Git Product home page Git Product logo

Comments (14)

QMSLWSJ avatar QMSLWSJ commented on June 11, 2024

错误如下:
【train】 epoch:0 85/1434 loss:7.5998
【train】 epoch:0 86/1434 loss:12.1990
【train】 epoch:0 87/1434 loss:18.4305
【train】 epoch:0 88/1434 loss:13.8174
【train】 epoch:0 89/1434 loss:16.8664
Traceback (most recent call last):
File "C:\Users\秋明山老王司机\Desktop\pytorch_bert_bilstm_crf_ner-main\main.py", line 266, in
bertForNer.train()
File "C:\Users\秋明山老王司机\Desktop\pytorch_bert_bilstm_crf_ner-main\main.py", line 64, in train
dev_loss, precision, recall, f1_score = self.dev()
File "C:\Users\秋明山老王司机\Desktop\pytorch_bert_bilstm_crf_ner-main\main.py", line 83, in dev
batch_output = np.array(batch_output)
ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (8,) + inhomogeneous part.

from pytorch_bert_bilstm_crf_ner.

QMSLWSJ avatar QMSLWSJ commented on June 11, 2024

紧急求助,谢谢大佬

from pytorch_bert_bilstm_crf_ner.

taishan1994 avatar taishan1994 commented on June 11, 2024

紧急求助,谢谢大佬

image

我直接拷贝项目运行的,没啥问题呀。

from pytorch_bert_bilstm_crf_ner.

taishan1994 avatar taishan1994 commented on June 11, 2024

紧急求助,谢谢大佬

image

我直接拷贝项目运行的,没啥问题呀。

from pytorch_bert_bilstm_crf_ner.

QMSLWSJ avatar QMSLWSJ commented on June 11, 2024

紧急求助,谢谢大佬

image

我直接拷贝项目运行的,没啥问题呀。

我使用的是您简介readme中最下面的cner参数,以形参的形式运行,然后会报错,我带入我自己的数据也有一样的问题,都是在89轮时报错,错误如下 setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (8,) + inhomogeneous part.各种调试孩子已经傻了,大佬帮忙看看吧

from pytorch_bert_bilstm_crf_ner.

QMSLWSJ avatar QMSLWSJ commented on June 11, 2024

抱歉晚上打扰您,重新下载您的源码,使用您的数据集和参数,还是存在相同问题,通过debug,感觉问题还是处在dev部分
if self.args.use_crf == 'True':
batch_output = dev_logits
batch_output = np.array(batch_output)
else:
batch_output = dev_logits.detach().cpu().numpy()
batch_output = np.argmax(batch_output, axis=2)

            if len(batch_output_all) == 0:
                batch_output_all = batch_output
            else:
                batch_output_all = np.append(batch_output_all, batch_output, axis=0)

不知道您运行的部分这部分有没有问题。

from pytorch_bert_bilstm_crf_ner.

taishan1994 avatar taishan1994 commented on June 11, 2024

setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (8,)

pytorch-crf版本是0.7.2么,再打印一下dev里面的batch_output,看看是什么。

from pytorch_bert_bilstm_crf_ner.

QMSLWSJ avatar QMSLWSJ commented on June 11, 2024

输出如下

FVW71P2YWWAZ{FMGHSPYO

from pytorch_bert_bilstm_crf_ner.

QMSLWSJ avatar QMSLWSJ commented on June 11, 2024

大佬,您能看看batch out有什么问题吗,或者您受累发一份您跑的源码看看吗,我是刚刚入门的纯小白,最近陷入瓶颈了,万分感谢!

from pytorch_bert_bilstm_crf_ner.

taishan1994 avatar taishan1994 commented on June 11, 2024

大佬,您能看看batch out有什么问题吗,或者您受累发一份您跑的源码看看吗,我是刚刚入门的纯小白,最近陷入瓶颈了,万分感谢!

你这里面的每一条数据的长度都不一样,肯定是有问题的。运行的时候在命令行运行,pycharm里面的话要带参数运行。我直接拷贝项目后运行指令就可以正常运行的。

from pytorch_bert_bilstm_crf_ner.

QMSLWSJ avatar QMSLWSJ commented on June 11, 2024

大佬,严格安装您的环境要求重试了一遍,跑通了,之前使用的是高版本pytorch和transformers,出现了这个问题,应该就是环境不兼容的问题,感谢大佬!

from pytorch_bert_bilstm_crf_ner.

QMSLWSJ avatar QMSLWSJ commented on June 11, 2024

前辈我在训练环节没有问题了,但是在predict预测部分,我将raw_txt修改为我的数据集,报错Expected tensor for argument #1 'indices' to have scalar type Long; but got torch.cuda.IntTensor instead (while checking arguments for embedding)。debug好像是Tensor数据类型的问题,但对于如何修改没有思路,请问您有什么好的见解吗?

from pytorch_bert_bilstm_crf_ner.

taishan1994 avatar taishan1994 commented on June 11, 2024

前辈我在训练环节没有问题了,但是在predict预测部分,我将raw_txt修改为我的数据集,报错Expected tensor for argument #1 'indices' to have scalar type Long; but got torch.cuda.IntTensor instead (while checking arguments for embedding)。debug好像是Tensor数据类型的问题,但对于如何修改没有思路,请问您有什么好的见解吗?

predict里面改一下:
attention_masks = torch.from_numpy(np.array(encode_dict['attention_mask'])).long().unsqueeze(0).to(device)

from pytorch_bert_bilstm_crf_ner.

yjj-ui avatar yjj-ui commented on June 11, 2024

大佬,严格安装您的环境要求重试了一遍,跑通了,之前使用的是高版本pytorch和transformers,出现了这个问题,应该就是环境不兼容的问题,感谢大佬!

您好,请问您都调整了什么版本可以说一下吗

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.