Transformers documentation

Donut

Transformers

You are viewing v4.24.0 version. A newer version v4.47.1 is available.

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

Donut

Overview

The Donut model was proposed in OCR-free Document Understanding Transformer by Geewook Kim, Teakgyu Hong, Moonbin Yim, Jeongyeon Nam, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, Seunghyun Park. Donut consists of an image Transformer encoder and an autoregressive text Transformer decoder to perform document understanding tasks such as document image classification, form understanding and visual question answering.

The abstract from the paper is the following:

Understanding document images (e.g., invoices) is a core but challenging task since it requires complex functions such as reading text and a holistic understanding of the document. Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs. Although such OCR-based approaches have shown promising performance, they suffer from 1) high computational costs for using OCR; 2) inflexibility of OCR models on languages or types of document; 3) OCR error propagation to the subsequent process. To address these issues, in this paper, we introduce a novel OCR-free VDU model named Donut, which stands for Document understanding transformer. As the first step in OCR-free VDU research, we propose a simple architecture (i.e., Transformer) with a pre-training objective (i.e., cross-entropy loss). Donut is conceptually simple yet effective. Through extensive experiments and analyses, we show a simple OCR-free VDU model, Donut, achieves state-of-the-art performances on various VDU tasks in terms of both speed and accuracy. In addition, we offer a synthetic data generator that helps the model pre-training to be flexible in various languages and domains.

Donut high-level overview. Taken from the original paper.

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

Tips:

The quickest way to get started with Donut is by checking the tutorial notebooks, which show how to use the model at inference time as well as fine-tuning on custom data.
Donut is always used within the VisionEncoderDecoder framework.

Inference

Donut’s VisionEncoderDecoder model accepts images as input and makes use of generate() to autoregressively generate text given the input image.

The DonutFeatureExtractor class is responsible for preprocessing the input image and [XLMRobertaTokenizer/XLMRobertaTokenizerFast] decodes the generated target tokens to the target string. The DonutProcessor wraps DonutFeatureExtractor and [XLMRobertaTokenizer/XLMRobertaTokenizerFast] into a single instance to both extract the input features and decode the predicted token ids.

Step-by-step Document Image Classification

>>> import re

>>> from transformers import DonutProcessor, VisionEncoderDecoderModel
>>> from datasets import load_dataset
>>> import torch

>>> processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-rvlcdip")
>>> model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-rvlcdip")

>>> device = "cuda" if torch.cuda.is_available() else "cpu"
>>> model.to(device)
>>> # load document image
>>> dataset = load_dataset("hf-internal-testing/example-documents", split="test")
>>> image = dataset[1]["image"]

>>> # prepare decoder inputs
>>> task_prompt = "<s_rvlcdip>"
>>> decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids

>>> pixel_values = processor(image, return_tensors="pt").pixel_values

>>> outputs = model.generate(
...     pixel_values.to(device),
...     decoder_input_ids=decoder_input_ids.to(device),
...     max_length=model.decoder.config.max_position_embeddings,
...     early_stopping=True,
...     pad_token_id=processor.tokenizer.pad_token_id,
...     eos_token_id=processor.tokenizer.eos_token_id,
...     use_cache=True,
...     num_beams=1,
...     bad_words_ids=[[processor.tokenizer.unk_token_id]],
...     return_dict_in_generate=True,
... )

>>> sequence = processor.batch_decode(outputs.sequences)[0]
>>> sequence = sequence.replace(processor.tokenizer.eos_token, "").replace(processor.tokenizer.pad_token, "")
>>> sequence = re.sub(r"<.*?>", "", sequence, count=1).strip()  # remove first task start token
>>> print(processor.token2json(sequence))
{'class': 'advertisement'}

Step-by-step Document Parsing

>>> import re

>>> from transformers import DonutProcessor, VisionEncoderDecoderModel
>>> from datasets import load_dataset
>>> import torch

>>> processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")
>>> model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")

>>> device = "cuda" if torch.cuda.is_available() else "cpu"
>>> model.to(device)
>>> # load document image
>>> dataset = load_dataset("hf-internal-testing/example-documents", split="test")
>>> image = dataset[2]["image"]

>>> # prepare decoder inputs
>>> task_prompt = "<s_cord-v2>"
>>> decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids

>>> pixel_values = processor(image, return_tensors="pt").pixel_values

>>> outputs = model.generate(
...     pixel_values.to(device),
...     decoder_input_ids=decoder_input_ids.to(device),
...     max_length=model.decoder.config.max_position_embeddings,
...     early_stopping=True,
...     pad_token_id=processor.tokenizer.pad_token_id,
...     eos_token_id=processor.tokenizer.eos_token_id,
...     use_cache=True,
...     num_beams=1,
...     bad_words_ids=[[processor.tokenizer.unk_token_id]],
...     return_dict_in_generate=True,
... )

>>> sequence = processor.batch_decode(outputs.sequences)[0]
>>> sequence = sequence.replace(processor.tokenizer.eos_token, "").replace(processor.tokenizer.pad_token, "")
>>> sequence = re.sub(r"<.*?>", "", sequence, count=1).strip()  # remove first task start token
>>> print(processor.token2json(sequence))
{'menu': {'nm': 'CINNAMON SUGAR', 'unitprice': '17,000', 'cnt': '1 x', 'price': '17,000'}, 'sub_total': {'subtotal_price': '17,000'}, 'total': {'total_price': '17,000', 'cashprice': '20,000', 'changeprice': '3,000'}}

Step-by-step Document Visual Question Answering (DocVQA)

>>> import re

>>> from transformers import DonutProcessor, VisionEncoderDecoderModel
>>> from datasets import load_dataset
>>> import torch

>>> processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa")
>>> model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa")

>>> device = "cuda" if torch.cuda.is_available() else "cpu"
>>> model.to(device)
>>> # load document image from the DocVQA dataset
>>> dataset = load_dataset("hf-internal-testing/example-documents", split="test")
>>> image = dataset[0]["image"]

>>> # prepare decoder inputs
>>> task_prompt = "<s_docvqa><s_question>{user_input}</s_question><s_answer>"
>>> question = "When is the coffee break?"
>>> prompt = task_prompt.replace("{user_input}", question)
>>> decoder_input_ids = processor.tokenizer(prompt, add_special_tokens=False, return_tensors="pt").input_ids

>>> pixel_values = processor(image, return_tensors="pt").pixel_values

>>> outputs = model.generate(
...     pixel_values.to(device),
...     decoder_input_ids=decoder_input_ids.to(device),
...     max_length=model.decoder.config.max_position_embeddings,
...     early_stopping=True,
...     pad_token_id=processor.tokenizer.pad_token_id,
...     eos_token_id=processor.tokenizer.eos_token_id,
...     use_cache=True,
...     num_beams=1,
...     bad_words_ids=[[processor.tokenizer.unk_token_id]],
...     return_dict_in_generate=True,
... )

>>> sequence = processor.batch_decode(outputs.sequences)[0]
>>> sequence = sequence.replace(processor.tokenizer.eos_token, "").replace(processor.tokenizer.pad_token, "")
>>> sequence = re.sub(r"<.*?>", "", sequence, count=1).strip()  # remove first task start token
>>> print(processor.token2json(sequence))
{'question': 'When is the coffee break?', 'answer': '11-14 to 11:39 a.m.'}

See the model hub to look for Donut checkpoints.

Training

We refer to the tutorial notebooks.

DonutSwinConfig

class transformers.DonutSwinConfig

< source >

( image_size = 224 patch_size = 4 num_channels = 3 embed_dim = 96 depths = [2, 2, 6, 2] num_heads = [3, 6, 12, 24] window_size = 7 mlp_ratio = 4.0 qkv_bias = True hidden_dropout_prob = 0.0 attention_probs_dropout_prob = 0.0 drop_path_rate = 0.1 hidden_act = 'gelu' use_absolute_embeddings = False patch_norm = True initializer_range = 0.02 layer_norm_eps = 1e-05 **kwargs )

