vivit b 16x2

Providergoogle
Categoryvideo-classification
Licensemit
Downloads423
Stars0

Overview

ViViT-B/16x2 is a Video Vision Transformer designed for efficient video classification by treating video clips as sequences of spatio-temporal patches. Unlike traditional 2D CNNs that rely on heavy temporal pooling or 3D convolutions, this model leverages a transformer architecture to capture long-range dependencies across both space and time. For developers, this means superior performance in action recognition and event detection tasks where temporal context is critical. It integrates well into PyTorch or TensorFlow pipelines via Hugging Face, offering a scalable alternative to legacy video models. Compared to standard ViT, the 16x2 patch embedding optimizes the trade-off between computational overhead and granularity, making it suitable for deployment in video analysis pipelines where latency and accuracy must be balanced.

Highlights

  • Transformer-based architecture for high-accuracy video classification.
  • Efficient spatio-temporal patch embedding reduces compute overhead.
  • Ideal for action recognition and event detection use cases.
  • Easy integration via standard ML frameworks and libraries.
  • Permissive MIT license for flexible commercial deployment.

Usage

Install
# Install Hugging Face transformers
pip install transformers torch
SDK Usage
# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("google/vivit-b-16x2")
tokenizer = AutoTokenizer.from_pretrained("google/vivit-b-16x2")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance 
pip install -U huggingface_hub

CLI Download

Download the full repository

Download the full repository 
huggingface-cli download google/vivit-b-16x2

Download a single file to a local folder (e.g. config.json into ./dir)

Download a single file to a local folder (e.g. config.json into ./dir) 
huggingface-cli download google/vivit-b-16x2 config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('google/vivit-b-16x2')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://huggingface.co/google/vivit-b-16x2

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/google/vivit-b-16x2

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

Install Transformers 
pip install -U transformers torch

Load the model and run inference

Load the model and run inference 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('google/vivit-b-16x2')
tokenizer = AutoTokenizer.from_pretrained('google/vivit-b-16x2')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance 
pip install modelscope

CLI Download

Download the full repository

Download the full repository 
modelscope download --model google/vivit-b-16x2

Download a single file to a local folder (e.g. README.md into ./dir)

Download a single file to a local folder (e.g. README.md into ./dir) 
modelscope download --model google/vivit-b-16x2 README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('google/vivit-b-16x2')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://www.modelscope.cn/google/vivit-b-16x2.git

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/google/vivit-b-16x2.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

Install the ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

Load the model and run inference 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'google/vivit-b-16x2')

Full Documentation

来源: HuggingFace

---
license: "mit"
tags:

  • vision

  • video-classification

---

ViViT (Video Vision Transformer)

ViViT model as introduced in the paper ViViT: A Video Vision Transformer by Arnab et al. and first released in this repository.

Disclaimer: The team releasing ViViT did not write a model card for this model so this model card has been written by the Hugging Face team.

Model description

ViViT is an extension of the Vision Transformer (ViT) to video.

We refer to the paper for details.

Intended uses & limitations

The model is mostly meant to intended to be fine-tuned on a downstream task, like video classification. See the model hub to look for fine-tuned versions on a task that interests you.

How to use

For code examples, we refer to the documentation.

BibTeX entry and citation info

bibtex
@misc{arnab2021vivit,
      title={ViViT: A Video Vision Transformer}, 
      author={Anurag Arnab and Mostafa Dehghani and Georg Heigold and Chen Sun and Mario Lučić and Cordelia Schmid},
      year={2021},
      eprint={2103.15691},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
View official source
Join our Telegram