We implement a Zero-Shot Key Word Spotting on speechcommands_v2 using ImageBind. All rights to the ImageBind model go to the authors of ImageBind, and I do not claim rights to it.
The implementation is in the notebook KWS-Using-ImageBind.ipynb. First install pytorch 1.13+ and other 3rd party dependencies.
conda create --name imagebind python=3.9 -y
conda activate imagebind
pip install -r requirements.txtFor windows users, you might need to install soundfile for reading/writing audio files. (Thanks @congyue1977)
pip install soundfile
Extract and compare features across modalities (e.g. Image, Text and Audio).
import data
import torch
from models import imagebind_model
from models.imagebind_model import ModalityType
text_list=["A dog.", "A car", "A bird"]
image_paths=[".assets/dog_image.jpg", ".assets/car_image.jpg", ".assets/bird_image.jpg"]
audio_paths=[".assets/dog_audio.wav", ".assets/car_audio.wav", ".assets/bird_audio.wav"]
device = "cuda:0" if torch.cuda.is_available() else "cpu"
# Instantiate model
model = imagebind_model.imagebind_huge(pretrained=True)
model.eval()
model.to(device)
# Load data
inputs = {
ModalityType.TEXT: data.load_and_transform_text(text_list, device),
ModalityType.VISION: data.load_and_transform_vision_data(image_paths, device),
ModalityType.AUDIO: data.load_and_transform_audio_data(audio_paths, device),
}
with torch.no_grad():
embeddings = model(inputs)
print(
"Vision x Text: ",
torch.softmax(embeddings[ModalityType.VISION] @ embeddings[ModalityType.TEXT].T, dim=-1),
)
print(
"Audio x Text: ",
torch.softmax(embeddings[ModalityType.AUDIO] @ embeddings[ModalityType.TEXT].T, dim=-1),
)
print(
"Vision x Audio: ",
torch.softmax(embeddings[ModalityType.VISION] @ embeddings[ModalityType.AUDIO].T, dim=-1),
)
# Expected output:
#
# Vision x Text:
# tensor([[9.9761e-01, 2.3694e-03, 1.8612e-05],
# [3.3836e-05, 9.9994e-01, 2.4118e-05],
# [4.7997e-05, 1.3496e-02, 9.8646e-01]])
#
# Audio x Text:
# tensor([[1., 0., 0.],
# [0., 1., 0.],
# [0., 0., 1.]])
#
# Vision x Audio:
# tensor([[0.8070, 0.1088, 0.0842],
# [0.1036, 0.7884, 0.1079],
# [0.0018, 0.0022, 0.9960]])Please see the model card for details.
ImageBind code and model weights are released under the CC-BY-NC 4.0 license. See LICENSE for additional details.
See contributing and the code of conduct.
If you find this repository useful, please consider giving a star ⭐ and citation
@inproceedings{girdhar2023imagebind,
title={ImageBind: One Embedding Space To Bind Them All},
author={Girdhar, Rohit and El-Nouby, Alaaeldin and Liu, Zhuang
and Singh, Mannat and Alwala, Kalyan Vasudev and Joulin, Armand and Misra, Ishan},
booktitle={CVPR},
year={2023}
}