zjunlp / openue Goto Github PK

作者你好，我跑了pytorch版本两个脚本run_ner.sh，run_seq.sh，发现loss都没有变化，训练到最后评价指标也都是接近于0，请问是哪里设置不对吗？

您好！我想尝试运行OpenUE的ske.ipynb代码，我在网上查询SKE数据集的下载源为http://lic2019.ccf.org.cn/kg ，但是我无法打开这个网址（2021.12.8 20:07），可能是因为原网址失效了。
所以想请问您这边可以直接提供原数据吗？或者有其他下载路径也可以？
非常感谢！

Hey, first of all, great work. Loved your work in this field.
I think Event Extraction is not working properly on the demo page(http://openue.top/index.html). Can you have a look at it?
Another request is to prepare the documentation in English. A lot of people will be having many questions about the dataset used, entities on which model is trained, pretrained model f scores, and so on.

Whenever I hover over the Knowledge graph in demo page, it shows something in Chinese which I am not able to understand. Can you have a look at it? Secondly how about showing the predicate instead of the predicate code.

Traceback (most recent call last):
File "main.py", line 146, in
main()
File "main.py", line 117, in main
if not test_only: trainer.fit(lit_model, datamodule=data)
File "/cephfs/xqwang/openue/openue/lib/python3.7/site-packages/pytorch_lightning/trainer/trainer.py", line 458, in fit
self._run(model)
File "/cephfs/xqwang/openue/openue/lib/python3.7/site-packages/pytorch_lightning/trainer/trainer.py", line 756, in _run
self.dispatch()
File "/cephfs/xqwang/openue/openue/lib/python3.7/site-packages/pytorch_lightning/trainer/trainer.py", line 797, in dispatch
self.accelerator.start_training(self)
File "/cephfs/xqwang/openue/openue/lib/python3.7/site-packages/pytorch_lightning/accelerators/accelerator.py", line 96, in start_training
self.training_type_plugin.start_training(trainer)
File "/cephfs/xqwang/openue/openue/lib/python3.7/site-packages/pytorch_lightning/plugins/training_type/ddp_spawn.py", line 122, in start_training
mp.spawn(self.new_process, **self.mp_spawn_kwargs)
File "/cephfs/xqwang/openue/openue/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 230, in spawn
return start_processes(fn, args, nprocs, join, daemon, start_method='spawn')
File "/cephfs/xqwang/openue/openue/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 179, in start_processes
process.start()
File "/root/miniconda3/lib/python3.7/multiprocessing/process.py", line 112, in start
self._popen = self._Popen(self)
File "/root/miniconda3/lib/python3.7/multiprocessing/context.py", line 284, in _Popen
return Popen(process_obj)
File "/root/miniconda3/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 32, in init
super().init(process_obj)
File "/root/miniconda3/lib/python3.7/multiprocessing/popen_fork.py", line 20, in init
self._launch(process_obj)
File "/root/miniconda3/lib/python3.7/multiprocessing/popen_spawn_posix.py", line 47, in _launch
reduction.dump(process_obj, fp)
File "/root/miniconda3/lib/python3.7/multiprocessing/reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
AttributeError: Can't pickle local object 'get_linear_schedule_with_warmup..lr_lambda'

