Transformers documentation

DeiT

Join the Hugging Face community

and get access to the augmented documentation experience

to get started

# DeiT

This is a recently introduced model so the API hasn’t been tested extensively. There may be some bugs or slight breaking changes to fix it in the future. If you see something strange, file a Github Issue.

## Overview

The DeiT model was proposed in Training data-efficient image transformers & distillation through attention by Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, Hervé Jégou. The Vision Transformer (ViT) introduced in Dosovitskiy et al., 2020 has shown that one can match or even outperform existing convolutional neural networks using a Transformer encoder (BERT-like). However, the ViT models introduced in that paper required training on expensive infrastructure for multiple weeks, using external data. DeiT (data-efficient image transformers) are more efficiently trained transformers for image classification, requiring far less data and far less computing resources compared to the original ViT models.

The abstract from the paper is the following:

Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. However, these visual transformers are pre-trained with hundreds of millions of images using an expensive infrastructure, thereby limiting their adoption. In this work, we produce a competitive convolution-free transformer by training on Imagenet only. We train them on a single computer in less than 3 days. Our reference vision transformer (86M parameters) achieves top-1 accuracy of 83.1% (single-crop evaluation) on ImageNet with no external data. More importantly, we introduce a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention. We show the interest of this token-based distillation, especially when using a convnet as a teacher. This leads us to report results competitive with convnets for both Imagenet (where we obtain up to 85.2% accuracy) and when transferring to other tasks. We share our code and models.

Tips:

• Compared to ViT, DeiT models use a so-called distillation token to effectively learn from a teacher (which, in the DeiT paper, is a ResNet like-model). The distillation token is learned through backpropagation, by interacting with the class ([CLS]) and patch tokens through the self-attention layers.
• There are 2 ways to fine-tune distilled models, either (1) in a classic way, by only placing a prediction head on top of the final hidden state of the class token and not using the distillation signal, or (2) by placing both a prediction head on top of the class token and on top of the distillation token. In that case, the [CLS] prediction head is trained using regular cross-entropy between the prediction of the head and the ground-truth label, while the distillation prediction head is trained using hard distillation (cross-entropy between the prediction of the distillation head and the label predicted by the teacher). At inference time, one takes the average prediction between both heads as final prediction. (2) is also called “fine-tuning with distillation”, because one relies on a teacher that has already been fine-tuned on the downstream dataset. In terms of models, (1) corresponds to DeiTForImageClassification and (2) corresponds to DeiTForImageClassificationWithTeacher.
• Note that the authors also did try soft distillation for (2) (in which case the distillation prediction head is trained using KL divergence to match the softmax output of the teacher), but hard distillation gave the best results.
• All released checkpoints were pre-trained and fine-tuned on ImageNet-1k only. No external data was used. This is in contrast with the original ViT model, which used external data like the JFT-300M dataset/Imagenet-21k for pre-training.
• The authors of DeiT also released more efficiently trained ViT models, which you can directly plug into ViTModel or ViTForImageClassification. Techniques like data augmentation, optimization, and regularization were used in order to simulate training on a much larger dataset (while only using ImageNet-1k for pre-training). There are 4 variants available (in 3 different sizes): facebook/deit-tiny-patch16-224, facebook/deit-small-patch16-224, facebook/deit-base-patch16-224 and facebook/deit-base-patch16-384. Note that one should use DeiTFeatureExtractor in order to prepare images for the model.

This model was contributed by nielsr. The TensorFlow version of this model was added by amyeroberts.

## DeiTConfig

### class transformers.DeiTConfig

< >

( hidden_size = 768 num_hidden_layers = 12 num_attention_heads = 12 intermediate_size = 3072 hidden_act = 'gelu' hidden_dropout_prob = 0.0 attention_probs_dropout_prob = 0.0 initializer_range = 0.02 layer_norm_eps = 1e-12 is_encoder_decoder = False image_size = 224 patch_size = 16 num_channels = 3 qkv_bias = True encoder_stride = 16 **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.
• intermediate_size (int, optional, defaults to 3072) — Dimensionality of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder.
• 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 0.1) — The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
• attention_probs_dropout_prob (float, optional, defaults to 0.1) — 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-12) — 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 16) — 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.
• encoder_stride (int, optional, defaults to 16) — Factor to increase the spatial resolution by in the decoder head for masked image modeling.

