transformers DataCollatorForTokenClassification类
transformers
huggingface/transformers: 是一个基于 Python 的自然语言处理库,它使用了 PostgreSQL 数据库存储数据。适合用于自然语言处理任务的开发和实现,特别是对于需要使用 Python 和 PostgreSQL 数据库的场景。特点是自然语言处理库、Python、PostgreSQL 数据库。
项目地址:https://gitcode.com/gh_mirrors/tra/transformers
免费下载资源
·
构造方法
DataCollatorForTokenClassification(
tokenizer: PreTrainedTokenizerBase,
padding: typing.Union[bool, str, transformers.utils.generic.PaddingStrategy] = True,
max_length: typing.Optional[int] = None,
pad_to_multiple_of: typing.Optional[int] = None,
label_pad_token_id: int = -100,
return_tensors: str = 'pt'
)
在进行NER(实体命名识别)任务时使用的数据收集器,该数据收集器不仅会动态的处理输入的数据,而且会处理数据的标签。
参数tokenizer表示用于编码数据的分词器。
参数padding表示填充方式,可以为布尔类型、字符串类型或者一个PaddingStrategy对象。当值为布尔类型时,True表示填充至最大序列长度,False表示不填充。当为字符串类型时,"longest"表示填充值最大序列长度,"max_length"表示填充值参数max_length设置的长度,"do_not_pad"表示不填充。
参数max_length表示填充序列的最大长度,当设置padding="max_length"时,该参数才会有用。
参数pad_to_multiple_of表示填充的序列的倍数。
参数label_pad_token_id表示填充标签时的值,默认为-100。注意,默认数据中序列填充的值为0,这与标签填充的值不一致。
参数return_tensors表示返回数据的类型,有三个可选项,分别是"tf"、“pt”、“np”,分别表示tensorflow可以处理的数据类型,pytorch可以处理的数据类型以及numpy数据类型。
使用示例
def preprocess_fn(data):
tokenized_inputs = tokenizer(data["tokens"], truncation=True, is_split_into_words=True)
labels = []
for i, label in enumerate(data["ner_tags"]):
word_ids = tokenized_inputs.word_ids(batch_index=i)
previous_word_id = None
label_ids = []
for idx in word_ids:
if idx is None:
label_ids.append(-100)
elif idx != previous_word_id:
label_ids.append(label[idx])
previous_word_id = idx
labels.append(label_ids)
tokenized_inputs["labels"] = labels
return tokenized_inputs
dataset = datasets.load_dataset("conll2003")
label_list = dataset["train"].features["ner_tags"].feature.names
tokenizer = transformers.AutoTokenizer.from_pretrained("distilbert-base-uncased")
data_collator = transformers.DataCollatorForTokenClassification(tokenizer=tokenizer,
padding=True,
label_pad_token_id=-100,
return_tensors="tf")
dataset = dataset.map(preprocess_fn,
batched=True,
batch_size=1000,
remove_columns=["id", "tokens", "pos_tags", "chunk_tags", "ner_tags"])
train_dataset = dataset["train"].to_tf_dataset(columns=["input_ids", "attention_mask"],
batch_size=16,
shuffle=True,
collate_fn=data_collator,
label_cols=["labels"])
GitHub 加速计划 / tra / transformers
130.24 K
25.88 K
下载
huggingface/transformers: 是一个基于 Python 的自然语言处理库,它使用了 PostgreSQL 数据库存储数据。适合用于自然语言处理任务的开发和实现,特别是对于需要使用 Python 和 PostgreSQL 数据库的场景。特点是自然语言处理库、Python、PostgreSQL 数据库。
最近提交(Master分支:2 个月前 )
33868a05
* [i18n-HI] Translated accelerate page to Hindi
* Update docs/source/hi/accelerate.md
Co-authored-by: K.B.Dharun Krishna <kbdharunkrishna@gmail.com>
* Update docs/source/hi/accelerate.md
Co-authored-by: K.B.Dharun Krishna <kbdharunkrishna@gmail.com>
* Update docs/source/hi/accelerate.md
Co-authored-by: K.B.Dharun Krishna <kbdharunkrishna@gmail.com>
* Update docs/source/hi/accelerate.md
Co-authored-by: K.B.Dharun Krishna <kbdharunkrishna@gmail.com>
---------
Co-authored-by: Kay <kay@Kays-MacBook-Pro.local>
Co-authored-by: K.B.Dharun Krishna <kbdharunkrishna@gmail.com> 13 天前
e2ac16b2
* rework converter
* Update modular_model_converter.py
* Update modular_model_converter.py
* Update modular_model_converter.py
* Update modular_model_converter.py
* cleaning
* cleaning
* finalize imports
* imports
* Update modular_model_converter.py
* Better renaming to avoid visiting same file multiple times
* start converting files
* style
* address most comments
* style
* remove unused stuff in get_needed_imports
* style
* move class dependency functions outside class
* Move main functions outside class
* style
* Update modular_model_converter.py
* rename func
* add augmented dependencies
* Update modular_model_converter.py
* Add types_to_file_type + tweak annotation handling
* Allow assignment dependency mapping + fix regex
* style + update modular examples
* fix modular_roberta example (wrong redefinition of __init__)
* slightly correct order in which dependencies will appear
* style
* review comments
* Performance + better handling of dependencies when they are imported
* style
* Add advanced new classes capabilities
* style
* add forgotten check
* Update modeling_llava_next_video.py
* Add prority list ordering in check_conversion as well
* Update check_modular_conversion.py
* Update configuration_gemma.py 13 天前
更多推荐
已为社区贡献7条内容
所有评论(0)