vit base patch14 reg4 dinov2.lvd142m

提供商timm
分类image-feature-extraction
许可证apache-2.0
下载量2.0K
星标0

简介

这是一个基于 DINOv2 预训练权重的 ViT-Base 视觉模型，采用 14x14 的 Patch 分割。不同于传统的有监督模型，它通过自监督学习在海量数据上训练，能够提取出极强的通用图像特征。对于开发者而言，它相当于一个强大的“视觉编码器”，无需从零训练即可直接用于图像检索、语义分割或作为下游任务的特征提取层。上手难度低，可通过 timm 库快速调用，是替代传统 ResNet 或 CLIP 视觉端以提升特征表达能力的理想选择。

核心亮点

  • 自监督预训练，图像特征表达能力极强
  • 兼容 timm 库，一行代码快速加载部署
  • 适用于图像检索、聚类等无监督视觉任务
  • 无需标注数据即可实现高质量特征提取

使用方法

安装依赖
# 安装 Hugging Face transformers
pip install transformers torch
SDK 使用
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("timm/vit_base_patch14_reg4_dinov2.lvd142m")
tokenizer = AutoTokenizer.from_pretrained("timm/vit_base_patch14_reg4_dinov2.lvd142m")

Hugging Face 下载

我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 huggingface_hub：

操作指引 
pip install -U huggingface_hub

命令行下载

下载完整模型库

下载完整模型库 
huggingface-cli download timm/vit_base_patch14_reg4_dinov2.lvd142m

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例）

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例） 
huggingface-cli download timm/vit_base_patch14_reg4_dinov2.lvd142m config.json --local-dir ./dir

更多命令行下载选项，可参见官方文档

SDK 下载

SDK 下载 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('timm/vit_base_patch14_reg4_dinov2.lvd142m')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://huggingface.co/timm/vit_base_patch14_reg4_dinov2.lvd142m

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/timm/vit_base_patch14_reg4_dinov2.lvd142m

模型文件托管在 Hugging Face Hub，使用 HF CLI / SDK / Git 直接下载，不经过本站。

PyTorch / Transformers 使用

安装 Transformers

安装 Transformers 
pip install -U transformers torch

模型加载和推理

模型加载和推理 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('timm/vit_base_patch14_reg4_dinov2.lvd142m')
tokenizer = AutoTokenizer.from_pretrained('timm/vit_base_patch14_reg4_dinov2.lvd142m')

模型下载

我们推荐使用命令行或者 ModelScope SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 ModelScope：

操作指引 
pip install modelscope

命令行下载

下载完整模型库

下载完整模型库 
modelscope download --model timm/vit_base_patch14_reg4_dinov2.lvd142m

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例）

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例） 
modelscope download --model timm/vit_base_patch14_reg4_dinov2.lvd142m README.md --local_dir ./dir

更多更丰富的命令行下载选项，可参见具体文档

SDK 下载

SDK 下载 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('timm/vit_base_patch14_reg4_dinov2.lvd142m')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://www.modelscope.cn/timm/vit_base_patch14_reg4_dinov2.lvd142m.git

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/timm/vit_base_patch14_reg4_dinov2.lvd142m.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 快速开发

下载并安装 ModelScope library

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

模型加载和推理

模型加载和推理 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'timm/vit_base_patch14_reg4_dinov2.lvd142m')

完整文档

来源: HuggingFace

---
license: apache-2.0
library_name: timm
tags:

  • image-feature-extraction

  • timm

  • transformers

---

Model card for vit_base_patch14_reg4_dinov2.lvd142m

A Vision Transformer (ViT) image feature model with registers. Pretrained on LVD-142M with self-supervised DINOv2 method.

Model Details

  • Model Type: Image classification / feature backbone
  • Model Stats:
- Params (M): 86.6 - GMACs: 117.5 - Activations (M): 115.0 - Image size: 518 x 518
  • Papers:
- Vision Transformers Need Registers: https://arxiv.org/abs/2309.16588 - DINOv2: Learning Robust Visual Features without Supervision: https://arxiv.org/abs/2304.07193 - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
  • Original: https://github.com/facebookresearch/dinov2
  • Pretrain Dataset: LVD-142M

Model Usage

Image Classification

python
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))


model = timm.create_model('vit_base_patch14_reg4_dinov2.lvd142m', pretrained=True)
model = model.eval()


get model specific transforms (normalization, resize)

data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1


top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)

Image Embeddings

python
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))


model = timm.create_model(
    'vit_base_patch14_reg4_dinov2.lvd142m',
    pretrained=True,
    num_classes=0,  # remove classifier nn.Linear
)
model = model.eval()


get model specific transforms (normalization, resize)

data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor


or equivalently (without needing to set num_classes=0)


output = model.forward_features(transforms(img).unsqueeze(0))
output is unpooled, a (1, 1374, 768) shaped tensor


output = model.forward_head(output, pre_logits=True)
output is a (1, num_features) shaped tensor

Model Comparison

Explore the dataset and runtime metrics of this model in timm model results.

Citation

bibtex
@article{darcet2023vision,
  title={Vision Transformers Need Registers},
  author={Darcet, Timoth{'e}e and Oquab, Maxime and Mairal, Julien and Bojanowski, Piotr},
  journal={arXiv preprint arXiv:2309.16588},
  year={2023}
}
bibtex
@misc{oquab2023dinov2,
  title={DINOv2: Learning Robust Visual Features without Supervision},
  author={Oquab, Maxime and Darcet, Timothée and Moutakanni, Theo and Vo, Huy V. and Szafraniec, Marc and Khalidov, Vasil and Fernandez, Pierre and Haziza, Daniel and Massa, Francisco and El-Nouby, Alaaeldin and Howes, Russell and Huang, Po-Yao and Xu, Hu and Sharma, Vasu and Li, Shang-Wen and Galuba, Wojciech and Rabbat, Mike and Assran, Mido and Ballas, Nicolas and Synnaeve, Gabriel and Misra, Ishan and Jegou, Herve and Mairal, Julien and Labatut, Patrick and Joulin, Armand and Bojanowski, Piotr},
  journal={arXiv:2304.07193},
  year={2023}
}
bibtex
@article{dosovitskiy2020vit,
  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
  author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
  journal={ICLR},
  year={2021}
}
bibtex
@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
查看官方来源