This is the configuration class to store the configuration of a DeiTModel. It is used to instantiate an DeiT 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 DeiT facebook/deit-base-distilled-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 DeiTModel, DeiTConfig

>>> # Initializing a DeiT deit-base-distilled-patch16-224 style configuration
>>> configuration = DeiTConfig()

>>> # Initializing a model from the deit-base-distilled-patch16-224 style configuration
>>> model = DeiTModel(configuration)

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

## DeiTFeatureExtractor

### class transformers.DeiTFeatureExtractor

< >

( do_resize = True size = 256 resample = <Resampling.BICUBIC: 3> do_center_crop = True crop_size = 224 do_normalize = True image_mean = None image_std = None **kwargs )

Parameters

• do_resize (bool, optional, defaults to True) — Whether to resize the input to a certain size.
• size (int or Tuple(int), optional, defaults to 256) — Resize the input to the given size. If a tuple is provided, it should be (width, height). If only an integer is provided, then the input will be resized to (size, size). Only has an effect if do_resize is set to True.
• resample (int, optional, defaults to PIL.Image.BICUBIC) — An optional resampling filter. This can be one of PIL.Image.NEAREST, PIL.Image.BOX, PIL.Image.BILINEAR, PIL.Image.HAMMING, PIL.Image.BICUBIC or PIL.Image.LANCZOS. Only has an effect if do_resize is set to True.
• do_center_crop (bool, optional, defaults to True) — Whether to crop the input at the center. If the input size is smaller than crop_size along any edge, the image is padded with 0’s and then center cropped.
• crop_size (int, optional, defaults to 224) — Desired output size when applying center-cropping. Only has an effect if do_center_crop is set to True.
• do_normalize (bool, optional, defaults to True) — Whether or not to normalize the input with image_mean and image_std.
• image_mean (List[int], defaults to [0.485, 0.456, 0.406]) — The sequence of means for each channel, to be used when normalizing images.
• image_std (List[int], defaults to [0.229, 0.224, 0.225]) — The sequence of standard deviations for each channel, to be used when normalizing images.

Constructs a DeiT feature extractor.

This feature extractor inherits from FeatureExtractionMixin which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.

#### __call__

< >

( images: typing.Union[PIL.Image.Image, numpy.ndarray, ForwardRef('torch.Tensor'), typing.List[PIL.Image.Image], typing.List[numpy.ndarray], typing.List[ForwardRef('torch.Tensor')]] return_tensors: typing.Union[str, transformers.utils.generic.TensorType, NoneType] = None **kwargs ) BatchFeature

Parameters

• images (PIL.Image.Image, np.ndarray, torch.Tensor, List[PIL.Image.Image], List[np.ndarray], List[torch.Tensor]) — The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a number of channels, H and W are image height and width.
• return_tensors (str or TensorType, optional, defaults to 'np') — If set, will return tensors of a particular framework. Acceptable values are:

• 'tf': Return TensorFlow tf.constant objects.
• 'pt': Return PyTorch torch.Tensor objects.
• 'np': Return NumPy np.ndarray objects.
• 'jax': Return JAX jnp.ndarray objects.

Returns

BatchFeature

A BatchFeature with the following fields:

• pixel_values — Pixel values to be fed to a model, of shape (batch_size, num_channels, height, width).

Main method to prepare for the model one or several image(s).

NumPy arrays and PyTorch tensors are converted to PIL images when resizing, so the most efficient is to pass PIL images.

## DeiTModel

### class transformers.DeiTModel

< >

( config: DeiTConfig add_pooling_layer: bool = True use_mask_token: bool = False )

Parameters

• config (DeiTConfig) — 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 DeiT 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

< >

( pixel_values: typing.Optional[torch.Tensor] = None bool_masked_pos: typing.Optional[torch.BoolTensor] = 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 DeiTFeatureExtractor. See DeiTFeatureExtractor.call() 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.

