yhcc / bartabsa Goto Github PK

View Code? Open in Web Editor NEW

141.0 141.0 28.0 1.84 MB

Python 100.00%

bartabsa's People

Contributors

Stargazers

Watchers

bartabsa's Issues

关于Embedding

非常感谢公开论文代码！
现在有个问题想请教下：
对于公式（7），为什么需要再加一次BARTTokenEmbed （5）？我的理解是BARTTokenEmbed 已经是BART Encoder（2）的 input. 这个是因为最后的prediction更好吗？如果不加效果会差很多吗？谢谢！

关于logs日志loss文件为空及fitlog展示问题

您好，我使用fitlog观察指标发现只有metric的曲线，发现logs目录中loss.log是空文件，请问是为什么呢，如果想添加应该如何修改呢？此外best_metric参数能否在metric曲线上表示出来呢？期待早些回复，谢谢

fastnlp与fitlog安装包问题

您好！我想请问下按照readme.md文件中的pip install git+https://github.com/fastnlp/fastNLP@dev
pip install git+https://github.com/fastnlp/fitlog装不成功这两个包，能给一下具体的流程吗？主要是不清楚目前哪里出的问题。网上好多方法都试了

error

您好，在我按照readme和issue#1安装好相关库后。
我在训练时遇到一个错误，不知道怎么回事。

Traceback (most recent call last):
  File "train.py", line 24, in <module>
    fitlog.set_log_dir('logs')
  File "miniconda3/envs/bart-absa/lib/python3.7/site-packages/fitlog/__init__.py", line 122, in set_log_dir
    _logger.set_log_dir(log_dir, new_log)
  File "miniconda3/envs/bart-absa/lib/python3.7/site-packages/fitlog/fastlog/logger.py", line 32, in wrapper
    return func(*args, **kwargs)
  File "miniconda3/envs/bart-absa/lib/python3.7/site-packages/fitlog/fastlog/logger.py", line 174, in set_log_dir
    raise NotADirectoryError("`{}` is not exist.".format(log_dir))
NotADirectoryError: `logs` is not exist.

关于模型的测试问题

您好，我发现代码里没有直接在测试集上进行测试的代码。是不是仿照trainer，调用fastNLP的Tester类然后传一下测试集数据就可以了呢。

无论设置的batch size是多少（4/8/32等都试过），都会显示一次如下信息。
input fields after batch(if batch size is 2):
tgt_tokens: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2, 22])
src_tokens: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2, 41])
src_seq_len: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2])
tgt_seq_len: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2])
target fields after batch(if batch size is 2):
tgt_tokens: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2, 22])
target_span: (1)type:numpy.ndarray (2)dtype:object, (3)shape:(2,)
tgt_seq_len: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2])
这一块输出没有看懂。请求作者帮忙解释一下，谢谢。

Inference

Could you please upload the inference file?

请问为什么换了一个新数据集（英文）无法跑通

作者您好，我想要将ATE任务的数据集换成一个新的数据集（ASTE-Data-V2），在我将数据转换为ATE任务要求的格式后（与wang的数据格式一致），代码跑不通了。

bug存在于BartDecoder中，具体如下：

我输出了一下，这里input_ids并不是具体的tensor值，变成了数据的地址信息（比如 <torch.Tensor object at 0x7ff5ce4b2280>），positions也变成了类似情况。

请问你们在数据预处理阶段有对数据做什么特殊处理吗？或者ATE任务对数据有什么特殊要求吗？

The question of results

您好，请问在运行程序时需要对模型参数进行调整吗，比如学习率什么的，我没有对模型做任何修改的前提下，得到的结果（准确率、F1、Recall）和论文中得到的结果差异很大，请问这是为什么呢，希望能尽快得到您的答复！

RuntimeError freeze_support()

I'm following your readme, while using train.py in the dataset pengb I had this error:

` python train.py --dataset pengb/14lap
Read cache from caches/data_facebook/bart-base_pengb/14lap_False.pt.
The number of tokens in tokenizer  50265
50268 50273
input fields after batch(if batch size is 2):
        tgt_tokens: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2, 22])
        src_tokens: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2, 41])
        src_seq_len: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2])
        tgt_seq_len: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2])
target fields after batch(if batch size is 2):
        tgt_tokens: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2, 22])
        target_span: (1)type:numpy.ndarray (2)dtype:object, (3)shape:(2,)
        tgt_seq_len: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2])

training epochs started 2021-12-10-15-44-42-060416
Epoch 1/50:   0%|                                                          | 0/2850 [00:00<?, ?it/s, loss:{0:<6.5f}]Read cache from caches/data_facebook/bart-base_pengb/14lap_False.pt.
The number of tokens in tokenizer  50265
50268 50273
input fields after batch(if batch size is 2):
        tgt_tokens: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2, 22])
        src_tokens: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2, 41])
        src_seq_len: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2])
        tgt_seq_len: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2])
target fields after batch(if batch size is 2):
        tgt_tokens: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2, 22])
        target_span: (1)type:numpy.ndarray (2)dtype:object, (3)shape:(2,)
        tgt_seq_len: (1)type:torch.Tensor (2)dtype:torch.int64, (3)shape:torch.Size([2])

training epochs started 2021-12-10-15-44-52-779581
Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "C:\ProgramData\Anaconda3\lib\multiprocessing\spawn.py", line 116, in spawn_main
    exitcode = _main(fd, parent_sentinel)
  File "C:\ProgramData\Anaconda3\lib\multiprocessing\spawn.py", line 125, in _main
    prepare(preparation_data)
  File "C:\ProgramData\Anaconda3\lib\multiprocessing\spawn.py", line 236, in prepare
    _fixup_main_from_path(data['init_main_from_path'])
  File "C:\ProgramData\Anaconda3\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
    main_content = runpy.run_path(main_path,
  File "C:\ProgramData\Anaconda3\lib\runpy.py", line 265, in run_path
    return _run_module_code(code, init_globals, run_name,
  File "C:\ProgramData\Anaconda3\lib\runpy.py", line 97, in _run_module_code
    _run_code(code, mod_globals, init_globals,
  File "C:\ProgramData\Anaconda3\lib\runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "C:\Users\sp\.conda\envs\BARTABSA\project\BARTABSA-main\peng\train.py", line 155, in <module>
    trainer.train(load_best_model=False)
  File "C:\ProgramData\Anaconda3\lib\site-packages\fastNLP\core\trainer.py", line 667, in train
    raise e
  File "C:\ProgramData\Anaconda3\lib\site-packages\fastNLP\core\trainer.py", line 658, in train
    self._train()
  File "C:\ProgramData\Anaconda3\lib\site-packages\fastNLP\core\trainer.py", line 712, in _train
    for batch_x, batch_y in self.data_iterator:
  File "C:\ProgramData\Anaconda3\lib\site-packages\fastNLP\core\batch.py", line 266, in __iter__
    for indices, batch_x, batch_y in self.dataiter:
  File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 359, in __iter__
    return self._get_iterator()
  File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 305, in _get_iterator
    return _MultiProcessingDataLoaderIter(self)
  File "C:\ProgramData\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 918, in __init__
    w.start()
  File "C:\ProgramData\Anaconda3\lib\multiprocessing\process.py", line 121, in start
    self._popen = self._Popen(self)
  File "C:\ProgramData\Anaconda3\lib\multiprocessing\context.py", line 224, in _Popen
    return _default_context.get_context().Process._Popen(process_obj)
  File "C:\ProgramData\Anaconda3\lib\multiprocessing\context.py", line 327, in _Popen
    return Popen(process_obj)
  File "C:\ProgramData\Anaconda3\lib\multiprocessing\popen_spawn_win32.py", line 45, in __init__
    prep_data = spawn.get_preparation_data(process_obj._name)
  File "C:\ProgramData\Anaconda3\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
    _check_not_importing_main()
  File "C:\ProgramData\Anaconda3\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
    raise RuntimeError('''
RuntimeError:
        An attempt has been made to start a new process before the
        current process has finished its bootstrapping phase.

        This probably means that you are not using fork to start your
        child processes and you have forgotten to use the proper idiom
        in the main module:

            if __name__ == '__main__':
                freeze_support()
                ...`

Reading around it seems that : multiprocessing usually doesn't work in a console in Windows. When using a spawning system instead of fork, python must import modules and create state in the child process to get things to work. The outer script must be protected with a if name=="main": clause.
I don't know where to change the code however. Any hints?

