DINOv2

DINOv2 is a vision foundation model that uses ViT as a feature extractor for multiple downstream tasks like image classification and depth estimation. It focuses on stabilizing and accelerating training through techniques like a faster memory-efficient attention, sequence packing, improved stochastic depth, Fully Sharded Data Parallel (FSDP), and model distillation.

You can find all the original DINOv2 checkpoints under the Dinov2 collection.

Click on the DINOv2 models in the right sidebar for more examples of how to apply DINOv2 to different vision tasks.

The example below demonstrates how to obtain an image embedding with Pipeline or the AutoModel class.

Pipeline

AutoModel

Quantization reduces the memory burden of large models by representing the weights in a lower precision. Refer to the Quantization overview for more available quantization backends.

The example below uses torchao to only quantize the weights to int4.

# pip install torchao
import requests
from transformers import TorchAoConfig, AutoImageProcessor, AutoModelForImageClassification
from torchao.quantization import Int4WeightOnlyConfig
from PIL import Image

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

processor = AutoImageProcessor.from_pretrained('facebook/dinov2-giant-imagenet1k-1-layer')

quant_config = Int4WeightOnlyConfig(group_size=128)
quantization_config = TorchAoConfig(quant_type=quant_config)

model = AutoModelForImageClassification.from_pretrained(
    'facebook/dinov2-giant-imagenet1k-1-layer',
    torch_dtype=torch.bfloat16,
    device_map="auto",
    quantization_config=quantization_config
)

inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits
predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])

Notes

Use torch.jit.trace to speedup inference. However, it will produce some mismatched elements. The difference between the original and traced model is 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())

Dinov2Config

class transformers.Dinov2Config

< source >

( hidden_size = 768 num_hidden_layers = 12 num_attention_heads = 12 mlp_ratio = 4 hidden_act = 'gelu' hidden_dropout_prob = 0.0 attention_probs_dropout_prob = 0.0 initializer_range = 0.02 layer_norm_eps = 1e-06 image_size = 224 patch_size = 14 num_channels = 3 qkv_bias = True layerscale_value = 1.0 drop_path_rate = 0.0 use_swiglu_ffn = False out_features = None out_indices = None apply_layernorm = True reshape_hidden_states = True use_mask_token = True **kwargs )

Parameters

hidden_size (int, optional, defaults to 768) — Dimensionality of the encoder layers and the pooler layer.
num_hidden_layers (int, optional, defaults to 12) — Number of hidden layers in the Transformer encoder.
num_attention_heads (int, optional, defaults to 12) — Number of attention heads for each attention layer in the Transformer encoder.
mlp_ratio (int, optional, defaults to 4) — Ratio of the hidden size of the MLPs relative to the hidden_size.
hidden_act (str or function, optional, defaults to "gelu") — The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "selu" and "gelu_new" are supported.
hidden_dropout_prob (float, optional, defaults to 0.0) — The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
attention_probs_dropout_prob (float, optional, defaults to 0.0) — The dropout ratio for the attention probabilities.
initializer_range (float, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
layer_norm_eps (float, optional, defaults to 1e-06) — The epsilon used by the layer normalization layers.
image_size (int, optional, defaults to 224) — The size (resolution) of each image.
patch_size (int, optional, defaults to 14) — The size (resolution) of each patch.
num_channels (int, optional, defaults to 3) — The number of input channels.
qkv_bias (bool, optional, defaults to True) — Whether to add a bias to the queries, keys and values.
layerscale_value (float, optional, defaults to 1.0) — Initial value to use for layer scale.
drop_path_rate (float, optional, defaults to 0.0) — Stochastic depth rate per sample (when applied in the main path of residual layers).
use_swiglu_ffn (bool, optional, defaults to False) — Whether to use the SwiGLU feedforward neural network.
out_features (List[str], optional) — If used as backbone, list of features to output. Can be any of "stem", "stage1", "stage2", etc. (depending on how many stages the model has). If unset and out_indices is set, will default to the corresponding stages. If unset and out_indices is unset, will default to the last stage. Must be in the same order as defined in the stage_names attribute.
out_indices (List[int], optional) — If used as backbone, list of indices of features to output. Can be any of 0, 1, 2, etc. (depending on how many stages the model has). If unset and out_features is set, will default to the corresponding stages. If unset and out_features is unset, will default to the last stage. Must be in the same order as defined in the stage_names attribute.
apply_layernorm (bool, optional, defaults to True) — Whether to apply layer normalization to the feature maps in case the model is used as backbone.
reshape_hidden_states (bool, optional, defaults to True) — Whether to reshape the feature maps to 4D tensors of shape (batch_size, hidden_size, height, width) in case the model is used as backbone. If False, the feature maps will be 3D tensors of shape (batch_size, seq_len, hidden_size).
use_mask_token (bool, optional, defaults to True) — Whether to use mask_token in embeddings.

This is the configuration class to store the configuration of a Dinov2Model. It is used to instantiate an Dinov2 model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the Dinov2 google/dinov2-base-patch16-224 architecture.

Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.

