PKU-YuanGroup/LanguageBind

Issues

• AttributeError: 'NoneType' object has no attribute 'astype' in Depth processor

  #68 opened 2 months ago by SoyeonHH
  1

• ValueError: Input image size (112*1036) doesn't match model ([112, 1036]*[112, 1036]).

  #67 opened 2 months ago by JeffRody
  1

• 关于数据集的一些问题

  #57 opened 6 months ago by XiaoZong0
  1

• Does the model work in scenarios with missing modalities?

  #66 opened 3 months ago by naajeehxe
  2

• embedding arithmetic

  #65 opened 3 months ago by bakachan19
  0

• Combination of multiple modalities

  #38 opened a year ago by anthony-mendil
  7

• How to calculate similarity of Video to audio?

  #64 opened 4 months ago by Coooderr
  0

• token masking and contrastive learning

  #63 opened 4 months ago by ooochen-30
  0

• Can not find datasets for LanguageBind_Image？

  #62 opened 4 months ago by superwood
  0

• where is the code of LanguageBind_Image and how to train it?

  #61 opened 4 months ago by superwood
  0

• Embedding similarity

  #60 opened 5 months ago by akBear23
  0

• Any support for languages other than English?

  #59 opened 5 months ago by ragesh2000
  0

• Method of running evaluation on MSR-VTT dataset

  #58 opened 5 months ago by sartaki
  0

• Video-Language Pre-training hours

  #56 opened 7 months ago by msw6468
  0

• Are some of these models interchangeable?

  #55 opened 7 months ago by felmoreno1726
  0

• Pretraining on video dataset without lora.

  #54 opened 7 months ago by shihuai
  0

• Clarification questions about the framework

  #50 opened 9 months ago by felmoreno1726
  4

• Inquiry on Unimodal Fine-Tuning with Locked Image in LanguageBind

  #41 opened 8 months ago by hexinyi2101
  0

• Any plans to use Long-CLIP to extend text input token limit?

  #53 opened 8 months ago by lennartmoritz
  0

• Fine-tuneing LLM + LanguageBind?

  #42 opened 10 months ago by Crystalxd
  1

• Non-reproducible MSRVTT results - I get R@1 accuracy less than 1%

  #51 opened 9 months ago by lennartmoritz
  2

• gpu资源

  #47 opened 9 months ago by letaozhang
  1

• NameError: name 'get_audio_anno' is not defined

  #52 opened 8 months ago by noah003
  0

• where is LanguageBind_Image

  #46 opened 10 months ago by hd201708010401
  2

• 关于视频文本的训练问题

  #49 opened 9 months ago by Tunanzzz
  0

• How to load pt model trained according to Training LanguageBind step?

  #48 opened 9 months ago by haochange
  1

• Inconsistent running results of inference.py

  #45 opened 10 months ago by Jade999
  5

• confusion about VIDAL-10M video-text data

  #44 opened 10 months ago by wli333
  0

• The length of text that the text encoder can handle

  #40 opened a year ago by song-wensong
  1

• VIT-H model on other modality [Audio/Depth/Thermal]

  #39 opened a year ago by tikboaHIT
  1

• Audio-Language Alignment data for reproduction

  #36 opened a year ago by memoiry
  1

• Use of undefined functions during fine_tune with custom audio data

  #37 opened a year ago by okaybody10
  1

• Can you share the NYU-D dataset you used for evaluation, e.g. how to split the dataset?

  #29 opened a year ago by bf-yang
  2

• finetuning on a classification task

  #35 opened a year ago by Sravanthgithub
  0

• Vision encoder version

  #34 opened a year ago by JosephPai
  1

• What is the training configurations for full tuning?

  #32 opened a year ago by StanLei52
  4

• Congrats on Acceptance !!!

  #33 opened a year ago by SenmiaoORZ
  1

• batch inference

  #31 opened a year ago by doyikim1
  0

• What's the difference between LanguageBind and LLaVA-1.5

  #26 opened a year ago by OPilgrim
  2

• 视频特征的提取支持动态帧数吗，效果相对于8帧会有下降或者变差吗

  #27 opened a year ago by 1093842024
  1

• Why don't to share the parameters backbone between Image and Video?

  #28 opened a year ago by SCZwangxiao
  1

• how to load LanguageBind/LanguageBind_Video_Huge_V1.5_FT model

  #30 opened a year ago by valencebond
  1

• Add flash attention 2

  #19 opened a year ago by pphuc25
  7

• VIT-H model release

  #22 opened a year ago by tikboaHIT
  2

• How to Initialize the multi-modal encoders & training from scratch

  #25 opened a year ago by chen-yy20
  1

• where is the LanguageBind_Audio_FT in huggingface?

  #24 opened a year ago by kou35
  1

• about LanguageBind_Video_merge

  #23 opened a year ago by kou35
  1

• Hashtags and prompts?

  #21 opened a year ago by Kamino666
  4

• 用于特征提取对齐，选用输出为什么参数

  #20 opened a year ago by xiaohaochen0308
  1

• Can I change embeddings['image'].shape from 768 to 1024?

  #18 opened a year ago by dongfeicui
  1