transformers/docs/source/en/model_doc/dinov2.md

DINOv2

Overview

The DINOv2 model was proposed in DINOv2: Learning Robust Visual Features without Supervision by Maxime Oquab, Timothée Darcet, Théo Moutakanni, Huy Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, Mahmoud Assran, Nicolas Ballas, Wojciech Galuba, Russell Howes, Po-Yao Huang, Shang-Wen Li, Ishan Misra, Michael Rabbat, Vasu Sharma, Gabriel Synnaeve, Hu Xu, Hervé Jegou, Julien Mairal, Patrick Labatut, Armand Joulin, Piotr Bojanowski. DINOv2 is an upgrade of DINO, a self-supervised method applied on Vision Transformers. This method enables all-purpose visual features, i.e., features that work across image distributions and tasks without finetuning.

The abstract from the paper is the following:

The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. These models could greatly simplify the use of images in any system by producing all-purpose visual features, i.e., features that work across image distributions and tasks without finetuning. This work shows that existing pretraining methods, especially self-supervised methods, can produce such features if trained on enough curated data from diverse sources. We revisit existing approaches and combine different techniques to scale our pretraining in terms of data and model size. Most of the technical contributions aim at accelerating and stabilizing the training at scale. In terms of data, we propose an automatic pipeline to build a dedicated, diverse, and curated image dataset instead of uncurated data, as typically done in the self-supervised literature. In terms of models, we train a ViT model (Dosovitskiy et al., 2020) with 1B parameters and distill it into a series of smaller models that surpass the best available all-purpose features, OpenCLIP (Ilharco et al., 2021) on most of the benchmarks at image and pixel levels.

This model was contributed by nielsr. The original code can be found here.

Usage tips

The model can be traced using torch.jit.trace which leverages JIT compilation to optimize the model making it faster to run. Note this still produces some mis-matched elements and the difference between the original model and the traced model is of the order of 1e-4.

import torch
from transformers import AutoImageProcessor, AutoModel
from PIL import Image
import requests

url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)

processor = AutoImageProcessor.from_pretrained('facebook/dinov2-base')
model = AutoModel.from_pretrained('facebook/dinov2-base')

inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)
last_hidden_states = outputs[0]

# We have to force return_dict=False for tracing
model.config.return_dict = False

with torch.no_grad():
    traced_model = torch.jit.trace(model, [inputs.pixel_values])
    traced_outputs = traced_model(inputs.pixel_values)

print((last_hidden_states - traced_outputs[0]).abs().max())

Resources

A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with DINOv2.

• Demo notebooks for DINOv2 can be found here. 🌎

• [Dinov2ForImageClassification] is supported by this example script and notebook.
• See also: Image classification task guide

If you're interested in submitting a resource to be included here, please feel free to open a Pull Request and we'll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.

Dinov2Config

autodoc Dinov2Config

Dinov2Model

autodoc Dinov2Model - forward

Dinov2ForImageClassification

autodoc Dinov2ForImageClassification - forward

FlaxDinov2Model

autodoc FlaxDinov2Model - call

FlaxDinov2ForImageClassification

autodoc FlaxDinov2ForImageClassification - call