Hugging Face's logo

Transformers documentation

Swin2SR

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v5.3.0).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Swin2SR

개요

Swin2SR 모델은 Marcos V. Conde, Ui-Jin Choi, Maxime Burchi, Radu Timofte가 제안한 논문 Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration에서 소개되었습니다. Swin2SR은 SwinIR 모델을 개선하고자 Swin Transformer v2 레이어를 도입함으로써, 훈련 불안정성, 사전 훈련과 미세 조정 간의 해상도 차이, 그리고 데이터 의존성 문제를 완화시킵니다.

논문의 초록은 다음과 같습니다:

압축은 스트리밍 서비스, 가상 현실, 비디오 게임과 같은 대역폭이 제한된 시스템을 통해 이미지와 영상을 효율적으로 전송하고 저장하는 데 중요한 역할을 합니다. 하지만 압축은 필연적으로 원본 정보의 손실과 아티팩트를 초래하며, 이는 시각적 품질을 심각하게 저하시킬 수 있습니다. 이러한 이유로, 압축된 이미지의 품질 향상은 활발한 연구 주제가 되고 있습니다. 현재 대부분의 최첨단 이미지 복원 방법은 합성곱 신경망을 기반으로 하지만, SwinIR과 같은 트랜스포머 기반 방법들도 이 작업에서 인상적인 성능을 보여주고 있습니다. 이번 논문에서는 Swin Transformer V2를 사용해 SwinIR을 개선하여 이미지 초해상도 작업, 특히 압축된 입력 시나리오에서 성능을 향상시키고자 합니다. 이 방법을 통해 트랜스포머 비전 모델을 훈련할 때 발생하는 주요 문제들, 예를 들어 훈련 불안정성, 사전 훈련과 미세 조정 간 해상도 차이, 그리고 데이터 의존성을 해결할 수 있습니다. 우리는 JPEG 압축 아티팩트 제거, 이미지 초해상도(클래식 및 경량), 그리고 압축된 이미지 초해상도라는 세 가지 대표적인 작업에서 실험을 수행했습니다. 실험 결과, 우리의 방법인 Swin2SR은 SwinIR의 훈련 수렴성과 성능을 향상시킬 수 있으며, “AIM 2022 Challenge on Super-Resolution of Compressed Image and Video”에서 상위 5위 솔루션으로 선정되었습니다.

drawing Swin2SR 아키텍처. 원본 논문에서 발췌.

이 모델은 nielsr가 기여하였습니다. 원본 코드는 여기에서 확인할 수 있습니다.

리소스

Swin2SR demo notebook은 여기에서 확인할 수 있습니다.

SwinSR을 활용한 image super-resolution demo space는 여기에서 확인할 수 있습니다.

Swin2SRImageProcessor

class transformers.Swin2SRImageProcessor

< >

( **kwargs: typing_extensions.Unpack[transformers.models.swin2sr.image_processing_swin2sr.Swin2SRImageProcessorKwargs] )

Parameters

  • size_divisor (int, kwargs, optional, defaults to self.size_divisor) — The size to make the height and width divisible by when padding.
  • **kwargs (ImagesKwargs, optional) — Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments.

Constructs a Swin2SRImageProcessor image processor.

preprocess

< >

( images: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']] **kwargs: typing_extensions.Unpack[transformers.models.swin2sr.image_processing_swin2sr.Swin2SRImageProcessorKwargs] ) → ~image_processing_base.BatchFeature

Parameters

  • 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.
  • size_divisor (int, kwargs, optional, defaults to self.size_divisor) — The size to make the height and width divisible by when padding.
  • return_tensors (str or TensorType, optional) — Returns stacked tensors if set to 'pt', otherwise returns a list of tensors.
  • **kwargs (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.

