LanguageBind's picture
Update README.md
dd4bbe0 verified
metadata
license: mit

ใ€ICLR 2024 ๐Ÿ”ฅใ€‘LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

If you like our project, please give us a star โญ on GitHub for latest update.

๐Ÿ“ฐ News

  • [2024.01.27] ๐Ÿ‘€๐Ÿ‘€๐Ÿ‘€ Our MoE-LLaVA is released! A sparse model with 3B parameters outperformed the dense model with 7B parameters.
  • [2024.01.16] ๐Ÿ”ฅ๐Ÿ”ฅ๐Ÿ”ฅ Our LanguageBind has been accepted at ICLR 2024! We earn the score of 6(3)8(6)6(6)6(6) here.
  • [2023.12.15] ๐Ÿ’ช๐Ÿ’ช๐Ÿ’ช We expand the ๐Ÿ’ฅ๐Ÿ’ฅ๐Ÿ’ฅ VIDAL dataset and now have 10M video-text data. We launch LanguageBind_Video 1.5, checking our model zoo.
  • [2023.12.10] We expand the ๐Ÿ’ฅ๐Ÿ’ฅ๐Ÿ’ฅ VIDAL dataset and now have 10M depth and 10M thermal data. We are in the process of uploading thermal and depth data on Hugging Face and expect the whole process to last 1-2 months.
  • [2023.11.27] ๐Ÿ”ฅ๐Ÿ”ฅ๐Ÿ”ฅ We have updated our paper with emergency zero-shot results., checking our โœจ results.
  • [2023.11.26] ๐Ÿ’ฅ๐Ÿ’ฅ๐Ÿ’ฅ We have open-sourced all textual sources and corresponding YouTube IDs here.
  • [2023.11.26] ๐Ÿ“ฃ๐Ÿ“ฃ๐Ÿ“ฃ We have open-sourced fully fine-tuned Video & Audio, achieving improved performance once again, checking our model zoo.
  • [2023.11.22] We are about to release a fully fine-tuned version, and the HUGE version is currently undergoing training.
  • [2023.11.21] ๐Ÿ’ฅ We are releasing sample data in DATASETS.md so that individuals who are interested can further modify the code to train it on their own data.
  • [2023.11.20] ๐Ÿš€๐Ÿš€๐Ÿš€ Video-LLaVA builds a large visual-language model to achieve ๐ŸŽ‰SOTA performances based on LanguageBind encoders.
  • [2023.10.23] ๐ŸŽถ LanguageBind-Audio achieves ๐ŸŽ‰๐ŸŽ‰๐ŸŽ‰state-of-the-art (SOTA) performance on 5 datasets, checking our โœจ results!
  • [2023.10.14] ๐Ÿ˜ฑ Released a stronger LanguageBind-Video, checking our โœจ results! The video checkpoint have updated on Huggingface Model Hub!
  • [2023.10.10] We provide sample data, which can be found in assets, and emergency zero-shot usage is described.
  • [2023.10.07] The checkpoints are available on ๐Ÿค— Huggingface Model.
  • [2023.10.04] Code and demo are available now! Welcome to watch ๐Ÿ‘€ this repository for the latest updates.

๐Ÿ˜ฎ Highlights

๐Ÿ’ก High performance, but NO intermediate modality required

LanguageBind is a language-centric multimodal pretraining approach, taking the language as the bind across different modalities because the language modality is well-explored and contains rich semantics.

  • The following first figure shows the architecture of LanguageBind. LanguageBind can be easily extended to segmentation, detection tasks, and potentially to unlimited modalities.

โšก๏ธ A multimodal, fully aligned and voluminous dataset

We propose VIDAL-10M, 10 Million data with Video, Infrared, Depth, Audio and their corresponding Language, which greatly expands the data beyond visual modalities.

  • The second figure shows our proposed VIDAL-10M dataset, which includes five modalities: video, infrared, depth, audio, and language.

