
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/keras/engine/base_layer.py in get_config(self)
578 # or that `get_config` has been overridden:
579 if len(extra_args) > 1 and hasattr(self.get_config, '_is_default'):
--> 580 raise NotImplementedError('Layers with arguments in `__init__` must '
581 'override `get_config`.')
582 # TODO(reedwm): Handle serializing self._dtype_policy.
NotImplementedError: Layers with arguments in `__init__` must override `get_config`.
NotImplementedError: Layers with arguments in `__init__` must override `get_config`
上面的帖子反映了我的问题，并且有一个可能的答案，但是我真的不明白建议的内容。我该怎么办？