Swin2SRConfig

class transformers.Swin2SRConfig

< >

( output_hidden_states: bool | None = False return_dict: bool | None = True dtype: typing.Union[str, ForwardRef('torch.dtype'), NoneType] = None chunk_size_feed_forward: int = 0 is_encoder_decoder: bool = False id2label: dict[int, str] | dict[str, str] | None = None label2id: dict[str, int] | dict[str, str] | None = None problem_type: typing.Optional[typing.Literal['regression', 'single_label_classification', 'multi_label_classification']] = None tokenizer_class: str | transformers.tokenization_utils_base.PreTrainedTokenizerBase | None = None image_size: int | list[int] | tuple[int, int] = 64 patch_size: int | list[int] | tuple[int, int] = 1 num_channels: int = 3 num_channels_out: int | None = None embed_dim: int = 180 depths: list[int] | tuple[int, ...] = (6, 6, 6, 6, 6, 6) num_heads: list[int] | tuple[int, ...] = (6, 6, 6, 6, 6, 6) window_size: int = 8 mlp_ratio: float = 2.0 qkv_bias: bool = True hidden_dropout_prob: float = 0.0 attention_probs_dropout_prob: float = 0.0 drop_path_rate: float = 0.1 hidden_act: str = 'gelu' use_absolute_embeddings: bool = False initializer_range: float = 0.02 layer_norm_eps: float = 1e-05 upscale: int = 2 img_range: float = 1.0 resi_connection: str = '1conv' upsampler: str = 'pixelshuffle' )

Parameters

  • output_hidden_states (bool, optional, defaults to False) — Whether or not the model should return all hidden-states.
  • return_dict (bool, optional, defaults to True) — Whether to return a ModelOutput (dataclass) instead of a plain tuple.
  • dtype (Union[str, torch.dtype], optional) — The chunk size of all feed forward layers in the residual attention blocks. A chunk size of 0 means that the feed forward layer is not chunked. A chunk size of n means that the feed forward layer processes n < sequence_length embeddings at a time. For more information on feed forward chunking, see How does Feed Forward Chunking work?.
  • chunk_size_feed_forward (int, optional, defaults to 0) — The dtype of the weights. This attribute can be used to initialize the model to a non-default dtype (which is normally float32) and thus allow for optimal storage allocation. For example, if the saved model is float16, ideally we want to load it back using the minimal amount of memory needed to load float16 weights.
  • is_encoder_decoder (bool, optional, defaults to False) — Whether the model is used as an encoder/decoder or not.
  • id2label (Union[dict[int, str], dict[str, str]], optional) — A map from index (for instance prediction index, or target index) to label.
  • label2id (Union[dict[str, int], dict[str, str]], optional) — A map from label to index for the model.
  • problem_type (Literal[regression, single_label_classification, multi_label_classification], optional) — Problem type for XxxForSequenceClassification models. Can be one of "regression", "single_label_classification" or "multi_label_classification".
  • tokenizer_class (Union[str, ~tokenization_utils_base.PreTrainedTokenizerBase], optional) — The class name of model’s tokenizer.
  • image_size (Union[int, list[int], tuple[int, int]], optional, defaults to 64) — The size (resolution) of each image.
  • patch_size (Union[int, list[int], tuple[int, int]], optional, defaults to 1) — The size (resolution) of each patch.
  • num_channels (int, optional, defaults to 3) — The number of input channels.
  • num_channels_out (int, optional, defaults to num_channels) — The number of output channels. If not set, it will be set to num_channels.
  • embed_dim (int, optional, defaults to 180) — Dimensionality of the embeddings and hidden states.
  • depths (list(int), optional, defaults to [6, 6, 6, 6, 6, 6]) — Depth of each layer in the Transformer encoder.
  • num_heads (list(int), optional, defaults to [6, 6, 6, 6, 6, 6]) — Number of attention heads in each layer of the Transformer encoder.
  • window_size (int, optional, defaults to 8) — Size of windows.
  • mlp_ratio (float, optional, defaults to 2.0) — 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 (float, optional, defaults to 0.0) — The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
  • attention_probs_dropout_prob (float, optional, defaults to 0.0) — The dropout ratio for the attention probabilities.
  • drop_path_rate (float, 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.
  • upscale (int, optional, defaults to 2) — The upscale factor for the image. 2/3/4/8 for image super resolution, 1 for denoising and compress artifact reduction
  • img_range (float, optional, defaults to 1.0) — The range of the values of the input image.
  • resi_connection (str, optional, defaults to "1conv") — The convolutional block to use before the residual connection in each stage.
  • upsampler (str, optional, defaults to "pixelshuffle") — The reconstruction reconstruction module. Can be ‘pixelshuffle’/‘pixelshuffledirect’/‘nearest+conv’/None.