Example:

>>> from transformers import Dinov2Config, Dinov2Model

>>> # Initializing a Dinov2 dinov2-base-patch16-224 style configuration
>>> configuration = Dinov2Config()

>>> # Initializing a model (with random weights) from the dinov2-base-patch16-224 style configuration
>>> model = Dinov2Model(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config

Pytorch

Hide Pytorch content

Dinov2Model

class transformers.Dinov2Model

< source >

( config: Dinov2Config )

Parameters

config (Dinov2Config) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

The bare DINOv2 Model transformer outputting raw hidden-states without any specific head on top. This model is a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< source >

( pixel_values: typing.Optional[torch.Tensor] = None bool_masked_pos: typing.Optional[torch.Tensor] = None head_mask: typing.Optional[torch.Tensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.BaseModelOutputWithPooling or tuple(torch.FloatTensor)

Parameters

pixel_values (torch.FloatTensor of shape (batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using AutoImageProcessor. See BitImageProcessor.preprocess() for details.
bool_masked_pos (torch.BoolTensor of shape (batch_size, sequence_length)) — Boolean masked positions. Indicates which patches are masked (1) and which aren’t (0). Only relevant for pre-training.
head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.

Returns

transformers.modeling_outputs.BaseModelOutputWithPooling or tuple(torch.FloatTensor)

A transformers.modeling_outputs.BaseModelOutputWithPooling or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (Dinov2Config) and inputs.

last_hidden_state (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the model.
pooler_output (torch.FloatTensor of shape (batch_size, hidden_size)) — Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining.
hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.FloatTensor (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The Dinov2Model forward method, overrides the __call__ special method.

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Example:

>>> from transformers import AutoImageProcessor, Dinov2Model
>>> import torch
>>> from datasets import load_dataset

>>> dataset = load_dataset("huggingface/cats-image", trust_remote_code=True)
>>> image = dataset["test"]["image"][0]

>>> image_processor = AutoImageProcessor.from_pretrained("facebook/dinov2-base")
>>> model = Dinov2Model.from_pretrained("facebook/dinov2-base")

>>> inputs = image_processor(image, return_tensors="pt")

>>> with torch.no_grad():
...     outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 257, 768]

Dinov2ForImageClassification

class transformers.Dinov2ForImageClassification

< source >

( config: Dinov2Config )

Parameters

config (Dinov2Config) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

Dinov2 Model transformer with an image classification head on top (a linear layer on top of the final hidden state of the [CLS] token) e.g. for ImageNet.

This model is a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< source >

( pixel_values: typing.Optional[torch.Tensor] = None head_mask: typing.Optional[torch.Tensor] = None labels: typing.Optional[torch.Tensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.ImageClassifierOutput or tuple(torch.FloatTensor)

Parameters

pixel_values (torch.FloatTensor of shape (batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using AutoImageProcessor. See BitImageProcessor.preprocess() for details.
head_mask (torch.FloatTensor of shape (num_heads,) or (num_layers, num_heads), optional) — Mask to nullify selected heads of the self-attention modules. Mask values selected in [0, 1]:
- 1 indicates the head is not masked,
- 0 indicates the head is masked.
output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
labels (torch.LongTensor of shape (batch_size,), optional) — Labels for computing the image classification/regression loss. Indices should be in [0, ..., config.num_labels - 1]. If config.num_labels == 1 a regression loss is computed (Mean-Square loss), If config.num_labels > 1 a classification loss is computed (Cross-Entropy).

Returns

transformers.modeling_outputs.ImageClassifierOutput or tuple(torch.FloatTensor)

A transformers.modeling_outputs.ImageClassifierOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (Dinov2Config) and inputs.

loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Classification (or regression if config.num_labels==1) loss.
logits (torch.FloatTensor of shape (batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax).
hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.FloatTensor (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each stage) of shape (batch_size, sequence_length, hidden_size). Hidden-states (also called feature maps) of the model at the output of each stage.
attentions (tuple(torch.FloatTensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.FloatTensor (one for each layer) of shape (batch_size, num_heads, patch_size, sequence_length).

Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The Dinov2ForImageClassification forward method, overrides the __call__ special method.

Example:

>>> from transformers import AutoImageProcessor, Dinov2ForImageClassification
>>> import torch
>>> from datasets import load_dataset

>>> dataset = load_dataset("huggingface/cats-image", trust_remote_code=True)
>>> image = dataset["test"]["image"][0]

>>> image_processor = AutoImageProcessor.from_pretrained("facebook/dinov2-small-imagenet1k-1-layer")
>>> model = Dinov2ForImageClassification.from_pretrained("facebook/dinov2-small-imagenet1k-1-layer")

>>> inputs = image_processor(image, return_tensors="pt")

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> # model predicts one of the 1000 ImageNet classes
>>> predicted_label = logits.argmax(-1).item()
>>> print(model.config.id2label[predicted_label])
tabby, tabby cat

JAX

Hide JAX content

FlaxDinov2Model

class transformers.FlaxDinov2Model

< source >

( config: Dinov2Config input_shape = None seed: int = 0 dtype: dtype = <class 'jax.numpy.float32'> _do_init: bool = True **kwargs )

Parameters

config (Dinov2Config) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
dtype (jax.numpy.dtype, optional, defaults to jax.numpy.float32) — The data type of the computation. Can be one of jax.numpy.float32, jax.numpy.float16 (on GPUs) and jax.numpy.bfloat16 (on TPUs).

