Comments (1)
使用数据集cner训练bert-bilstm和bert-bilstm-crf模型后,运行predict.py出现以下报错
raceback (most recent call last): File "F:/NER_project/pytorch_bert_bilstm_crf_ner/predict.py", line 120, in print(batch_predict(raw_text, model, device, args, id2query)) File "F:/NER_project/pytorch_bert_bilstm_crf_ner/predict.py", line 39, in batch_predict logits = model(token_ids, attention_masks, token_type_ids, None) File "D:\Envs\easy_bert\lib\site-packages\torch\nn\modules\module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "F:\NER_project\pytorch_bert_bilstm_crf_ner\bert_ner_model.py", line 269, in forward seq_out = seq_out.contiguous().view(batch_size, self.args.max_seq_len, -1) # [batchsize, max_len, num_tags] RuntimeError: shape '[1, 150, -1]' is invalid for input of size 1815
看一下你的参数。
from pytorch_bert_bilstm_crf_ner.
Related Issues (20)
- 大哥你好。我想问一下File "/home/vrlab/wwt/pytorch_bert_bilstm_crf_ner-main/bert_base_model.py", line 11, in __init__ assert os.path.exists(bert_dir) and os.path.exists(config_path), \ AssertionError: pretrained bert file does not exist是为啥 HOT 5
- 运行问题 HOT 6
- 您好 HOT 9
- 大佬您好,可以帮忙看看这个bug吗 HOT 13
- 换成BIO类型的数据应该怎么做? HOT 7
- 导出onnx问题 Error(s) in loading state_dict for BertNerModel: Unexpected key(s) in state_dict: "linear.weight", "linear.bias". HOT 2
- 对BERT模型进行继续预训练对提高性能是否有帮助? HOT 4
- 训练自己的数据,内存占用一直增长,直到吃满内存 HOT 2
- 请问一小pkl文件怎么处理得到? HOT 1
- > 我加你qq吧,你说下。 HOT 2
- 关于使用CRF文件将BERT+CRF模型转换为ONNX的问题 HOT 6
- 网页问题 HOT 1
- 英文实体识别的问题 HOT 1
- RuntimeError: expected predicate to be bool, got torch.uint8 HOT 1
- Albert问题 HOT 2
- AssertionError: pretrained bert file does not exist HOT 1
- 更换数据集后报CUDA error: device-side assert triggered HOT 1
- 求一份分词数据集 HOT 1
- 我的checkpoints文件夹是空的 HOT 1
- 这个命名实体识别的算法思路是什么? HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pytorch_bert_bilstm_crf_ner.