This is the configuration class to store the configuration of a Swin2SRModel. It is used to instantiate a Swin2Sr 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 caidas/swin2sr-classicalsr-x2-64

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 Swin2SRConfig, Swin2SRModel

>>> # Initializing a Swin2SR caidas/swin2sr-classicalsr-x2-64 style configuration
>>> configuration = Swin2SRConfig()

>>> # Initializing a model (with random weights) from the caidas/swin2sr-classicalsr-x2-64 style configuration
>>> model = Swin2SRModel(configuration)

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

Swin2SRModel

class transformers.Swin2SRModel

< >

( config )

Parameters

  • config (Swin2SRModel) — 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 Swin2Sr Model outputting raw hidden-states without any specific head on top.

This model inherits from 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 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: FloatTensor output_attentions: bool | None = None output_hidden_states: bool | None = None return_dict: bool | None = None **kwargs ) → BaseModelOutput or tuple(torch.FloatTensor)

Parameters

  • pixel_values (torch.FloatTensor of shape (batch_size, num_channels, image_size, image_size)) — The tensors corresponding to the input images. Pixel values can be obtained using Swin2SRImageProcessor. See Swin2SRImageProcessor.__call__() for details (processor_class uses Swin2SRImageProcessor for processing images).
  • 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

BaseModelOutput or tuple(torch.FloatTensor)

A BaseModelOutput 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 (Swin2SRConfig) and inputs.

The Swin2SRModel 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)) — Sequence of hidden-states at the output of the last layer of the model.

  • 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.

Example:

Swin2SRForImageSuperResolution

class transformers.Swin2SRForImageSuperResolution

< >

( config )

Parameters

  • config (Swin2SRForImageSuperResolution) — 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.

Swin2SR Model transformer with an upsampler head on top for image super resolution and restoration.

This model inherits from 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 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: torch.FloatTensor | None = None labels: torch.LongTensor | None = None output_attentions: bool | None = None output_hidden_states: bool | None = None return_dict: bool | None = None **kwargs ) → ImageSuperResolutionOutput or tuple(torch.FloatTensor)

Parameters

  • 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 Swin2SRImageProcessor. See Swin2SRImageProcessor.__call__() for details (processor_class uses Swin2SRImageProcessor for processing images).
  • labels (torch.LongTensor of shape (batch_size, sequence_length), optional) — Labels for computing the masked language modeling loss. Indices should either be in [0, ..., config.vocab_size] or -100 (see input_ids docstring). Tokens with indices set to -100 are ignored (masked), the loss is only computed for the tokens with labels in [0, ..., config.vocab_size].
  • 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

ImageSuperResolutionOutput or tuple(torch.FloatTensor)

A ImageSuperResolutionOutput 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 (Swin2SRConfig) and inputs.

The Swin2SRForImageSuperResolution 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) — Reconstruction loss.

  • reconstruction (torch.FloatTensor of shape (batch_size, num_channels, height, width)) — Reconstructed images, possibly upscaled.

  • 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.

Example:

>>> import torch
>>> import numpy as np
>>> from PIL import Image
>>> import httpx
>> from io import BytesIO

>>> from transformers import AutoImageProcessor, Swin2SRForImageSuperResolution

>>> processor = AutoImageProcessor.from_pretrained("caidas/swin2SR-classical-sr-x2-64")
>>> model = Swin2SRForImageSuperResolution.from_pretrained("caidas/swin2SR-classical-sr-x2-64")

>>> url = "https://huggingface.co/spaces/jjourney1125/swin2sr/resolve/main/samples/butterfly.jpg"
>>> with httpx.stream("GET", url) as response:
...     image = Image.open(BytesIO(response.read()))
>>> # prepare image for the model
>>> inputs = processor(image, return_tensors="pt")

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

>>> output = outputs.reconstruction.data.squeeze().float().cpu().clamp_(0, 1).numpy()
>>> output = np.moveaxis(output, source=0, destination=-1)
>>> output = (output * 255.0).round().astype(np.uint8)  # float32 to uint8
>>> # you can visualize `output` with `Image.fromarray`
Update on GitHub

←Swin Transformer V2 Table Transformer→