我试图复制here中的代码并将bert model应用于另一个dataset，但是在创建自己的测试并进行训练后，我偶然发现了这个问题。
这是我的完整文件
import tensorflow as tf
import pandas as pd
import tensorflow_hub as hub
import os
import json
import re
import numpy as np
from bert.tokenization import FullTokenizer
from tqdm import tqdm
#from keras.backend.tensorflow_backend import set_session
import keras.backend as K
#To make tf 2.0 compatible with tf1.0 code, we disable the tf2.0 functionalities
tf.compat.v1.disable_eager_execution()
# Initialize session
sess = tf.compat.v1.Session()
# Params for bert model and tokenization
bert_path = "https://tfhub.dev/google/bert_uncased_L-12_H-768_A-12/1"
max_seq_length = 1024
#Load all files from a directory in a DataFrame.
def load_dataset(directory):
data = {}
data["text"] = []
data["label"] = []
with open(directory) as json_file:
temp = json.load(json_file)
for p in temp['Outputs']:
data["text"].append(p["text"])
data["label"].append(p["class"])
return pd.DataFrame.from_dict(data)
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_output = (bert_output)(bert_inputs)
dense = tf.keras.layers.Dense(256, activation="relu")(bert_output)
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.compat.v1.local_variables_initializer())
sess.run(tf.compat.v1.global_variables_initializer())
sess.run(tf.compat.v1.tables_initializer())
K.tensorflow_backend.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 = 1024
train_df = load_dataset('ShuffledDatasetTrain.jsonl')
test_df = load_dataset('ShuffledDatasetTest.jsonl')
# Create datasets (Only take up to max_seq_length words for memory)
train_text = train_df["text"].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["label"].tolist()
test_text = test_df["text"].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["label"].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)
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=8,
)
if __name__ == "__main__":
main()
这是错误
Using TensorFlow backend.
Converting examples to features: 100%|██████████| 13000/13000 [03:32<00:00, 61.29it/s]
Converting examples to features: 100%|██████████| 2000/2000 [00:32<00:00, 61.83it/s]
WARNING:tensorflow:From C:\Users\Nitish_2\Miniconda3\lib\site-packages\tensorflow_core\python\ops\resource_variable_ops.py:1630: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.
Instructions for updating:
If using Keras pass *_constraint arguments to layers.
WARNING:tensorflow:From C:\Users\Nitish_2\Miniconda3\lib\site-packages\tensorflow_core\python\ops\resource_variable_ops.py:1630: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.
Instructions for updating:
If using Keras pass *_constraint arguments to layers.
Model: "model"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_ids (InputLayer) [(None, 1024)] 0
__________________________________________________________________________________________________
input_masks (InputLayer) [(None, 1024)] 0
__________________________________________________________________________________________________
segment_ids (InputLayer) [(None, 1024)] 0
__________________________________________________________________________________________________
bert_layer (BertLayer) (None, 768) 110104890 input_ids[0][0]
input_masks[0][0]
segment_ids[0][0]
__________________________________________________________________________________________________
dense (Dense) (None, 256) 196864 bert_layer[0][0]
__________________________________________________________________________________________________
dense_1 (Dense) (None, 1) 257 dense[0][0]
==================================================================================================
Total params: 110,302,011
Trainable params: 21,460,737
Non-trainable params: 88,841,274
__________________________________________________________________________________________________
Train on 13000 samples, validate on 2000 samples
2019-12-30 00:45:54.780164: W tensorflow/core/framework/op_kernel.cc:1622] OP_REQUIRES failed at resource_variable_ops.cc:660 : Not found: Resource localhost/bert_layer_module/bert/embeddings/word_embeddings/class tensorflow::Var does not exist.
Traceback (most recent call last):
File "C:/Users/Nitish_2/PycharmProjects/GPT-detection/Model.py", line 323, in <module>
main()
File "C:/Users/Nitish_2/PycharmProjects/GPT-detection/Model.py", line 319, in main
batch_size=8,
File "C:\Users\Nitish_2\Miniconda3\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 728, in fit
use_multiprocessing=use_multiprocessing)
File "C:\Users\Nitish_2\Miniconda3\lib\site-packages\tensorflow_core\python\keras\engine\training_arrays.py", line 674, in fit
steps_name='steps_per_epoch')
File "C:\Users\Nitish_2\Miniconda3\lib\site-packages\tensorflow_core\python\keras\engine\training_arrays.py", line 393, in model_iteration
batch_outs = f(ins_batch)
File "C:\Users\Nitish_2\Miniconda3\lib\site-packages\tensorflow_core\python\keras\backend.py", line 3580, in __call__
run_metadata=self.run_metadata)
File "C:\Users\Nitish_2\Miniconda3\lib\site-packages\tensorflow_core\python\client\session.py", line 1472, in __call__
run_metadata_ptr)
tensorflow.python.framework.errors_impl.FailedPreconditionError: Error while reading resource variable bert_layer_module/bert/encoder/layer_10/attention/self/query/kernel from Container: localhost. This could mean that the variable was uninitialized. Not found: Resource localhost/bert_layer_module/bert/encoder/layer_10/attention/self/query/kernel/class tensorflow::Var does not exist.
[[{{node bert_layer/bert_layer_module_apply_tokens/bert/encoder/layer_10/attention/self/query/MatMul/ReadVariableOp}}]]
对于为什么会发生这种情况的任何见解都会受到赞赏，如果我没有提供适当的信息，请告诉我，这是我第一次在这里提出问题。