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 (DeiTConfig) 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 DeiTModel 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 DeiTFeatureExtractor, DeiTModel
>>> import torch
>>> from datasets import load_dataset

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

>>> feature_extractor = DeiTFeatureExtractor.from_pretrained("facebook/deit-base-distilled-patch16-224")
>>> model = DeiTModel.from_pretrained("facebook/deit-base-distilled-patch16-224")

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

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

>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 198, 768]

## DeiTForMaskedImageModeling

### class transformers.DeiTForMaskedImageModeling

< >

( config: DeiTConfig )

Parameters

• config (DeiTConfig) — 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.

DeiT Model with a decoder on top for masked image modeling, as proposed in SimMIM. 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

< >

( pixel_values: typing.Optional[torch.Tensor] = None bool_masked_pos: typing.Optional[torch.BoolTensor] = 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.MaskedLMOutput 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 DeiTFeatureExtractor. See DeiTFeatureExtractor.call() 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.
• bool_masked_pos (torch.BoolTensor of shape (batch_size, num_patches)) — Boolean masked positions. Indicates which patches are masked (1) and which aren’t (0).

Returns

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

A transformers.modeling_outputs.MaskedLMOutput 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 (DeiTConfig) and inputs.

• loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Masked language modeling (MLM) loss.

• logits (torch.FloatTensor of shape (batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head (scores for each vocabulary token 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 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 DeiTForMaskedImageModeling 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.

Examples:

>>> from transformers import DeiTFeatureExtractor, DeiTForMaskedImageModeling
>>> import torch
>>> from PIL import Image
>>> import requests

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

>>> feature_extractor = DeiTFeatureExtractor.from_pretrained("facebook/deit-base-distilled-patch16-224")
>>> model = DeiTForMaskedImageModeling.from_pretrained("facebook/deit-base-distilled-patch16-224")

>>> num_patches = (model.config.image_size // model.config.patch_size) ** 2
>>> pixel_values = feature_extractor(images=image, return_tensors="pt").pixel_values
>>> # create random boolean mask of shape (batch_size, num_patches)
>>> bool_masked_pos = torch.randint(low=0, high=2, size=(1, num_patches)).bool()

>>> outputs = model(pixel_values, bool_masked_pos=bool_masked_pos)
>>> loss, reconstructed_pixel_values = outputs.loss, outputs.logits
>>> list(reconstructed_pixel_values.shape)
[1, 3, 224, 224]

## DeiTForImageClassification

### class transformers.DeiTForImageClassification

< >

( config: DeiTConfig )

Parameters

• config (DeiTConfig) — 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.

DeiT 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

< >

( 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 DeiTFeatureExtractor. See DeiTFeatureExtractor.call() 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 (DeiTConfig) 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 DeiTForImageClassification 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.

Examples:

>>> from transformers import DeiTFeatureExtractor, DeiTForImageClassification
>>> import torch
>>> from PIL import Image
>>> import requests

>>> torch.manual_seed(3)
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)

>>> # note: we are loading a DeiTForImageClassificationWithTeacher from the hub here,
>>> # so the head will be randomly initialized, hence the predictions will be random
>>> feature_extractor = DeiTFeatureExtractor.from_pretrained("facebook/deit-base-distilled-patch16-224")
>>> model = DeiTForImageClassification.from_pretrained("facebook/deit-base-distilled-patch16-224")

>>> inputs = feature_extractor(images=image, return_tensors="pt")
>>> outputs = model(**inputs)
>>> logits = outputs.logits
>>> # model predicts one of the 1000 ImageNet classes
>>> predicted_class_idx = logits.argmax(-1).item()
>>> print("Predicted class:", model.config.id2label[predicted_class_idx])
Predicted class: maillot

## DeiTForImageClassificationWithTeacher

### class transformers.DeiTForImageClassificationWithTeacher

< >

( config: DeiTConfig )

Parameters

• config (DeiTConfig) — 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.

