# Donut [Donut (Document Understanding Transformer)](https://huggingface.co/papers/2111.15664) is a visual document understanding model that doesn't require an Optical Character Recognition (OCR) engine. Unlike traditional approaches that extract text using OCR before processing, Donut employs an end-to-end Transformer-based architecture to directly analyze document images. This eliminates OCR-related inefficiencies making it more accurate and adaptable to diverse languages and formats. Donut features vision encoder ([Swin](./swin)) and a text decoder ([BART](./bart)). Swin converts document images into embeddings and BART processes them into meaningful text sequences. You can find all the original Donut checkpoints under the [Naver Clova Information Extraction](https://huggingface.co/naver-clova-ix) organization. > [!TIP] > Click on the Donut models in the right sidebar for more examples of how to apply Donut to different language and vision tasks. The examples below demonstrate how to perform document understanding tasks using Donut with [Pipeline](/docs/transformers/v5.8.0/en/main_classes/pipelines#transformers.Pipeline) and [AutoModel](/docs/transformers/v5.8.0/en/model_doc/auto#transformers.AutoModel) ```python # pip install datasets from transformers import pipeline pipeline = pipeline( task="document-question-answering", model="naver-clova-ix/donut-base-finetuned-docvqa", device=0, ) dataset = load_dataset("hf-internal-testing/example-documents", split="test") image = dataset[0]["image"] pipeline(image=image, question="What time is the coffee break?") ``` ```python # pip install datasets from datasets import load_dataset from transformers import AutoModelForImageTextToText, AutoProcessor processor = AutoProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa") model = AutoModelForImageTextToText.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa", device_map="auto") dataset = load_dataset("hf-internal-testing/example-documents", split="test") image = dataset[0]["image"] question = "What time is the coffee break?" task_prompt = f"{question}" inputs = processor(image, task_prompt, return_tensors="pt").to(model.device) outputs = model.generate( input_ids=inputs.input_ids, pixel_values=inputs.pixel_values, max_length=512 ) answer = processor.decode(outputs[0], skip_special_tokens=True) print(answer) ``` Quantization reduces the memory burden of large models by representing the weights in a lower precision. Refer to the [Quantization](../quantization/overview) overview for more available quantization backends. The example below uses [torchao](../quantization/torchao) to only quantize the weights to int4. ```python # pip install datasets torchao from datasets import load_dataset from transformers import AutoModelForImageTextToText, AutoProcessor, TorchAoConfig quantization_config = TorchAoConfig("int4_weight_only", group_size=128) processor = AutoProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa") model = AutoModelForImageTextToText.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa", quantization_config=quantization_config, device_map="auto") dataset = load_dataset("hf-internal-testing/example-documents", split="test") image = dataset[0]["image"] question = "What time is the coffee break?" task_prompt = f"{question}" inputs = processor(image, task_prompt, return_tensors="pt").to(model.device) outputs = model.generate( input_ids=inputs.input_ids, pixel_values=inputs.pixel_values, max_length=512 ) answer = processor.decode(outputs[0], skip_special_tokens=True) print(answer) ``` ## Notes - Use Donut for document image classification as shown below. ```py 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_map="auto") model.to(model.device) # doctest: +IGNORE_RESULT # load document image dataset = load_dataset("hf-internal-testing/example-documents", split="test") image = dataset[1]["image"] # prepare decoder inputs task_prompt = "" decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").to(model.device).input_ids pixel_values = processor(image, return_tensors="pt").to(model.device).pixel_values outputs = model.generate( pixel_values.to(model.device), decoder_input_ids=decoder_input_ids.to(model.device), max_length=model.decoder.config.max_position_embeddings, pad_token_id=processor.tokenizer.pad_token_id, eos_token_id=processor.tokenizer.eos_token_id, use_cache=True, 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'} ``` - Use Donut for document parsing as shown below. ```py import re from datasets import load_dataset from transformers import DonutProcessor, VisionEncoderDecoderModel 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_map="auto") model.to(model.device) # doctest: +IGNORE_RESULT # load document