我正在尝试微调 HuggingFace TFBertModel 以便能够将某些文本分类为单个标签。我已经启动并运行了模型,但是从一开始精度就极低。我的期望是准确度会很高,因为它使用 BERT 预训练的权重作为起点。我希望得到一些关于我哪里出错的建议。
我正在使用这里的 bbc-text 数据集:
加载数据
df = pd.read_csv(open(<s3 url>),encoding='utf-8', error_bad_lines=False)
df = df.sample(frac=1)
df = df.dropna(how='any')
价值计数
sport 511
business 510
politics 417
tech 401
entertainment 386
Name: label, dtype: int64
预处理
def preprocess_text(sen):
# Convert html entities to normal
sentence = unescape(sen)
# Remove html tags
sentence = remove_tags(sentence)
# Remove newline chars
sentence = remove_newlinechars(sentence)
# Remove punctuations and numbers
sentence = re.sub('[^a-zA-Z]', ' ', sentence)
# Convert to lowercase
sentence = sentence.lower()
return sentence
def remove_newlinechars(text):
return " ".join(text.splitlines())
def remove_tags(text):
TAG_RE = re.compile(r'<[^>]+>')
return TAG_RE.sub('', text)
df['text_prepd'] = df['text'].apply(preprocess_text)
拆分数据
train, val = train_test_split(df, test_size=0.30, shuffle=True, stratify=df['label'])
编码标签
from sklearn.preprocessing import LabelEncoder
label_encoder = LabelEncoder()
y_train = np.asarray(le.fit_transform(train['label']))
y_val = np.asarray(le.fit_transform(val['label']))
定义BERT输入函数
# Initialise Bert Tokenizer
bert_tokenizer_transformer = BertTokenizer.from_pretrained('bert-base-cased')
def create_input_array(df, tokenizer, args):
sentences = df.text_prepd.values
input_ids = []
attention_masks = []
token_type_ids = []
for sent in tqdm(sentences):
# `encode_plus` will:
# (1) Tokenize the sentence.
# (2) Prepend the `[CLS]` token to the start.
# (3) Append the `[SEP]` token to the end.
# (4) Map tokens to their IDs.
# (5) Pad or truncate the sentence to `max_length`
# (6) Create attention masks for [PAD] tokens.
encoded_dict = tokenizer.encode_plus(
sent, # Sentence to encode.
add_special_tokens=True, # Add '[CLS]' and '[SEP]'
max_length=args.max_seq_len, # Pad & truncate all sentences.
pad_to_max_length=True,
return_attention_mask=True, # Construct attn. masks.
return_tensors='tf', # Return tf tensors.
)
# Add the encoded sentence to the list.
input_ids.append(encoded_dict['input_ids'])
# And its attention mask (simply differentiates padding from non-padding).
attention_masks.append(encoded_dict['attention_mask'])
token_type_ids.append(encoded_dict['token_type_ids'])
input_ids = tf.convert_to_tensor(input_ids)
attention_masks = tf.convert_to_tensor(attention_masks)
token_type_ids = tf.convert_to_tensor(token_type_ids)
return input_ids, attention_masks, token_type_ids
将数据转换为 Bert 输入
train_inputs = [create_input_array(train[:], tokenizer=tokenizer, args=args)]
val_inputs = [create_input_array(val[:], tokenizer=tokenizer, args=args)]
train_inputs, y_train
然后我val_inputs, y_val
应用以下函数来重塑并转换为 numpy 数组。然后将此函数返回的列表作为参数传递给 keras fit 方法。我意识到转换为 tf.tensors 然后转换为 numpy 有点矫枉过正,但我认为这不会产生影响。我最初试图使用 tf.datasets 但切换到 numpy。
def convert_inputs_to_tf_dataset(inputs,y, args):
# args.max_seq_len = 256
ids = inputs[0][1]
masks = inputs[0][1]
token_types = inputs[0][2]
ids = tf.reshape(ids, (-1, args.max_seq_len))
print("Input ids shape: ", ids.shape)
masks = tf.reshape(masks, (-1, args.max_seq_len))
print("Input Masks shape: ", masks.shape)
token_types = tf.reshape(token_types, (-1, args.max_seq_len))
print("Token type ids shape: ", token_types.shape)
ids=ids.numpy()
masks = masks.numpy()
token_types = token_types.numpy()
return [ids, masks, token_types, y]
凯拉斯模型
# args.max_seq_len = 256
# n_classes = 6
model = TFBertForSequenceClassification.from_pretrained('bert-base-uncased', trainable=True, num_labels=n_classes)
input_ids_layer = Input(shape=(args.max_seq_len, ), dtype=np.int32)
input_mask_layer = Input(shape=(args.max_seq_len, ), dtype=np.int32)
input_token_type_layer = Input(shape=(args.max_seq_len,), dtype=np.int32)
bert_layer = model([input_ids_layer, input_mask_layer, input_token_type_layer])[0]
flat_layer = Flatten()(bert_layer)
dropout= Dropout(0.3)(flat_layer)
dense_output = Dense(n_classes, activation='softmax')(dropout)
model_ = Model(inputs=[input_ids_layer, input_mask_layer, input_token_type_layer], outputs=dense_output)
编译和拟合
loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
metric = tf.keras.metrics.SparseCategoricalAccuracy('accuracy')
model.compile(optimizer='adam', loss=loss, metrics=[metric])
model.fit(inputs=..., outputs=..., validation_data=..., epochs=50, batch_size = 32, metrics=metric, verbose=1)
Epoch 32/50
1401/1401 [==============================] - 42s 30ms/sample - loss: 1.6103 - accuracy: 0.2327 - val_loss: 1.6042 -
val_accuracy: 0.2308
因为我使用的是 BERT,所以只需要几个 epoch,所以我期望在 32 个 epoch 之后会有比 23% 高得多的东西。