Coder Social home page Coder Social logo

作者大大您好!我在训练我自己的数据时,出现了以下的问题,我尝试着用pop函数来解决,但始一直解决不了,麻烦你帮我看看问题所在!! about pytorch_bert_bilstm_crf_ner HOT 9 CLOSED

taishan1994 avatar taishan1994 commented on June 4, 2024
作者大大您好!我在训练我自己的数据时,出现了以下的问题,我尝试着用pop函数来解决,但始一直解决不了,麻烦你帮我看看问题所在!!

from pytorch_bert_bilstm_crf_ner.

Comments (9)

taishan1994 avatar taishan1994 commented on June 4, 2024

RuntimeError: Error(s) in loading state_dict for NormalNerModel: size mismatch for linear.weight: copying a param with shape torch.Size([33, 256]) from checkpoint, the shape in current model is torch.Size([25, 256]). size mismatch for linear.bias: copying a param with shape torch.Size([33]) from checkpoint, the shape in current model is torch.Size([25]). size mismatch for crf.start_transitions: copying a param with shape torch.Size([33]) from checkpoint, the shape in current model is torch.Size([25]). size mismatch for crf.end_transitions: copying a param with shape torch.Size([33]) from checkpoint, the shape in current model is torch.Size([25]). size mismatch for crf.transitions: copying a param with shape torch.Size([33, 33]) from checkpoint, the shape in current model is torch.Size([25, 25]).

实体的标签数目不对。

from pytorch_bert_bilstm_crf_ner.

shitft avatar shitft commented on June 4, 2024

from pytorch_bert_bilstm_crf_ner.

taishan1994 avatar taishan1994 commented on June 4, 2024

请问要怎么解决呀!我是小白一枚,实在不知道改哪里! 发自我的iPhone

------------------ 原始邮件 ------------------ 发件人: 西西嘛呦 @.> 发送时间: 2022年11月17日 19:30 收件人: taishan1994/pytorch_bert_bilstm_crf_ner @.> 抄送: shitft @.>, Author @.> 主题: 回复:[taishan1994/pytorch_bert_bilstm_crf_ner] 作者大大您好!我在训练我自己的数据时,出现了以下的问题,我尝试着用pop函数来解决,但始一直解决不了,麻烦你帮我看看问题所在!! (Issue #26) RuntimeError: Error(s) in loading state_dict for NormalNerModel: size mismatch for linear.weight: copying a param with shape torch.Size([33, 256]) from checkpoint, the shape in current model is torch.Size([25, 256]). size mismatch for linear.bias: copying a param with shape torch.Size([33]) from checkpoint, the shape in current model is torch.Size([25]). size mismatch for crf.start_transitions: copying a param with shape torch.Size([33]) from checkpoint, the shape in current model is torch.Size([25]). size mismatch for crf.end_transitions: copying a param with shape torch.Size([33]) from checkpoint, the shape in current model is torch.Size([25]). size mismatch for crf.transitions: copying a param with shape torch.Size([33, 33]) from checkpoint, the shape in current model is torch.Size([25, 25]). 实体的标签数目不对。 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

nor_ent2id.json里面有多少个标签就设置num_tags=多少

from pytorch_bert_bilstm_crf_ner.

shitft avatar shitft commented on June 4, 2024

from pytorch_bert_bilstm_crf_ner.

shitft avatar shitft commented on June 4, 2024

又来打扰您啦!
我在main.sh和bert_ner_model中修改了mum=tags的参数,没有解决问题。我是在windows中运行项目的,下载了git后在pycharm终端已经能正常运行main.sh文件了,但是一运行main.py还是会出现size mismatch的错误!
您有空时帮我看看

from pytorch_bert_bilstm_crf_ner.

taishan1994 avatar taishan1994 commented on June 4, 2024

又来打扰您啦! 我在main.sh和bert_ner_model中修改了mum=tags的参数,没有解决问题。我是在windows中运行项目的,下载了git后在pycharm终端已经能正常运行main.sh文件了,但是一运行main.py还是会出现size mismatch的错误! 您有空时帮我看看

不要在pycharm里面直接运行,将指令复制出来在终端里面运行。

from pytorch_bert_bilstm_crf_ner.

shitft avatar shitft commented on June 4, 2024

作者大大,我在将model_name设为bilstm、idcnn、crf训练时会出现model.pt不生成的问题,之前用您的数据训练时,也出现了checkpoints下有的模型有.pt文件,有的没有的问题,请问是因为什么呐

另外就是,我的显卡是rtx2060s 8G的,我把model_name修改为bert,Albert等模型时,就会报错说我的内存不足,我看了csdn上的几个解决策略,都没能解决我目前的问题!请问除了换显卡,还能通过其他方法来解决吗

from pytorch_bert_bilstm_crf_ner.

taishan1994 avatar taishan1994 commented on June 4, 2024

作者大大,我在将model_name设为bilstm、idcnn、crf训练时会出现model.pt不生成的问题,之前用您的数据训练时,也出现了checkpoints下有的模型有.pt文件,有的没有的问题,请问是因为什么呐

另外就是,我的显卡是rtx2060s 8G的,我把model_name修改为bert,Albert等模型时,就会报错说我的内存不足,我看了csdn上的几个解决策略,都没能解决我目前的问题!请问除了换显卡,还能通过其他方法来解决吗

1、打印下train里面保存模型的那里看看是否有执行保存模型。train里面有个eval_steps,如果总的step小于它是不会有模型生成的。
2、调小train_batch_size和eval_batch_size直到显存够用为止。

from pytorch_bert_bilstm_crf_ner.

shitft avatar shitft commented on June 4, 2024

from pytorch_bert_bilstm_crf_ner.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.