DeiT Model transformer with image classification heads on top (a linear layer on top of the final hidden state of the [CLS] token and a linear layer on top of the final hidden state of the distillation token) e.g. for ImageNet.

.. warning::

This model supports inference-only. Fine-tuning with distillation (i.e. with a teacher) is not yet supported.

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

< >

( pixel_values: 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.models.deit.modeling_deit.DeiTForImageClassificationWithTeacherOutput 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 DeiTFeatureExtractor. See DeiTFeatureExtractor.call() 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.

Returns

transformers.models.deit.modeling_deit.DeiTForImageClassificationWithTeacherOutput or tuple(torch.FloatTensor)

A transformers.models.deit.modeling_deit.DeiTForImageClassificationWithTeacherOutput 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 (DeiTConfig) and inputs.

• logits (torch.FloatTensor of shape (batch_size, config.num_labels)) — Prediction scores as the average of the cls_logits and distillation logits.
• cls_logits (torch.FloatTensor of shape (batch_size, config.num_labels)) — Prediction scores of the classification head (i.e. the linear layer on top of the final hidden state of the class token).
• distillation_logits (torch.FloatTensor of shape (batch_size, config.num_labels)) — Prediction scores of the distillation head (i.e. the linear layer on top of the final hidden state of the distillation token).
• 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 + 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(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 DeiTForImageClassificationWithTeacher 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 DeiTFeatureExtractor, DeiTForImageClassificationWithTeacher
>>> import torch
>>> from datasets import load_dataset

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

>>> feature_extractor = DeiTFeatureExtractor.from_pretrained("facebook/deit-base-distilled-patch16-224")
>>> model = DeiTForImageClassificationWithTeacher.from_pretrained("facebook/deit-base-distilled-patch16-224")

>>> inputs = feature_extractor(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

## TFDeiTModel

### class transformers.TFDeiTModel

< >

( *args **kwargs )

Parameters

• config (DeiTConfig) — 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 DeiT Model transformer outputting raw hidden-states without any specific head on top. This model is a TensorFlow tf.keras.layers.Layer. Use it as a regular TensorFlow Module and refer to the TensorFlow documentation for all matter related to general usage and behavior.

#### call

< >

( pixel_values: typing.Optional[tensorflow.python.framework.ops.Tensor] = None bool_masked_pos: typing.Optional[tensorflow.python.framework.ops.Tensor] = None head_mask: typing.Optional[tensorflow.python.framework.ops.Tensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None training: bool = False ) transformers.modeling_tf_outputs.TFBaseModelOutputWithPooling or tuple(tf.Tensor)

Parameters

• pixel_values (tf.Tensor of shape (batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using DeiTFeatureExtractor. See DeiTFeatureExtractor.call() for details.
• head_mask (tf.Tensor 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_tf_outputs.TFBaseModelOutputWithPooling or tuple(tf.Tensor)

A transformers.modeling_tf_outputs.TFBaseModelOutputWithPooling or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (DeiTConfig) and inputs.

• last_hidden_state (tf.Tensor of shape (batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the model.

• pooler_output (tf.Tensor 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.

This output is usually not a good summary of the semantic content of the input, you’re often better with averaging or pooling the sequence of hidden-states for the whole input sequence.

• hidden_states (tuple(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of tf.Tensor (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(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of tf.Tensor (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 TFDeiTModel 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 DeiTFeatureExtractor, TFDeiTModel
>>> from datasets import load_dataset

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

>>> feature_extractor = DeiTFeatureExtractor.from_pretrained("facebook/deit-base-distilled-patch16-224")
>>> model = TFDeiTModel.from_pretrained("facebook/deit-base-distilled-patch16-224")

>>> inputs = feature_extractor(image, return_tensors="tf")
>>> outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 198, 768]

## TFDeiTForMaskedImageModeling

### class transformers.TFDeiTForMaskedImageModeling

< >

( *args **kwargs )

Parameters

• config (DeiTConfig) — 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.