image dataset = load_dataset("hf-internal-testing/example-documents", split="test") image = dataset[2]["image"] # prepare decoder inputs task_prompt = "" decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").to(model.device).input_ids pixel_values = processor(image, return_tensors="pt").to(model.device).pixel_values outputs = model.generate( pixel_values.to(model.device), decoder_input_ids=decoder_input_ids.to(model.device), max_length=model.decoder.config.max_position_embeddings, pad_token_id=processor.tokenizer.pad_token_id, eos_token_id=processor.tokenizer.eos_token_id, use_cache=True, 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'}} ``` ## DonutSwinConfig[[transformers.DonutSwinConfig]] #### transformers.DonutSwinConfig[[transformers.DonutSwinConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/donut/configuration_donut_swin.py#L24) This is the configuration class to store the configuration of a Donut SwinModel. It is used to instantiate a Donut Swin 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 [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.8.0/en/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> 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 ``` **Parameters:** image_size (`Union[int, list[int], tuple[int, int]]`, *optional*, defaults to `224`) : The size (resolution) of each image. patch_size (`Union[int, list[int], tuple[int, 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 the embeddings and hidden states. depths (`Union[list[int], tuple[int, ...]]`, *optional*, defaults to `(2, 2, 6, 2)`) : Depth of each layer in the Transformer. num_heads (`Union[list[int], tuple[int, ...]]`, *optional*, defaults to `(3, 6, 12, 24)`) : Number of attention heads for each attention layer in the Transformer decoder. window_size (`int`, *optional*, defaults to 7) : Size of windows. mlp_ratio (`float`, *optional*, defaults to `4.0`) : Ratio of the MLP hidden dim to the embedding dim. qkv_bias (`bool`, *optional*, defaults to `True`) : Whether to add a bias to the queries, keys and values. hidden_dropout_prob (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`Union[float, int]`, *optional*, defaults to `0.0`) : The dropout ratio for the attention probabilities. drop_path_rate (`Union[float, int]`, *optional*, defaults to `0.1`) : Drop path rate for the patch fusion. hidden_act (`str`, *optional*, defaults to `gelu`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc. use_absolute_embeddings (`bool`, *optional*, defaults to `False`) : Whether to use absolute position embeddings. 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-05`) : The epsilon used by the layer normalization layers. ## DonutImageProcessor[[transformers.DonutImageProcessor]] #### transformers.DonutImageProcessor[[transformers.DonutImageProcessor]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/donut/image_processing_donut.py#L46) Constructs a image_processor_class image processor. preprocesstransformers.DonutImageProcessor.preprocesshttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/donut/image_processing_donut.py#L70[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']]"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.models.donut.image_processing_donut.DonutImageProcessorKwargs]"}]- **images** (`Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]`) -- Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. - **do_thumbnail** (`bool`, *kwargs*, *optional*, defaults to `self.do_thumbnail`) -- Whether to resize the image using thumbnail method. - **do_align_long_axis** (`bool`, *kwargs*, *optional*, defaults to `self.do_align_long_axis`) -- Whether to align the long axis of the image with the long axis of `size` by rotating by 90 degrees. - **return_tensors** (`str` or [TensorType](/docs/transformers/v5.8.0/en/internal/file_utils#transformers.TensorType), *optional*) -- Returns stacked tensors if set to `'pt'`, otherwise returns a list of tensors. - ****kwargs** ([ImagesKwargs](/docs/transformers/v5.8.0/en/main_classes/processors#transformers.ImagesKwargs), *optional*) -- Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments.0`~image_processing_base.BatchFeature`- **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. **Parameters:** do_thumbnail (`bool`, *kwargs*, *optional*, defaults to `self.do_thumbnail`) : Whether to resize the image using thumbnail method. do_align_long_axis (`bool`, *kwargs*, *optional*, defaults to `self.do_align_long_axis`) : Whether to align the long axis of the image with the long axis of `size` by rotating by 90 