Parameters

image_size (int, optional, defaults to 224) — The size (resolution) of each image.
patch_size (int, optional, defaults to 4) — The size (resolution) of each patch.
num_channels (int, optional, defaults to 3) — The number of input channels.
embed_dim (int, optional, defaults to 96) — Dimensionality of patch embedding.
depths (list(int), optional, defaults to [2, 2, 6, 2]) — Depth of each layer in the Transformer encoder.
num_heads (list(int), optional, defaults to [3, 6, 12, 24]) — Number of attention heads in each layer of the Transformer encoder.
window_size (int, optional, defaults to 7) — Size of windows.
mlp_ratio (float, optional, defaults to 4.0) — Ratio of MLP hidden dimensionality to embedding dimensionality.
qkv_bias (bool, optional, defaults to True) — Whether or not a learnable bias should be added to the queries, keys and values.
hidden_dropout_prob (float, optional, defaults to 0.0) — The dropout probability for all fully connected layers in the embeddings and encoder.
attention_probs_dropout_prob (float, optional, defaults to 0.0) — The dropout ratio for the attention probabilities.
drop_path_rate (float, optional, defaults to 0.1) — Stochastic depth rate.
hidden_act (str or function, optional, defaults to "gelu") — The non-linear activation function (function or string) in the encoder. If string, "gelu", "relu", "selu" and "gelu_new" are supported.
use_absolute_embeddings (bool, optional, defaults to False) — Whether or not to add absolute position embeddings to the patch embeddings.
patch_norm (bool, optional, defaults to True) — Whether or not to add layer normalization after patch embedding.
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.

This is the configuration class to store the configuration of a DonutSwinModel. It is used to instantiate a Donut 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 Donut naver-clova-ix/donut-base 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 DonutSwinConfig, DonutSwinModel

>>> # Initializing a Donut naver-clova-ix/donut-base style configuration
>>> configuration = DonutSwinConfig()

>>> # Randomly initializing a model from the naver-clova-ix/donut-base style configuration
>>> model = DonutSwinModel(configuration)

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

DonutFeatureExtractor

class transformers.DonutFeatureExtractor

< source >

( do_resize = True size = [1920, 2560] resample = <Resampling.BILINEAR: 2> do_thumbnail = True do_align_long_axis = False do_pad = True do_normalize = True image_mean = None image_std = None **kwargs )

Parameters

do_resize (bool, optional, defaults to True) — Whether to resize the shorter edge of the input to the minimum value of a certain size.
size (Tuple(int), optional, defaults to [1920, 2560]) — Resize the shorter edge of the input to the minimum value of the given size. Should be a tuple of (width, height). Only has an effect if do_resize is set to True.
resample (int, optional, defaults to PIL.Image.Resampling.BILINEAR) — An optional resampling filter. This can be one of PIL.Image.Resampling.NEAREST, PIL.Image.Resampling.BOX, PIL.Image.Resampling.BILINEAR, PIL.Image.Resampling.HAMMING, PIL.Image.Resampling.BICUBIC or PIL.Image.Resampling.LANCZOS. Only has an effect if do_resize is set to True.
do_thumbnail (bool, optional, defaults to True) — Whether to thumbnail the input to the given size.
do_align_long_axis (bool, optional, defaults to False) — Whether to rotate the input if the height is greater than width.
do_pad (bool, optional, defaults to True) — Whether or not to pad the input to size.
do_normalize (bool, optional, defaults to True) — Whether or not to normalize the input with mean and standard deviation.
image_mean (List[int], defaults to [0.5, 0.5, 0.5]) — The sequence of means for each channel, to be used when normalizing images.
image_std (List[int], defaults to [0.5, 0.5, 0.5]) — The sequence of standard deviations for each channel, to be used when normalizing images.

Constructs a Donut 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

< source >

( images: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), typing.List[ForwardRef('PIL.Image.Image')], typing.List[numpy.ndarray], typing.List[ForwardRef('torch.Tensor')]] return_tensors: typing.Union[str, transformers.utils.generic.TensorType, NoneType] = None random_padding = False **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.
random_padding (bool, optional, defaults to False) — Whether to randomly pad the input to size.
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.

DonutProcessor

class transformers.DonutProcessor

< source >

( feature_extractor tokenizer )

Parameters

feature_extractor (DonutFeatureExtractor) — An instance of DonutFeatureExtractor. The feature extractor is a required input.
tokenizer ([XLMRobertaTokenizer/XLMRobertaTokenizerFast]) — An instance of [XLMRobertaTokenizer/XLMRobertaTokenizerFast]. The tokenizer is a required input.

