Bert-Multi-Label-Text-Classification

Bert-Multi-Label-Text-Classification copied to clipboard

How to fix the problem 02/18/2022 14:31:08 - INFO - root - initializing callbacks 02/18/2022 14:31:08 - INFO - root - ***** Running training ***** 02/18/2022 14:31:08 - INFO -...

fx7056

tools.py里 我用cpu进行训练，n_gpu=‘’， def prepare_device(use_gpu): """ setup GPU device if available, move model into configured device # 如果n_gpu_use为数字，则使用range生成list # 如果输入的是一个list，则默认使用list[0]作为controller Example: use_gpu = '' : cpu use_gpu = '0': cuda:0 use_gpu...

ZouRuia

I have train almost 80thousand examples within 2000 labels，valid acc almost 92%，but test result all example prob is blew 0.01.

6

I have trained almost 80thousand examples within 2000 labels，valid acc almost 92%，but test result all example prob is blew 0.01. I have tried tranning examples to predict.

w279805299

如果阈值为0.5,我不太理解。因为样本是0和1，所以预测值也应该接近0和1，那么经过sigmod以后不都是应该大于0.5吗，是不是意味着某个样本将会属于所有类别

wl915634785

使用XLNET进行训练时，准确率只有0.5左右，您是否有这样的问题？ 请问这个项目的XLNET数据输入是否有问题？ When training with XLNET, the accuracy is only about 0.5, do you have such a problem? Is there any problem with the XLNET data input for this project?

feitboiling

感谢分享

2

大佬，首先非常感谢你分享代码，我用过后发现有一处小问题，在xlnet_processor.py代码的157行和163行，input_mask值为0表示这个位置是真实的Token，而1表示这是一个Padding的Token，您看看这是否不小心弄反了 input_mask = **[0]** * len(input_ids) input_mask = (**[1]** * padding_len) + input_mask

junyu-Luo

Bumps [urllib3](https://github.com/urllib3/urllib3) from 1.25.3 to 1.26.5. Release notes Sourced from urllib3's releases. 1.26.5 :warning: IMPORTANT: urllib3 v2.0 will drop support for Python 2: Read more in the v2.0 Roadmap Fixed...

dependabot[bot]

自定义数据集只能用pkl?我记得之前用过csv 近期再用发现提示让我用pkl

1

请问哪里更改使用csv格式数据集来训练？ 我找了好久没有发现可以改的地方呢 def read_data(cls, input_file,quotechar = None): """Reads a tab separated value file.""" if 'pkl' in str(input_file): #pkl 改 csv ?? lines = load_pickle(input_file) else: lines = input_file return lines...

hdyzhuxun

RuntimeError: The expanded size of the tensor (9068) must match the existing size (453400) at non-singleton dimension 1. Target sizes: [5, 9068]. Tensor sizes: [1, 453400]

1

`Traceback (most recent call last): File "run_bert.py", line 222, in main() File "run_bert.py", line 215, in main run_train(args) File "run_bert.py", line 120, in run_train trainer.train(train_data=train_dataloader, valid_data=valid_dataloader) File "C:\MyDrive\PythonWs\NextGenWs\harshitha\Bert\IonePatient-our model\pybert\train\trainer.py", line...

aby005

No GPU Detected

3

Hello everyone i am beginner in BERT and python, and managed to get this code running after some error fixes, but i had another one that i had no idea...

creepayou