degrees. - ****kwargs** ([ImagesKwargs](/docs/transformers/v5.8.0/en/main_classes/processors#transformers.ImagesKwargs), *optional*) : Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments. **Returns:** ``~image_processing_base.BatchFeature`` - **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. ## DonutImageProcessorPil[[transformers.DonutImageProcessorPil]] #### transformers.DonutImageProcessorPil[[transformers.DonutImageProcessorPil]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/donut/image_processing_pil_donut.py#L46) Constructs a image_processor_class image processor. preprocesstransformers.DonutImageProcessorPil.preprocesshttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/donut/image_processing_pil_donut.py#L70[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']]"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.models.donut.image_processing_pil_donut.DonutImageProcessorKwargs]"}]- **images** (`Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]`) -- Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. - **do_thumbnail** (`bool`, *kwargs*, *optional*, defaults to `self.do_thumbnail`) -- Whether to resize the image using thumbnail method. - **do_align_long_axis** (`bool`, *kwargs*, *optional*, defaults to `self.do_align_long_axis`) -- Whether to align the long axis of the image with the long axis of `size` by rotating by 90 degrees. - **return_tensors** (`str` or [TensorType](/docs/transformers/v5.8.0/en/internal/file_utils#transformers.TensorType), *optional*) -- Returns stacked tensors if set to `'pt'`, otherwise returns a list of tensors. - ****kwargs** ([ImagesKwargs](/docs/transformers/v5.8.0/en/main_classes/processors#transformers.ImagesKwargs), *optional*) -- Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments.0`~image_processing_base.BatchFeature`- **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. **Parameters:** do_thumbnail (`bool`, *kwargs*, *optional*, defaults to `self.do_thumbnail`) : Whether to resize the image using thumbnail method. do_align_long_axis (`bool`, *kwargs*, *optional*, defaults to `self.do_align_long_axis`) : Whether to align the long axis of the image with the long axis of `size` by rotating by 90 degrees. - ****kwargs** ([ImagesKwargs](/docs/transformers/v5.8.0/en/main_classes/processors#transformers.ImagesKwargs), *optional*) : Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments. **Returns:** ``~image_processing_base.BatchFeature`` - **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. ## DonutProcessor[[transformers.DonutProcessor]] #### transformers.DonutProcessor[[transformers.DonutProcessor]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/donut/processing_donut.py#L34) Constructs a DonutProcessor which wraps a image processor and a tokenizer into a single processor. [DonutProcessor](/docs/transformers/v5.8.0/en/model_doc/donut#transformers.DonutProcessor) offers all the functionalities of `image_processor_class` and `tokenizer_class`. See the `~image_processor_class` and `~tokenizer_class` for more information. __call__transformers.DonutProcessor.__call__https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/donut/processing_donut.py#L38[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor'], NoneType] = None"}, {"name": "text", "val": ": str | list[str] | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.models.donut.processing_donut.DonutProcessorKwargs]"}]- **images** (`Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]`, *optional*) -- Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set `do_rescale=False`. - **text** (`Union[str, list[str]]`, *optional*) -- The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If you pass a pretokenized input, set `is_split_into_words=True` to avoid ambiguity with batched inputs. - **return_tensors** (`str` or [TensorType](/docs/transformers/v5.8.0/en/internal/file_utils#transformers.TensorType), *optional*) -- If set, will return tensors of a particular framework. Acceptable values are: - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return NumPy `np.ndarray` objects. - ****kwargs** ([ProcessingKwargs](/docs/transformers/v5.8.0/en/main_classes/processors#transformers.ProcessingKwargs), *optional*) -- Additional processing options for each modality (text, images, videos, audio). Model-specific parameters are listed above; see the TypedDict class for the complete list of supported arguments.0 **Parameters:** image_processor (`image_processor_class`) : The image processor is a required input. tokenizer (`tokenizer_class`) : The tokenizer is a required input. #### from_pretrained[[transformers.DonutProcessor.from_pretrained]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/processing_utils.py#L1380) Instantiate a processor associated with a pretrained model. This class method is simply calling the feature extractor [from_pretrained()](/docs/transformers/v5.8.0/en/main_classes/feature_extractor#transformers.FeatureExtractionMixin.from_pretrained), image processor [ImageProcessingMixin](/docs/transformers/v5.8.0/en/main_classes/image_processor#transformers.ImageProcessingMixin) and the tokenizer `~tokenization_utils_base.PreTrainedTokenizer.from_pretrained` methods. Please refer to the docstrings of the methods above for more information. **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. - a path to a *directory* containing a feature extractor file saved using the [save_pretrained()](/docs/transformers/v5.8.0/en/main_classes/feature_extractor#transformers.FeatureExtractionMixin.save_pretrained) method, e.g., `./my_model_directory/`. - a path 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()](/docs/transformers/v5.8.0/en/main_classes/feature_extractor#transformers.FeatureExtractionMixin.from_pretrained) and `~tokenization_utils_base.PreTrainedTokenizer.from_pretrained`. #### save_pretrained[[transformers.DonutProcessor.save_pretrained]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/processing_utils.py#L807) Saves the attributes of this processor (feature extractor, tokenizer...) in the specified directory so that it can be reloaded using the [from_pretrained()](/docs/transformers/v5.8.0/en/main_classes/processors#transformers.ProcessorMixin.from_pretrained) method. This class method is simply calling [save_pretrained()](/docs/transformers/v5.8.0/en/main_classes/feature_extractor#transformers.FeatureExtractionMixin.save_pretrained) and [save_pretrained()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.save_pretrained). Please refer to the docstrings of the methods above for more information. **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 (`dict[str, Any]`, *optional*) : Additional key word arguments passed along to the [push_to_hub()](/docs/transformers/v5.8.0/en/main_classes/model#transformers.utils.PushToHubMixin.push_to_hub) method. #### batch_decode[[transformers.DonutProcessor.batch_decode]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/processing_utils.py#L1617) This method forwards all its arguments to PreTrainedTokenizer's [batch_decode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.batch_decode). Please refer to the docstring of this method for more information. #### decode[[transformers.DonutProcessor.decode]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/processing_utils.py#L1626) This method forwards all its arguments to PreTrainedTokenizer's [decode()](/docs/transformers/v5.8.0/en/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.decode). Please refer to the docstring of this method for more information. ## DonutSwinModel[[transformers.DonutSwinModel]] #### transformers.DonutSwinModel[[transformers.DonutSwinModel]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/donut/modeling_donut_swin.py#L808) The bare Donut Swin Model outputting raw hidden-states without any specific head on top. This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#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. forwardtransformers.DonutSwinModel.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/donut/modeling_donut_swin.py#L832[{"name": "pixel_values", "val": ": torch.FloatTensor | None = None"}, {"name": "bool_masked_pos", "val": ": torch.BoolTensor | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "interpolate_pos_encoding", "val": ": bool = False"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **pixel_values** (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`, *optional*) -- The tensors corresponding to the input images. Pixel values can be obtained using [DonutImageProcessor](/docs/transformers/v5.8.0/en/model_doc/donut#transformers.DonutImageProcessor). See `DonutImageProcessor.__call__()` for details (`processor_class` uses [DonutImageProcessor](/docs/transformers/v5.8.0/en/model_doc/donut#transformers.DonutImageProcessor) for processing images). - **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). - **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. - **interpolate_pos_encoding** (`bool`, *optional*, defaults to `False`) -- Whether to interpolate the pre-trained position encodings. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0`DonutSwinModelOutput` or `tuple(torch.FloatTensor)`A `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](/docs/transformers/v5.8.0/en/model_doc/donut#transformers.DonutSwinConfig)) and inputs. The [DonutSwinModel](/docs/transformers/v5.8.0/en/model_doc/donut#transformers.