是否考虑过将decoder部分的任务转换为预测词角标，而不是bpe index

以公开数据集合训练得到模型，接着在新的数据集上进行三元组任务（triplet）抽取，发现Invalid token的比例很大

是否有考虑过在encoder的embedding部分对词（word）进行编码，decoder部分的任务转换为预测词角标的，从而减少了invalid token的比例？

the metric

您好，很感激您的工作，但是我对metric上有点小疑惑

"这里相同的pair会被计算多次".
请问这里计算多次指的是什么呢，以AE为例，这是指的BART可能生成重复的aspects？按理说重复的aspects只能算预测对1个。但是在metric中这些重复的aspects都会被当做tp计算？

但是我看您的代码好像进行了去重操作

所以"这里相同的pair会被计算多次".到底是什么意思呢，望解答

NotADirectoryError: `logs` is not exist.

Hello,
I'm following your instruction in the readme but when I try to launch

python train.py --dataset pengb/14lap

I get this error. What could be the cause?

Traceback (most recent call last):
  File ".\train.py", line 24, in <module>
    fitlog.set_log_dir('logs')
  File "C:\ProgramData\Anaconda3\lib\site-packages\fitlog\__init__.py", line 122, in set_log_dir
    _logger.set_log_dir(log_dir, new_log)
  File "C:\ProgramData\Anaconda3\lib\site-packages\fitlog\fastlog\logger.py", line 32, in wrapper
    return func(*args, **kwargs)
  File "C:\ProgramData\Anaconda3\lib\site-packages\fitlog\fastlog\logger.py", line 174, in set_log_dir
    raise NotADirectoryError("`{}` is not exist.".format(log_dir))
NotADirectoryError: `logs` is not exist.

建议

首先，恭喜你们成功发表该论文，也很感谢你们开源代码。
但是，我看了论文和代码，发现代码结构和论文阐述有很大出入，特别是涉及每个子任务的时候，因为没有合理的注释注解，看起来非常晦涩。所以我建议作者再更新一下readme，把整个代码思路和结构再次阐述一遍（尤其是每个子任务），非常感谢。

About reproduction

Hi,
I am reproducing you work, but I found that after running with the default settings on the pengb/14lab, I got the triplet metrics as follows: triple_f=57.73, triple_rec=56.81, triple_pre=58.68, while in the paper, the results should be: triple_f=58.69, triple_rec=56.19, triple_pre=61.41. Is there any suggestion?

中文数据集使用及模型加载问题

你好：
我参考你们的文章A Unified Generative Framework for Aspect-Based Sentiment ，想用这个模型作中文的ABSA，于是我将原文的facebook/bart-base替换成fnlp/bart-base-chinese，但是我这里有以下几个问题：

1：transformers在4.4.1版本加载模型时会报错：RuntimeError: Error(s) in loading state_dict for BartModel:

size mismatch for encoder.embed_positions.weight: copying a param with shape torch.Size([514, 768]) from checkpoint, the
shape in current model is torch.Size([512, 768]).
size mismatch for encoder.embed_positions.weight: copying a param with shape torch.Size([514, 768]) from checkpoint, the
shape in current model is torch.Size([512, 768]).
这主要是在这里：model = BartSeq2SeqModel.build_model(bart_name, tokenizer, label_ids=label_ids,
decoder_type=decoder_type,copy_gate=False, use_encoder_mlp=use_encoder_mlp, use_recur_pos=False)

2：facebook提供的batr-base中有一些文件是merges.txt和json形式的vocab，这与您在huggingface上提供的不一致。我将您在

huggingface上提供的有关bart-base-chinese提供的文件用tokenizer.from_pretrained("bart-base-chinese")使用时，pytorch报错：
OSError: Can't load tokenizer for 'bart-base-chinese'. Make sure that:
'bart-base-chinese' is a correct model identifier listed on 'https://huggingface.co/models'
or 'bart-base-chinese' is the correct path to a directory containing relevant tokenizer files
请问这个该怎么解决？

yhcc / bartabsa Goto Github PK

bartabsa's People

Contributors

Stargazers

Watchers

Forkers

bartabsa's Issues

Recommend Projects

Recommend Topics

Recommend Org