๐Ÿ”ฅ Multi-view enhanced description for training

We make multi-view enhancements to language. We produce multi-view description that combines meta-data, spatial, and temporal to greatly enhance the semantic information of the language. In addition we further enhance the language with ChatGPT to create a good semantic space for each modality aligned language.

๐Ÿค— Demo

  • Local demo. Highly recommend trying out our web demo, which incorporates all features currently supported by LanguageBind.
python gradio_app.py
  • Online demo. We provide the online demo in Huggingface Spaces. In this demo, you can calculate the similarity of modalities to language, such as audio-to-language, video-to-language, and depth-to-image.

๐Ÿ› ๏ธ Requirements and Installation

  • Python >= 3.8
  • Pytorch >= 1.13.1
  • CUDA Version >= 11.6
  • Install required packages:
git clone https://github.com/PKU-YuanGroup/LanguageBind
cd LanguageBind
pip install torch==1.13.1+cu116 torchvision==0.14.1+cu116 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu116
pip install -r requirements.txt

๐Ÿณ Model Zoo

The names in the table represent different encoder models. For example, LanguageBind/LanguageBind_Video_FT represents the fully fine-tuned version, while LanguageBind/LanguageBind_Video represents the LoRA-tuned version.

You can freely replace them in the recommended API usage. We recommend using the fully fine-tuned version, as it offers stronger performance.

VersionTuningModel sizeNum_framesHF LinkMSR-VTTDiDeMoActivityNetMSVD
LanguageBind_VideoLoRALarge8Link42.637.835.152.2
LanguageBind_Video_FTFull-tuningLarge8Link42.738.136.953.5
LanguageBind_Video_V1.5_FTFull-tuningLarge8Link42.839.738.454.1
LanguageBind_Video_V1.5_FTFull-tuningLarge12Coming soon
LanguageBind_Video_Huge_V1.5_FTFull-tuningHuge8Link44.839.941.053.7
LanguageBind_Video_Huge_V1.5_FTFull-tuningHuge12Coming soon

๐Ÿค– API

We open source all modalities preprocessing code. If you want to load the model (e.g. LanguageBind/LanguageBind_Thermal) from the model hub on Huggingface or on local, you can use the following code snippets!

Inference for Multi-modal Binding

We have provided some sample datasets in assets to quickly see how languagebind works.

import torch
from languagebind import LanguageBind, to_device, transform_dict, LanguageBindImageTokenizer

if __name__ == '__main__':
    device = 'cuda:0'
    device = torch.device(device)
    clip_type = {
        'video': 'LanguageBind_Video_FT',  # also LanguageBind_Video
        'audio': 'LanguageBind_Audio_FT',  # also LanguageBind_Audio
        'thermal': 'LanguageBind_Thermal',
        'image': 'LanguageBind_Image',
        'depth': 'LanguageBind_Depth',
    }

    model = LanguageBind(clip_type=clip_type, cache_dir='./cache_dir')
    model = model.to(device)
    model.eval()
    pretrained_ckpt = f'lb203/LanguageBind_Image'
    tokenizer = LanguageBindImageTokenizer.from_pretrained(pretrained_ckpt, cache_dir='./cache_dir/tokenizer_cache_dir')
    modality_transform = {c: transform_dict[c](model.modality_config[c]) for c in clip_type.keys()}

    image = ['assets/image/0.jpg', 'assets/image/1.jpg']
    audio = ['assets/audio/0.wav', 'assets/audio/1.wav']
    video = ['assets/video/0.mp4', 'assets/video/1.mp4']
    depth = ['assets/depth/0.png', 'assets/depth/1.png']
    thermal = ['assets/thermal/0.jpg', 'assets/thermal/1.jpg']
    language = ["Training a parakeet to climb up a ladder.", 'A lion climbing a tree to catch a monkey.']