请问这个是什么问题呢？run_ner.sh也遇到了同样的问题。依赖都是按照requirements安装的。

Traceback (most recent call last):
  File "main.py", line 7, in <module>
    import pytorch_lightning as pl
  File "/home/users/peikaili/.conda/envs/openue/lib/python3.8/site-packages/pytorch_lightning/__init__.py", line 20, in <module>
    from pytorch_lightning import metrics  # noqa: E402
  File "/home/users/peikaili/.conda/envs/openue/lib/python3.8/site-packages/pytorch_lightning/metrics/__init__.py", line 15, in <module>
    from pytorch_lightning.metrics.classification import (  # noqa: F401
  File "/home/users/peikaili/.conda/envs/openue/lib/python3.8/site-packages/pytorch_lightning/metrics/classification/__init__.py", line 14, in <module>
    from pytorch_lightning.metrics.classification.accuracy import Accuracy  # noqa: F401
  File "/home/users/peikaili/.conda/envs/openue/lib/python3.8/site-packages/pytorch_lightning/metrics/classification/accuracy.py", line 18, in <module>
    from pytorch_lightning.metrics.utils import deprecated_metrics
  File "/home/users/peikaili/.conda/envs/openue/lib/python3.8/site-packages/pytorch_lightning/metrics/utils.py", line 22, in <module>
    from torchmetrics.utilities.data import get_num_classes as _get_num_classes
ImportError: cannot import name 'get_num_classes' from 'torchmetrics.utilities.data' 

Just follow the readme file and show this error

Hi

Great work! I want to try out the model and while running the first step:

1. Data Preprocessing. Put the pretrained language model (e.g., BERT) in the pretrained_model folder and put all raw data (run script download_ske.sh in the benchmark folder) in the raw_data folder.

I couldn't find the benchmark folder and the script 'download_ske.sh'

I also could not find these scripts in any folders for step 4
sh export_seq.sh ske
sh serving_cls.sh ske

can you help me?

感谢你的工作。请问训练语料有哪些呢？是基于开源的语料训练的吗

您好！非常感谢该项目的开放与维护。

我在尝试运行时出现了两个问题：

1. 在 windows 10 - 64 位 环境下使用 Pycharm，安装完依赖和其他文件后，运行 run_ner/seq 没有反应，并没有下载对应的 ./dataset以及生成目录。

2. 在 colab 中使用 OpenUE_demo.ipynb 进行训练后尝试在使用 srcripts下 的 interactive.sh 时，报错：

Using /usr/local/lib/python3.7/dist-packagesFinished processing dependencies for openue==0.2.501/23/2022 12:58:52 - INFO - openue.data.data_module - add total special tokens: 50
['[relation0]', '[relation1]', '[relation2]', '[relation3]', '[relation4]', '[relation5]', '[relation6]', '[relation7]', '[relation8]', '[relation9]', '[relation10]', '[relation11]', '[relation12]', '[relation13]', '[relation14]', '[relation15]', '[relation16]', '[relation17]', '[relation18]', '[relation19]', '[relation20]', '[relation21]', '[relation22]', '[relation23]', '[relation24]', '[relation25]', '[relation26]', '[relation27]', '[relation28]', '[relation29]', '[relation30]', '[relation31]', '[relation32]', '[relation33]', '[relation34]', '[relation35]', '[relation36]', '[relation37]', '[relation38]', '[relation39]', '[relation40]', '[relation41]', '[relation42]', '[relation43]', '[relation44]', '[relation45]', '[relation46]', '[relation47]', '[relation48]', '[relation49]']
Traceback (most recent call last):
File "main.py", line 146, in
main()
File "main.py", line 94, in main
lit_model = litmodel_class(args=args, data_config=data.get_config())
File "/usr/local/lib/python3.7/dist-packages/openue/lit_models/transformer.py", line 166, in init
self._init_model()
File "/usr/local/lib/python3.7/dist-packages/openue/lit_models/transformer.py", line 175, in _init_model
self.model = Inference(self.args)
File "/usr/local/lib/python3.7/dist-packages/openue/models/model.py", line 145, in init
self._init_models()
File "/usr/local/lib/python3.7/dist-packages/openue/models/model.py", line 174, in _init_models
label2id={label: i for i, label in enumerate(self.labels_seq)},
File "/usr/local/lib/python3.7/dist-packages/transformers/models/auto/configuration_auto.py", line 582, in from_pretrained
config_dict, _ = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/transformers/configuration_utils.py", line 556, in get_config_dict
local_files_only=local_files_only,
File "/usr/local/lib/python3.7/dist-packages/transformers/configuration_utils.py", line 844, in get_configuration_file
path_or_repo, revision=revision, use_auth_token=use_auth_token, local_files_only=local_files_only
File "/usr/local/lib/python3.7/dist-packages/transformers/file_utils.py", line 2103, in get_list_of_files
return list_repo_files(path_or_repo, revision=revision, token=token)
File "/usr/local/lib/python3.7/dist-packages/huggingface_hub/hf_api.py", line 885, in list_repo_files
repo_id, revision=revision, token=token, timeout=timeout
File "/usr/local/lib/python3.7/dist-packages/huggingface_hub/hf_api.py", line 868, in model_info
r.raise_for_status()
File "/usr/local/lib/python3.7/dist-packages/requests/models.py", line 941, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/api/models/output/ske/seq/epoch=2-Eval

