-
在指定device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")前提下
使用自带的duie和dgre数据集都会在训练几个Epoch之后抛出如下错误：
【train】6/100 40420/713100 loss:2.2920708656311035
【train】6/100 40430/713100 lo…
-
我用您的代码进行了模型的训练，成功训练之后打算用predict.py代码进行预测的尝试
结果出现以下两个问题：
①输入文本过长似乎会发生“实体识别结果为空”的提示
②而输入较短的文本会提示访问huggingface的404，似乎我需要在huggingface上上传模型还是什么吗？
2023-01-24 15:21:36.106249: I tensorflow/stream_exe…
uyoin updated
2 months ago
-
RuntimeError: mat1 and mat2 shapes cannot be multiplied (11264x1024 and 768x6)
当
```
'roberta': (
'transformers.BertTokenizer',
'transformers.RobertaModel',
'transforme…
-
求助：我在执行BERT+CRF中run_MAVEN.sh的时候，遇到maven/dev.jsonl文件不存在的问题。下载的数据集中只有train/test/valid.jsonl三个，并没有所谓的dev.jsonl，前面的过程正常执行。
![1713520355449](https://github.com/THU-KEG/MAVEN-dataset/assets/75780667/e3…
-
Do you have some demonstration on what cases does grobid fail with crf and where delft is better, please?
You mention in the documentation: "current GROBID cheap approach" - were you refering …
flckv updated
3 weeks ago
-
作者大大你好，我只修改了config.py里面的标签，数据里面的空格我用的‘,’代替的，然后跑BERT-LSTM-CRF是正常的，但是相同的数据在BERT-CRF时就会报这个错误，错误是在model.py中的loss = self.crf(logits, labels, loss_mask) * (-1)请问是什么原因呀，麻烦您啦
-
Traceback (most recent call last):
File "/home/customer/qlf/code/Chinese-clinical-NER/bert_bilstm_crf/predict_bert.py", line 19, in
model=Bert_ner(config_path,checkpoint_path,dict_path).model…
-
Hi,
Really impressive work and a nice repository combining all the NER models.
I was trying to comprehend the codebase and what all are its capabilities. To that end, I made a list of NER-baselines …
-
['O', 'B-故障设备', 'I-故障设备', 'B-故障原因', 'I-故障原因']
{'O': 0, 'B-故障设备': 1, 'I-故障设备': 2, 'B-故障原因': 3, 'I-故障原因': 4}
Some weights of the model checkpoint at ./model_hub/chinese-bert-wwm-ext/ were not used whe…
-
C:\Users\yinli\miniconda3\envs\bbcn\python.exe D:\实体\pytorch_bert_bilstm_crf_ner-main\main.py
{0: 'O', 1: 'B-dep', 2: 'I-dep', 3: 'E-dep', 4: 'S-dep', 5: 'B-dru', 6: 'I-dru', 7: 'E-dru', 8: 'S-dru',…