    inputs = {
        'image': to_device(modality_transform['image'](image), device),
        'video': to_device(modality_transform['video'](video), device),
        'audio': to_device(modality_transform['audio'](audio), device),
        'depth': to_device(modality_transform['depth'](depth), device),
        'thermal': to_device(modality_transform['thermal'](thermal), device),
    }
    inputs['language'] = to_device(tokenizer(language, max_length=77, padding='max_length',
                                             truncation=True, return_tensors='pt'), device)

    with torch.no_grad():
        embeddings = model(inputs)

    print("Video x Text: \n",
          torch.softmax(embeddings['video'] @ embeddings['language'].T, dim=-1).detach().cpu().numpy())
    print("Image x Text: \n",
          torch.softmax(embeddings['image'] @ embeddings['language'].T, dim=-1).detach().cpu().numpy())
    print("Depth x Text: \n",
          torch.softmax(embeddings['depth'] @ embeddings['language'].T, dim=-1).detach().cpu().numpy())
    print("Audio x Text: \n",
          torch.softmax(embeddings['audio'] @ embeddings['language'].T, dim=-1).detach().cpu().numpy())
    print("Thermal x Text: \n",
          torch.softmax(embeddings['thermal'] @ embeddings['language'].T, dim=-1).detach().cpu().numpy())

Then returns the following result.

Video x Text: 
 [[9.9989331e-01 1.0667283e-04]
 [1.3255903e-03 9.9867439e-01]]
Image x Text: 
 [[9.9990666e-01 9.3292067e-05]
 [4.6132666e-08 1.0000000e+00]]
Depth x Text: 
 [[0.9954276  0.00457235]
 [0.12042473 0.8795753 ]]
Audio x Text: 
 [[0.97634876 0.02365119]
 [0.02917843 0.97082156]]
Thermal x Text: 
 [[0.9482511  0.0517489 ]
 [0.48746133 0.5125386 ]]

Emergency zero-shot

Since languagebind binds each modality together, we also found the emergency zero-shot. It's very simple to use.

print("Video x Audio: \n", torch.softmax(embeddings['video'] @ embeddings['audio'].T, dim=-1).detach().cpu().numpy())
print("Image x Depth: \n", torch.softmax(embeddings['image'] @ embeddings['depth'].T, dim=-1).detach().cpu().numpy())
print("Image x Thermal: \n", torch.softmax(embeddings['image'] @ embeddings['thermal'].T, dim=-1).detach().cpu().numpy())

Then, you will get:

Video x Audio: 
 [[1.0000000e+00 0.0000000e+00]
 [3.1150486e-32 1.0000000e+00]]
Image x Depth: 
 [[1. 0.]
 [0. 1.]]
Image x Thermal: 
 [[1. 0.]
 [0. 1.]]

Different branches for X-Language task

Additionally, LanguageBind can be disassembled into different branches to handle different tasks. Note that we do not train Image, which just initialize from OpenCLIP.

Thermal

import torch
from languagebind import LanguageBindThermal, LanguageBindThermalTokenizer, LanguageBindThermalProcessor

pretrained_ckpt = 'LanguageBind/LanguageBind_Thermal'
model = LanguageBindThermal.from_pretrained(pretrained_ckpt, cache_dir='./cache_dir')
tokenizer = LanguageBindThermalTokenizer.from_pretrained(pretrained_ckpt, cache_dir='./cache_dir')
thermal_process = LanguageBindThermalProcessor(model.config, tokenizer)

model.eval()
data = thermal_process([r"your/thermal.jpg"], ['your text'], return_tensors='pt')
with torch.no_grad():
    out = model(**data)

print(out.text_embeds @ out.image_embeds.T)

Depth

import torch
from languagebind import LanguageBindDepth, LanguageBindDepthTokenizer, LanguageBindDepthProcessor

pretrained_ckpt = 'LanguageBind/LanguageBind_Depth'
model = LanguageBindDepth.from_pretrained(pretrained_ckpt, cache_dir='./cache_dir')
tokenizer = LanguageBindDepthTokenizer.from_pretrained(pretrained_ckpt, cache_dir='./cache_dir')
depth_process = LanguageBindDepthProcessor(model.config, tokenizer)

model.eval()
data = depth_process([r"your/depth.png"], ['your text.'], return_tensors='pt')
with torch.no_grad():
    out = model(**data)

print(out.text_embeds @ out.image_embeds.T)