DeiT Model with a decoder on top for masked image modeling, as proposed in SimMIM. This model is a TensorFlow tf.keras.layers.Layer. Use it as a regular TensorFlow Module and refer to the TensorFlow documentation for all matter related to general usage and behavior.

#### call

< >

( pixel_values: typing.Optional[tensorflow.python.framework.ops.Tensor] = None bool_masked_pos: typing.Optional[tensorflow.python.framework.ops.Tensor] = None head_mask: typing.Optional[tensorflow.python.framework.ops.Tensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None training: bool = False ) transformers.modeling_tf_outputs.TFMaskedLMOutput or tuple(tf.Tensor)

Parameters

• pixel_values (tf.Tensor of shape (batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using DeiTFeatureExtractor. See DeiTFeatureExtractor.call() for details.
• head_mask (tf.Tensor 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.
• bool_masked_pos (tf.Tensor of type bool and shape (batch_size, num_patches)) — Boolean masked positions. Indicates which patches are masked (1) and which aren’t (0).

Returns

transformers.modeling_tf_outputs.TFMaskedLMOutput or tuple(tf.Tensor)

A transformers.modeling_tf_outputs.TFMaskedLMOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (DeiTConfig) and inputs.

• loss (tf.Tensor of shape (n,), optional, where n is the number of non-masked labels, returned when labels is provided) — Masked language modeling (MLM) loss.

• logits (tf.Tensor of shape (batch_size, sequence_length, config.vocab_size)) — Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).

• hidden_states (tuple(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of tf.Tensor (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(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of tf.Tensor (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 TFDeiTForMaskedImageModeling 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.

Examples:

>>> from transformers import DeiTFeatureExtractor, TFDeiTForMaskedImageModeling
>>> import tensorflow as tf
>>> from PIL import Image
>>> import requests

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

>>> feature_extractor = DeiTFeatureExtractor.from_pretrained("facebook/deit-base-distilled-patch16-224")
>>> model = TFDeiTForMaskedImageModeling.from_pretrained("facebook/deit-base-distilled-patch16-224")

>>> num_patches = (model.config.image_size // model.config.patch_size) ** 2
>>> pixel_values = feature_extractor(images=image, return_tensors="tf").pixel_values
>>> # create random boolean mask of shape (batch_size, num_patches)
>>> bool_masked_pos = tf.cast(tf.random.uniform((1, num_patches), minval=0, maxval=2, dtype=tf.int32), tf.bool)

>>> outputs = model(pixel_values, bool_masked_pos=bool_masked_pos)
>>> loss, reconstructed_pixel_values = outputs.loss, outputs.logits
>>> list(reconstructed_pixel_values.shape)
[1, 3, 224, 224]

## TFDeiTForImageClassification

### class transformers.TFDeiTForImageClassification

< >

( *args **kwargs )

Parameters

• config (DeiTConfig) — 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.

DeiT 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 TensorFlow tf.keras.layers.Layer. Use it as a regular TensorFlow Module and refer to the TensorFlow documentation for all matter related to general usage and behavior.

#### call

< >

( pixel_values: typing.Optional[tensorflow.python.framework.ops.Tensor] = None head_mask: typing.Optional[tensorflow.python.framework.ops.Tensor] = None labels: typing.Optional[tensorflow.python.framework.ops.Tensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None training: bool = False ) transformers.modeling_tf_outputs.TFImageClassifierOutput or tuple(tf.Tensor)

Parameters

• pixel_values (tf.Tensor of shape (batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using DeiTFeatureExtractor. See DeiTFeatureExtractor.call() for details.
• head_mask (tf.Tensor 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 (tf.Tensor 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_tf_outputs.TFImageClassifierOutput or tuple(tf.Tensor)

A transformers.modeling_tf_outputs.TFImageClassifierOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (DeiTConfig) and inputs.

• loss (tf.Tensor of shape (1,), optional, returned when labels is provided) — Classification (or regression if config.num_labels==1) loss.

