linwhitehat/ET-BERT

Issues

• 关于预训练的问题

  #62 opened a year ago by zyhxbz
  2

• 关于直接下载您处理好的cstnet-tls1.3数据集的疑问

  #68 opened 6 months ago by MiloGame
  4

• How to generate .tsv files

  #72 opened 6 months ago by aaminahassan
  2

• 语料库生成问题

  #82 opened 3 months ago by Chenxin2000
  0

• ET-BERT corpora lose

  #81 opened 3 months ago by goodgirl-prog
  0

• bugfix in main/data_process/dataset_cleaning.py

  #80 opened 3 months ago by feammer
  0

• Error in data processing in VPN dataset

  #79 opened 4 months ago by pb1069
  0

• uer utils中的misc.py问题

  #78 opened 4 months ago by vsvs5667
  0

• vocab_process/main.py 中缺少变量的全局定义

  #77 opened 4 months ago by feammer
  0

• 请问ET-BERT对于纯数据流能进行识别和分类吗

  #76 opened 4 months ago by alderpaw
  0

• 有关从pcap生成tsv文件遇到的问题

  #75 opened 5 months ago by plfnico
  1

• 微调数据预处理如何生成tsv文件的问题

  #58 opened 6 months ago by MiloGame
  3

• dataprogress

  #74 opened 6 months ago by 1195986182
  1

• 为什么采用bi-gram的形式，而不用tri-gram的形式

  #71 opened 6 months ago by Chenxin2000
  1

• Have you removed bidirectional IP and port information and protocol information to reduce the impact of packet headers? (e.g. remove 5-tuples)

  #70 opened 6 months ago by dbzzang-ping
  1

• CrossPlatForm数据集的问题

  #67 opened 6 months ago by WBSLZF
  1

• Data labeling?

  #65 opened 6 months ago by aaminahassan
  2

• 关于预训练和微调部分数据集来源一致的问题

  #57 opened 6 months ago by MiloGame
  1

• Categories in the ISCX VPN-NonVPN data

  #54 opened 6 months ago by satyandraguthula
  2

• 关于用于预训练的语料问题？

  #73 opened 6 months ago by AIIeinsein
  2

• 关于vocab_process的问题

  #69 opened 8 months ago by RicardoMLi
  0

• 有关数据清洗和数据预处理的问题

  #56 opened 9 months ago by MiloGame
  2

• 关于微调数据集把5000个samples都划分到同一类里的问题

  #59 opened 9 months ago by MiloGame
  2

• 直接下载的处理好的数据集进行微调时，发现缺失了一个关键文件

  #60 opened 9 months ago by MiloGame
  3

• VRAM needed for finetuning

  #63 opened a year ago by miqsoft
  2

• 关于微调后模型泛化能力的问题

  #66 opened a year ago by sdz614
  0

• how long to train?

  #64 opened a year ago by freebiesoft
  1

• 作者大大，请问dataset_cleanning.py里导入的ml_classifier模块怎么找不到

  #61 opened a year ago by zxxcjy123
  4

• 有关数据清洗和数据预处理的问题

  #55 opened a year ago by MiloGame
  1

• Malicious traffic definition

  #52 opened a year ago by Ziyan-22
  0

• 关于实际Flow level和packet Level方法的比较问题

  #51 opened a year ago by WBSLZF
  1

• null

  #53 opened a year ago by debugpro
  0

• data set update

  #50 opened a year ago by cookie1024
  2

• 数据清洗的问题

  #47 opened a year ago by WBSLZF
  4

• .3

  #49 opened a year ago by Szthing
  0

• ·

  #48 opened a year ago by Szthing
  0

• 求助

  #40 opened 2 years ago by Szthing
  4

• 关于预处理数据的问题

  #39 opened a year ago by JieJiemua
  4

• data preprocessing

  #46 opened a year ago by pemm-code
  3

• _pickle.UnpicklingError: invalid load key, '<'.

  #45 opened 2 years ago by HRH0517
  1

• 请问CSTNET-TLS 1.3数据集中的train_dataset.tsv训练数据集中的标签一共120，和下图并不对应，哪里有对应的label编号和标签解释呢

  #44 opened 2 years ago by CharlieUnderwood
  1

• 你好作者，能不能提供多一些的经过预处理的数据集！

  #37 opened 2 years ago by ctr555
  3

• 关于预训练的数据集

  #41 opened 2 years ago by wyx502
  4

• Dataset issues

  #43 opened 2 years ago by pemm-code
  1

• 您好，可以方便提供 ISCX-Tor、Cross-Platform(Android) 、Cross-Platform(iOS)的packet和flow级别的数据集

  #42 opened 2 years ago by Szthing
  1

• 模型效果差的问题

  #38 opened 2 years ago by lgbest123
  19

• 生成fine-tuning阶段数据部分时出现的问题

  #33 opened 2 years ago by WBSLZF
  6

• A Question about ISCX-Tor dataset

  #36 opened 2 years ago by network-traffic
  1

• 结果有差

  #34 opened 2 years ago by Szthing
  2

• 预处理数据

  #35 opened 2 years ago by JieJiemua
  0