cuhksz-nlp / aesiner Goto Github PK
View Code? Open in Web Editor NEWLicense: MIT License
License: MIT License
Excuse me, could you please release how to preprocess the original Ontonote4.0, because I can't get the information from the https://github.com/yhcc/OntoNotes-5.0-NER..
Thanks!!!
RT
非常感谢开源代码。但是我发现在执行WE数据的时候存在一些问题
Traceback (most recent call last):
File "train_zen_cn.py", line 268, in
trainer.train(load_best_model=False)
File "AESINER-master/fastNLP/core/trainer.py", line 702, in train
raise e
File "AESINER-master/fastNLP/core/trainer.py", line 695, in train
self._train()
File "AESINER-master/fastNLP/core/trainer.py", line 861, in _train
dep_matrix = self.get_dep_mask_matrix(indices, seq_len=torch.max(batch_x.get("seq_len")).item())
File "AESINER-master/fastNLP/core/trainer.py", line 796, in get_dep_mask_matrix
ret[i][j] = 1
IndexError: list assignment index out of range
Traceback (most recent call last):
File "train_zen_cn.py", line 262, in
trainer.train(load_best_model=False)
File "AESINER-master/fastNLP/core/trainer.py", line 702, in train
raise e
File "AESINER-master/fastNLP/core/trainer.py", line 695, in train
self._train()
File "AESINER-master/fastNLP/core/trainer.py", line 854, in _train
features = self.get_features(indices, seq_len=torch.max(batch_x.get("seq_len")).item())
File "AESINER-master/fastNLP/core/trainer.py", line 748, in get_features
ret_list[i] = torch.tensor(ret_list[i])
ValueError: expected sequence of length 29 at dim 1 (got 31)
請問這個該如何解決?
Traceback (most recent call last):
File "data_helper.py", line 401, in
request_features_from_stanford(data_dir, 'train')
File "data_helper.py", line 161, in request_features_from_stanford
results = nlp.annotate(sentence, properties=props)
File "/home/jsj201-6/mount1/lww/AESINER-master1/corenlp.py", line 160, in annotate
r_dict = json.loads(r.text)
File "/home/jsj201-6/anaconda3/envs/lww/lib/python3.7/json/init.py", line 348, in loads
return _default_decoder.decode(s)
File "/home/jsj201-6/anaconda3/envs/lww/lib/python3.7/json/decoder.py", line 337, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "/home/jsj201-6/anaconda3/envs/lww/lib/python3.7/json/decoder.py", line 355, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
是否对数据做过预处理,我用的WEIBO的数据集做的处理。只是将训练集、测试集、开发集改了名,我以为是空行符出现的错误,然后将数据中的空行删除,但也不行,不会爆出错,但是json文件为空了。请问是什么问题?
Hi I am trying to run the code on a GPU machine using my dataset. I am getting the following error, Can you please check?
Save cache to caches/tweet_dataset_bert_elmo_bioes_adatrans_True_123_10_10_10.pkl.
training epochs started 2022-03-12-16-43-15
Traceback (most recent call last):
File "/home/akalia/aesiner_project/train_bert_elmo_en.py", line 237, in
trainer.train(load_best_model=False)
File "/home/akalia/aesiner_project/fastNLP/core/trainer.py", line 702, in train
raise e
File "/home/akalia/aesiner_project/fastNLP/core/trainer.py", line 695, in train
self._train()
File "/home/akalia/aesiner_project/fastNLP/core/trainer.py", line 894, in _train
prediction = self._data_forward(self.model, batch_x)
File "/home/akalia/aesiner_project/fastNLP/core/trainer.py", line 1003, in _data_forward
y = network(
File "/home/akalia/anaconda3/envs/akalia/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/akalia/aesiner_project/models/TENER.py", line 444, in forward
return self._forward(chars, target, bigrams, pos_features, dep_features, chunk_features,
File "/home/akalia/aesiner_project/models/TENER.py", line 411, in _forward
hidden = self.embed(chars)
File "/home/akalia/anaconda3/envs/akalia/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/akalia/aesiner_project/fastNLP/embeddings/stack_embedding.py", line 94, in forward
outputs.append(embed(words))
File "/home/akalia/anaconda3/envs/akalia/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/akalia/aesiner_project/fastNLP/embeddings/elmo_embedding.py", line 136, in forward
outputs = self.model(words)
File "/home/akalia/anaconda3/envs/akalia/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/akalia/aesiner_project/fastNLP/embeddings/elmo_embedding.py", line 313, in forward
encoder_output = self.encoder(token_embedding, seq_len)
File "/home/akalia/anaconda3/envs/akalia/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/akalia/aesiner_project/fastNLP/modules/encoder/_elmo.py", line 319, in forward
inputs = nn.utils.rnn.pack_padded_sequence(inputs, sort_lens, batch_first=True)
File "/home/akalia/anaconda3/envs/akalia/lib/python3.9/site-packages/torch/nn/utils/rnn.py", line 249, in pack_padded_sequence
_VF._pack_padded_sequence(input, lengths, batch_first)
RuntimeError: 'lengths' argument should be a 1D CPU int64 tensor, but got 1D cuda:0 Long tensor
在其他数据集上一直出现IndexError:list index out of range问题,不清楚是不是索引有问题?从0开始最大应该是5249,但是会出现5250,应该如何解决?
您好,我想问一下tencent_unigram.txt文件在哪里怎么获取呢?或者您可以发给我一份么?
运行data_helper.py出现错误
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.