3. 应该如何在训练完成后进行指定输入文本的知识图谱提取呢（以 Colab 上的 Demo 为例）？使用 lit_model.inference(inputs) 吗？

祝您有愉快的一天！
因我刚开始这方面的工作，多有叨扰，感激不尽。

您好，我按照ske.ipynb的流程测试，但是结果很不理想，是超参设置的问题吗，按照默认config设置超参，无论是哪个任务F1值都很低

cloab 运行显示保存模型路径为None，请问我应该在哪里设置？

英文数据集的格式和中文数据集一样吗？能否提供一下英文数据集

    # read configs for the mode, model_name, etc. from setup_config.json
    setup_config_path = os.path.join(model_dir, "setup_config.json")
    if os.path.isfile(setup_config_path):
        with open(setup_config_path) as setup_config_file:
            self.setup_config = json.load(setup_config_file)
    else:
        logger.warning("Missing the setup_config.json file.")

执行run_ner.sh 训练出来的模型 文件夹下没有setup_config.json文件 ，打包成mar部署后 报错 Missing the setup_config.json file.

您好，问一下 ske.ipynb 的验证模块在colab怎么不行？出现上述错误。

新版本改动好多 啊

您好，最后的模型保存在哪里？我是用Google Colab训练的。
而且我发现Google Colab是否没有写完，我参照ske.ipynb编写实体识别模块，但是出现了如下错误：

您能否提供更完整的版本？

感谢作者提供的代码，但是我找不到predict_online.py这个文件呢

如题，看到之前的issue里面OpenUE可以用于事件抽取，并且提供了DuEE1.0数据集作为参考格式。请问DuEE1.0是可以直接作为模型输入还是需要改动呢？毕竟和demo中提供的三元组抽取数据集格式不一样

这个代码是否包含将数据知识抽取的代码啊，我只找到了训练的

运行./scripts/run_ner.sh
报错：
Traceback (most recent call last):
File "main.py", line 146, in
main()
File "main.py", line 73, in main
parser = _setup_parser()
File "main.py", line 33, in _setup_parser
trainer_parser = pl.Trainer.add_argparse_args(parser)
AttributeError: type object 'Trainer' has no attribute 'add_argparse_args'

1、README_CN.md文件中，python predict.sh ske 应该改为sh predict.sh ske；
2、openue/init.py中，所有"/home/ningyu.zny/work/OpenUE/pretrained_model/chinese_wwm_ext_L-12_H-768_A-12/bert_config.json"全路径应该改为相对路径；