Video

import torch
from languagebind import LanguageBindVideo, LanguageBindVideoTokenizer, LanguageBindVideoProcessor

pretrained_ckpt = 'LanguageBind/LanguageBind_Video_FT'  # also 'LanguageBind/LanguageBind_Video'
model = LanguageBindVideo.from_pretrained(pretrained_ckpt, cache_dir='./cache_dir')
tokenizer = LanguageBindVideoTokenizer.from_pretrained(pretrained_ckpt, cache_dir='./cache_dir')
video_process = LanguageBindVideoProcessor(model.config, tokenizer)

model.eval()
data = video_process(["your/video.mp4"], ['your text.'], return_tensors='pt')
with torch.no_grad():
    out = model(**data)

print(out.text_embeds @ out.image_embeds.T)

Audio

import torch
from languagebind import LanguageBindAudio, LanguageBindAudioTokenizer, LanguageBindAudioProcessor

pretrained_ckpt = 'LanguageBind/LanguageBind_Audio_FT'  # also 'LanguageBind/LanguageBind_Audio'
model = LanguageBindAudio.from_pretrained(pretrained_ckpt, cache_dir='./cache_dir')
tokenizer = LanguageBindAudioTokenizer.from_pretrained(pretrained_ckpt, cache_dir='./cache_dir')
audio_process = LanguageBindAudioProcessor(model.config, tokenizer)

model.eval()
data = audio_process([r"your/audio.wav"], ['your audio.'], return_tensors='pt')
with torch.no_grad():
    out = model(**data)

print(out.text_embeds @ out.image_embeds.T)

Image

Note that our image encoder is the same as OpenCLIP. Not as fine-tuned as other modalities.

import torch
from languagebind import LanguageBindImage,  LanguageBindImageTokenizer,  LanguageBindImageProcessor

pretrained_ckpt = 'LanguageBind/LanguageBind_Image'
model = LanguageBindImage.from_pretrained(pretrained_ckpt, cache_dir='./cache_dir')
tokenizer = LanguageBindImageTokenizer.from_pretrained(pretrained_ckpt, cache_dir='./cache_dir')
image_process = LanguageBindImageProcessor(model.config, tokenizer)

model.eval()
data = image_process([r"your/image.jpg"], ['your text.'], return_tensors='pt')
with torch.no_grad():
    out = model(**data)

print(out.text_embeds @ out.image_embeds.T)

๐Ÿ’ฅ VIDAL-10M

The datasets is in DATASETS.md.

๐Ÿ—๏ธ Training & Validating

The training & validating instruction is in TRAIN_AND_VALIDATE.md.

๐Ÿ‘ Acknowledgement

  • OpenCLIP An open source pretraining framework.
  • CLIP4Clip An open source Video-Text retrieval framework.
  • sRGB-TIR An open source framework to generate infrared (thermal) images.
  • GLPN An open source framework to generate depth images.

๐Ÿ”’ License

  • The majority of this project is released under the MIT license as found in the LICENSE file.
  • The dataset of this project is released under the CC-BY-NC 4.0 license as found in the DATASET_LICENSE file.

โœ๏ธ Citation

If you find our paper and code useful in your research, please consider giving a star :star: and citation :pencil:.

@misc{zhu2023languagebind,
      title={LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment}, 
      author={Bin Zhu and Bin Lin and Munan Ning and Yang Yan and Jiaxi Cui and Wang HongFa and Yatian Pang and Wenhao Jiang and Junwu Zhang and Zongwei Li and Cai Wan Zhang and Zhifeng Li and Wei Liu and Li Yuan},
      year={2023},
      eprint={2310.01852},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

โœจ Star History

Star History

๐Ÿค Contributors