Constructs a Donut processor which wraps a Donut feature extractor and an XLMRoBERTa tokenizer into a single processor.

DonutProcessor offers all the functionalities of DonutFeatureExtractor and [XLMRobertaTokenizer/XLMRobertaTokenizerFast]. See the call() and decode() for more information.

call

< source >

( *args **kwargs )

When used in normal mode, this method forwards all its arguments to AutoFeatureExtractor’s __call__() and returns its output. If used in the context as_target_processor() this method forwards all its arguments to DonutTokenizer’s ~DonutTokenizer.__call__. Please refer to the doctsring of the above two methods for more information.

from_pretrained

< source >

( pretrained_model_name_or_path **kwargs )

Parameters

pretrained_model_name_or_path (str or os.PathLike) — This can be either:
- a string, the model id of a pretrained feature_extractor hosted inside a model repo on huggingface.co. Valid model ids can be located at the root-level, like bert-base-uncased, or namespaced under a user or organization name, like dbmdz/bert-base-german-cased.
- a path to a directory containing a feature extractor file saved using the save_pretrained() method, e.g., ./my_model_directory/.
- a path or url to a saved feature extractor JSON file, e.g., ./my_model_directory/preprocessor_config.json. **kwargs — Additional keyword arguments passed along to both from_pretrained() and ~tokenization_utils_base.PreTrainedTokenizer.from_pretrained.

Instantiate a processor associated with a pretrained model.

This class method is simply calling the feature extractor from_pretrained() and the tokenizer ~tokenization_utils_base.PreTrainedTokenizer.from_pretrained methods. Please refer to the docstrings of the methods above for more information.

save_pretrained

< source >

( save_directory push_to_hub: bool = False **kwargs )

Parameters

save_directory (str or os.PathLike) — Directory where the feature extractor JSON file and the tokenizer files will be saved (directory will be created if it does not exist).
push_to_hub (bool, optional, defaults to False) — Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the repository you want to push to with repo_id (will default to the name of save_directory in your namespace). kwargs — Additional key word arguments passed along to the push_to_hub() method.

Saves the attributes of this processor (feature extractor, tokenizer…) in the specified directory so that it can be reloaded using the from_pretrained() method.

This class method is simply calling save_pretrained() and save_pretrained(). Please refer to the docstrings of the methods above for more information.

batch_decode

< source >

( *args **kwargs )

This method forwards all its arguments to DonutTokenizer’s batch_decode(). Please refer to the docstring of this method for more information.

decode

< source >

( *args **kwargs )

This method forwards all its arguments to DonutTokenizer’s decode(). Please refer to the docstring of this method for more information.

DonutSwinModel

class transformers.DonutSwinModel

< source >

( config add_pooling_layer = True use_mask_token = False )

Parameters

config (DonutSwinConfig) — 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 Donut Swin Model transformer outputting raw hidden-states without any specific head on top. This model is a PyTorch torch.nn.Module sub-class. 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.FloatTensor] = None bool_masked_pos: typing.Optional[torch.BoolTensor] = None head_mask: typing.Optional[torch.FloatTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.models.donut.modeling_donut_swin.DonutSwinModelOutput 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 AutoFeatureExtractor. See AutoFeatureExtractor.__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.donut.modeling_donut_swin.DonutSwinModelOutput or tuple(torch.FloatTensor)

A transformers.models.donut.modeling_donut_swin.DonutSwinModelOutput 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 (DonutSwinConfig) 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), optional, returned when add_pooling_layer=True is passed) — Average pooling of the last layer hidden-state.
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 stage) 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 stage) 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.
reshaped_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 stage) of shape (batch_size, hidden_size, height, width).

Hidden-states of the model at the output of each layer plus the initial embedding outputs reshaped to include the spatial dimensions.

The DonutSwinModel 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 AutoFeatureExtractor, DonutSwinModel
>>> import torch
>>> from datasets import load_dataset

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

>>> feature_extractor = AutoFeatureExtractor.from_pretrained("https://huggingface.co/naver-clova-ix/donut-base")
>>> model = DonutSwinModel.from_pretrained("https://huggingface.co/naver-clova-ix/donut-base")

>>> 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, 49, 768]

←Data2Vec FLAVA→