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. - **last_hidden_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*, defaults to `None`) -- 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, 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. - **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. **Parameters:** config ([DonutSwinModel](/docs/transformers/v5.8.0/en/model_doc/donut#transformers.DonutSwinModel)) : 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()](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. add_pooling_layer (`bool`, *optional*, defaults to `True`) : Whether to add a pooling layer use_mask_token (`bool`, *optional*, defaults to `False`) : Whether to use a mask token for masked image modeling. **Returns:** ``DonutSwinModelOutput` or `tuple(torch.FloatTensor)`` A `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](/docs/transformers/v5.8.0/en/model_doc/donut#transformers.DonutSwinConfig)) and inputs. ## DonutSwinForImageClassification[[transformers.DonutSwinForImageClassification]] #### transformers.DonutSwinForImageClassification[[transformers.DonutSwinForImageClassification]] [Source](https://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/donut/modeling_donut_swin.py#L904) DonutSwin 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. Note that it's possible to fine-tune DonutSwin on higher resolution images than the ones it has been trained on, by setting `interpolate_pos_encoding` to `True` in the forward of the model. This will interpolate the pre-trained position embeddings to the higher resolution. This model inherits from [PreTrainedModel](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel). Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.) This model is also a PyTorch [torch.nn.Module](https://pytorch.org/docs/stable/nn.html#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. forwardtransformers.DonutSwinForImageClassification.forwardhttps://github.com/huggingface/transformers/blob/v5.8.0/src/transformers/models/donut/modeling_donut_swin.py#L919[{"name": "pixel_values", "val": ": torch.FloatTensor | None = None"}, {"name": "labels", "val": ": torch.LongTensor | None = None"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "interpolate_pos_encoding", "val": ": bool = False"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **pixel_values** (`torch.FloatTensor` of shape `(batch_size, num_channels, image_size, image_size)`, *optional*) -- The tensors corresponding to the input images. Pixel values can be obtained using [DonutImageProcessor](/docs/transformers/v5.8.0/en/model_doc/donut#transformers.DonutImageProcessor). See `DonutImageProcessor.__call__()` for details (`processor_class` uses [DonutImageProcessor](/docs/transformers/v5.8.0/en/model_doc/donut#transformers.DonutImageProcessor) for processing images). - **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). - **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. - **interpolate_pos_encoding** (`bool`, *optional*, defaults to `False`) -- Whether to interpolate the pre-trained position encodings. - **return_dict** (`bool`, *optional*) -- Whether or not to return a [ModelOutput](/docs/transformers/v5.8.0/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0`DonutSwinImageClassifierOutput` or `tuple(torch.FloatTensor)`A `DonutSwinImageClassifierOutput` 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](/docs/transformers/v5.8.0/en/model_doc/donut#transformers.DonutSwinConfig)) and inputs. The [DonutSwinForImageClassification](/docs/transformers/v5.8.0/en/model_doc/donut#transformers.DonutSwinForImageClassification) 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. - **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 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. - **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. Example: ```python >>> from transformers import AutoImageProcessor, DonutSwinForImageClassification >>> import torch >>> from datasets import load_dataset >>> dataset = load_dataset("huggingface/cats-image") >>> image = dataset["test"]["image"][0] >>> image_processor = AutoImageProcessor.from_pretrained("naver-clova-ix/donut-base") >>> model = DonutSwinForImageClassification.from_pretrained("naver-clova-ix/donut-base") >>> 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]) ... ``` **Parameters:** config ([DonutSwinForImageClassification](/docs/transformers/v5.8.0/en/model_doc/donut#transformers.DonutSwinForImageClassification)) : 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()](/docs/transformers/v5.8.0/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** ``DonutSwinImageClassifierOutput` or `tuple(torch.FloatTensor)`` A `DonutSwinImageClassifierOutput` 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](/docs/transformers/v5.8.0/en/model_doc/donut#transformers.DonutSwinConfig)) and inputs.