能否发一份跑好的模型”ske_bert_entity_relation“到我邮箱？ [email protected]
感谢🙏

_INFO:tensorflow: name = predicate_output_weights:0, shape = (49, 768) INFO:tensorflow: name = predicate_output_bias:0, shape = (49,) INFO:tensorflow: name = token_label_output_weights:0, shape = (10, 768) INFO:tensorflow: name = token_label_output_bias:0, shape = (10,) INFO:tensorflow:Error recorded from evaluation_loop: Values of eval_metric_ops must be (metric_value, update_op) tuples, given: Tensor("ArgMax:0", shape=(?,), dtype=int32) for key: predicate_prediction INFO:tensorflow:evaluation_loop marked as finished WARNING:tensorflow:Reraising captured error Traceback (most recent call last): File "run_sequnce_labeling.py", line 883, in tf.app.run() File "/home/fanyongfeng/.conda/envs/ner-rc/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run _sys.exit(main(argv)) File "run_sequnce_labeling.py", line 814, in main result = estimator.evaluate(input_fn=eval_input_fn, steps=eval_steps) File "/home/fanyongfeng/.conda/envs/ner-rc/lib/python3.6/site-packages/tensorflow/contrib/tpu/python/tpu/tpu_estimator.py", line 2424, in evaluate rendezvous.raise_errors() File "/home/fanyongfeng/.conda/envs/ner-rc/lib/python3.6/site-packages/tensorflow/contrib/tpu/python/tpu/error_handling.py", line 128, in raise_errors six.reraise(typ, value, traceback) File "/home/fanyongfeng/.conda/envs/ner-rc/lib/python3.6/site-packages/six.py", line 703, in reraise raise value File "/home/fanyongfeng/.conda/envs/ner-rc/lib/python3.6/site-packages/tensorflow/contrib/tpu/python/tpu/tpu_estimator.py", line 2418, in evaluate name=name File "/home/fanyongfeng/.conda/envs/ner-rc/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 478, in evaluate return _evaluate() File "/home/fanyongfeng/.conda/envs/ner-rc/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 460, in _evaluate self._evaluate_build_graph(input_fn, hooks, checkpoint_path)) File "/home/fanyongfeng/.conda/envs/ner-rc/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1484, in _evaluate_build_graph self._call_model_fn_eval(input_fn, self.config)) File "/home/fanyongfeng/.conda/envs/ner-rc/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1520, in _call_model_fn_eval features, labels, model_fn_lib.ModeKeys.EVAL, config) File "/home/fanyongfeng/.conda/envs/ner-rc/lib/python3.6/site-packages/tensorflow/contrib/tpu/python/tpu/tpu_estimator.py", line 2195, in _call_model_fn features, labels, mode, config) File "/home/fanyongfeng/.conda/envs/ner-rc/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1195, in _call_model_fn model_fn_results = self._model_fn(features=features, **kwargs) File "/home/fanyongfeng/.conda/envs/ner-rc/lib/python3.6/site-packages/tensorflow/contrib/tpu/python/tpu/tpu_estimator.py", line 2479, in _model_fn features, labels, is_export_mode=is_export_mode) File "/home/fanyongfeng/.conda/envs/ner-rc/lib/python3.6/site-packages/tensorflow/contrib/tpu/python/tpu/tpu_estimator.py", line 1259, in call_without_tpu return self._call_model_fn(features, labels, is_export_mode=is_export_mode) File "/home/fanyongfeng/.conda/envs/ner-rc/lib/python3.6/site-packages/tensorflow/contrib/tpu/python/tpu/tpu_estimator.py", line 1538, in _call_model_fn return estimator_spec.as_estimator_spec() File "/home/fanyongfeng/.conda/envs/ner-rc/lib/python3.6/site-packages/tensorflow/contrib/tpu/python/tpu/tpu_estimator.py", line 330, in as_estimator_spec prediction_hooks=self.prediction_hooks + hooks) File "/home/fanyongfeng/.conda/envs/ner-rc/lib/python3.6/site-packages/tensorflow/python/estimator/model_fn.py", line 236, in new 'tuples, given: {} for key: {}'.format(value, key)) TypeError: Values of eval_metric_ops must be (metric_value, update_op) tuples, given: Tensor("ArgMax:0", shape=(?,), dtype=int32) for key: predicate_prediction _

使用的命令是sh train_seq.sh ske
环境问题全部解决，但是在运行训练命令后出现这个问题。
如果有调试好的代码可以发邮件给我：[email protected] 谢谢

源代码能做事件抽取吗