This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given dtype.

Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.

If you wish to change the dtype of the model parameters, see to_fp16() and to_bf16().

The bare Dinov2 Model transformer outputting raw hidden-states without any specific head on top.

This model inherits from FlaxPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading, saving and converting weights from PyTorch models)

This model is also a flax.linen.Module subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

call

< source >

( pixel_values params: dict = None dropout_rng: <function PRNGKey at 0x7fd375f65750> = None train: bool = False output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPooling or tuple(torch.FloatTensor)

Returns

transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPooling or tuple(torch.FloatTensor)

A transformers.modeling_flax_outputs.FlaxBaseModelOutputWithPooling or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (<class 'transformers.models.dinov2.configuration_dinov2.Dinov2Config'>) and inputs.

last_hidden_state (jnp.ndarray of shape (batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the model.
pooler_output (jnp.ndarray of shape (batch_size, hidden_size)) — Last layer hidden-state of the first token of the sequence (classification token) further processed by a Linear layer and a Tanh activation function. The Linear layer weights are trained from the next sentence prediction (classification) objective during pretraining.
hidden_states (tuple(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of jnp.ndarray (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The FlaxDinov2PreTrainedModel forward method, overrides the __call__ special method.

Examples:

>>> from transformers import AutoImageProcessor, FlaxDinov2Model
>>> from PIL import Image
>>> import requests

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

>>> image_processor = AutoImageProcessor.from_pretrained("facebook/dinov2-base")
>>> model = FlaxDinov2Model.from_pretrained("facebook/dinov2-base")

>>> inputs = image_processor(images=image, return_tensors="np")
>>> outputs = model(**inputs)
>>> last_hidden_states = outputs.last_hidden_state

FlaxDinov2ForImageClassification

class transformers.FlaxDinov2ForImageClassification

< source >

( config: Dinov2Config input_shape = None seed: int = 0 dtype: dtype = <class 'jax.numpy.float32'> _do_init: bool = True **kwargs )

Parameters

config (Dinov2Config) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.
dtype (jax.numpy.dtype, optional, defaults to jax.numpy.float32) — The data type of the computation. Can be one of jax.numpy.float32, jax.numpy.float16 (on GPUs) and jax.numpy.bfloat16 (on TPUs).

This can be used to enable mixed-precision training or half-precision inference on GPUs or TPUs. If specified all the computation will be performed with the given dtype.

Note that this only specifies the dtype of the computation and does not influence the dtype of model parameters.

If you wish to change the dtype of the model parameters, see to_fp16() and to_bf16().

Dinov2 Model transformer with an image classification head on top (a linear layer on top of the final hidden state of the [CLS] token) e.g. for ImageNet.

This model is also a flax.linen.Module subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

call

< source >

( pixel_values params: dict = None dropout_rng: <function PRNGKey at 0x7fd375f65750> = None train: bool = False output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_flax_outputs.FlaxSequenceClassifierOutput or tuple(torch.FloatTensor)

Returns

transformers.modeling_flax_outputs.FlaxSequenceClassifierOutput or tuple(torch.FloatTensor)

A transformers.modeling_flax_outputs.FlaxSequenceClassifierOutput or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (<class 'transformers.models.dinov2.configuration_dinov2.Dinov2Config'>) and inputs.

logits (jnp.ndarray of shape (batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax).
hidden_states (tuple(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of jnp.ndarray (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size).

Hidden-states of the model at the output of each layer plus the initial embedding outputs.
attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of jnp.ndarray (one for each layer) of shape (batch_size, num_heads, sequence_length, sequence_length).

Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The FlaxDinov2PreTrainedModel forward method, overrides the __call__ special method.

Example:

>>> from transformers import AutoImageProcessor, FlaxDinov2ForImageClassification
>>> from PIL import Image
>>> import jax
>>> import requests

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

>>> image_processor = AutoImageProcessor.from_pretrained("facebook/dinov2-base-imagenet1k-1-layer")
>>> model = FlaxDinov2ForImageClassification.from_pretrained("facebook/dinov2-base-imagenet1k-1-layer", from_pt=True)

>>> inputs = image_processor(images=image, return_tensors="np")
>>> outputs = model(**inputs)
>>> logits = outputs.logits

>>> # model predicts one of the 1000 ImageNet classes
>>> predicted_class_idx = jax.numpy.argmax(logits, axis=-1)
>>> print("Predicted class:", model.config.id2label[predicted_class_idx.item()])

< > Update on GitHub

Transformers

DINOv2

Notes

Dinov2Config

class transformers.Dinov2Config

Dinov2Model

class transformers.Dinov2Model

forward

Dinov2ForImageClassification

class transformers.Dinov2ForImageClassification

forward

FlaxDinov2Model

class transformers.FlaxDinov2Model

__call__

FlaxDinov2ForImageClassification

class transformers.FlaxDinov2ForImageClassification

__call__

call

call