• logits (tf.Tensor of shape (batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax).

• hidden_states (tuple(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of tf.Tensor (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(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of tf.Tensor (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 TFDeiTForImageClassification 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.

Examples:

>>> from transformers import DeiTFeatureExtractor, TFDeiTForImageClassification
>>> import tensorflow as tf
>>> from PIL import Image
>>> import requests

>>> tf.random.set_seed(3)
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)

>>> # note: we are loading a TFDeiTForImageClassificationWithTeacher from the hub here,
>>> # so the head will be randomly initialized, hence the predictions will be random
>>> feature_extractor = DeiTFeatureExtractor.from_pretrained("facebook/deit-base-distilled-patch16-224")
>>> model = TFDeiTForImageClassification.from_pretrained("facebook/deit-base-distilled-patch16-224")

>>> inputs = feature_extractor(images=image, return_tensors="tf")
>>> outputs = model(**inputs)
>>> logits = outputs.logits
>>> # model predicts one of the 1000 ImageNet classes
>>> predicted_class_idx = tf.math.argmax(logits, axis=-1)[0]
>>> print("Predicted class:", model.config.id2label[int(predicted_class_idx)])
Predicted class: ptarmigan

## TFDeiTForImageClassificationWithTeacher

### class transformers.TFDeiTForImageClassificationWithTeacher

< >

( *args **kwargs )

Parameters

• config (DeiTConfig) — 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.

DeiT Model transformer with image classification heads on top (a linear layer on top of the final hidden state of the [CLS] token and a linear layer on top of the final hidden state of the distillation token) e.g. for ImageNet.

.. warning::

This model supports inference-only. Fine-tuning with distillation (i.e. with a teacher) is not yet supported.

This model is a TensorFlow tf.keras.layers.Layer. Use it as a regular TensorFlow Module and refer to the TensorFlow documentation for all matter related to general usage and behavior.

#### call

< >

( pixel_values: typing.Optional[tensorflow.python.framework.ops.Tensor] = None head_mask: typing.Optional[tensorflow.python.framework.ops.Tensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None training: bool = False ) transformers.models.deit.modeling_tf_deit.TFDeiTForImageClassificationWithTeacherOutput or tuple(tf.Tensor)

Parameters

• pixel_values (tf.Tensor of shape (batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using DeiTFeatureExtractor. See DeiTFeatureExtractor.call() for details.
• head_mask (tf.Tensor 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.models.deit.modeling_tf_deit.TFDeiTForImageClassificationWithTeacherOutput or tuple(tf.Tensor)

A transformers.models.deit.modeling_tf_deit.TFDeiTForImageClassificationWithTeacherOutput or a tuple of tf.Tensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (DeiTConfig) and inputs.

• logits (tf.Tensor of shape (batch_size, config.num_labels)) — Prediction scores as the average of the cls_logits and distillation logits.
• cls_logits (tf.Tensor of shape (batch_size, config.num_labels)) — Prediction scores of the classification head (i.e. the linear layer on top of the final hidden state of the class token).
• distillation_logits (tf.Tensor of shape (batch_size, config.num_labels)) — Prediction scores of the distillation head (i.e. the linear layer on top of the final hidden state of the distillation token).
• hidden_states (tuple(tf.Tensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of tf.Tensor (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(tf.Tensor), optional, returned when output_attentions=True is passed or when config.output_attentions=True) — Tuple of tf.Tensor (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 TFDeiTForImageClassificationWithTeacher 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 DeiTFeatureExtractor, TFDeiTForImageClassificationWithTeacher
>>> import tensorflow as tf
>>> from datasets import load_dataset

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

>>> feature_extractor = DeiTFeatureExtractor.from_pretrained("facebook/deit-base-distilled-patch16-224")
>>> model = TFDeiTForImageClassificationWithTeacher.from_pretrained("facebook/deit-base-distilled-patch16-224")

>>> inputs = feature_extractor(image, return_tensors="tf")
>>> logits = model(**inputs).logits

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