# Swin2SR [[swin2sr]]

## 개요 [[overview]]

Swin2SR 모델은 Marcos V. Conde, Ui-Jin Choi, Maxime Burchi, Radu Timofte가 제안한 논문 [Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration](https://huggingface.co/papers/2209.11345)에서 소개되었습니다.
Swin2SR은 [SwinIR](https://github.com/JingyunLiang/SwinIR/) 모델을 개선하고자 [Swin Transformer v2](swinv2) 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.*

 Swin2SR 아키텍처. 원본 논문에서 발췌.

이 모델은 [nielsr](https://huggingface.co/nielsr)가 기여하였습니다.
원본 코드는 [여기](https://github.com/mv-lab/swin2sr)에서 확인할 수 있습니다.

## 리소스 [[resources]]

Swin2SR demo notebook은 [여기](https://github.com/NielsRogge/Transformers-Tutorials/tree/master/Swin2SR)에서 확인할 수 있습니다.

SwinSR을 활용한 image super-resolution demo space는 [여기](https://huggingface.co/spaces/jjourney1125/swin2sr)에서 확인할 수 있습니다.

## Swin2SRImageProcessor [[transformers.Swin2SRImageProcessor]][[transformers.Swin2SRImageProcessor]]

#### transformers.Swin2SRImageProcessor[[transformers.Swin2SRImageProcessor]]

[Source](https://github.com/huggingface/transformers/blob/v5.5.4/src/transformers/models/swin2sr/image_processing_swin2sr.py#L41)

Constructs a Swin2SRImageProcessor image processor.

preprocesstransformers.Swin2SRImageProcessor.preprocesshttps://github.com/huggingface/transformers/blob/v5.5.4/src/transformers/models/swin2sr/image_processing_swin2sr.py#L58[{"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.swin2sr.image_processing_swin2sr.Swin2SRImageProcessorKwargs]"}]- **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](/docs/transformers/v5.5.4/ko/internal/file_utils#transformers.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.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:**

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.

**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 [[transformers.Swin2SRConfig]][[transformers.Swin2SRConfig]]

#### transformers.Swin2SRConfig[[transformers.Swin2SRConfig]]

[Source](https://github.com/huggingface/transformers/blob/v5.5.4/src/transformers/models/swin2sr/configuration_swin2sr.py#L24)

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](https://huggingface.co/caidas/swin2sr-classicalsr-x2-64)

Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.5.4/ko/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the
documentation from [PreTrainedConfig](/docs/transformers/v5.5.4/ko/main_classes/configuration#transformers.PreTrainedConfig) for more information.

Example:

```python
>>> 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
```

**Parameters:**

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 (`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.

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.

## Swin2SRModel [[transformers.Swin2SRModel]][[transformers.Swin2SRModel]]

#### transformers.Swin2SRModel[[transformers.Swin2SRModel]]

[Source](https://github.com/huggingface/transformers/blob/v5.5.4/src/transformers/models/swin2sr/modeling_swin2sr.py#L721)

The bare Swin2Sr Model outputting raw hidden-states without any specific head on top.

This model inherits from [PreTrainedModel](/docs/transformers/v5.5.4/ko/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.Swin2SRModel.forwardhttps://github.com/huggingface/transformers/blob/v5.5.4/src/transformers/models/swin2sr/modeling_swin2sr.py#L763[{"name": "pixel_values", "val": ": FloatTensor"}, {"name": "output_attentions", "val": ": bool | None = None"}, {"name": "output_hidden_states", "val": ": bool | None = None"}, {"name": "return_dict", "val": ": bool | None = None"}, {"name": "**kwargs", "val": ""}]- **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](/docs/transformers/v5.5.4/ko/model_doc/swin2sr#transformers.Swin2SRImageProcessor). See `Swin2SRImageProcessor.__call__()` for details (`processor_class` uses
  [Swin2SRImageProcessor](/docs/transformers/v5.5.4/ko/model_doc/swin2sr#transformers.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](/docs/transformers/v5.5.4/ko/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0[BaseModelOutput](/docs/transformers/v5.5.4/ko/main_classes/output#transformers.modeling_outputs.BaseModelOutput) or `tuple(torch.FloatTensor)`A [BaseModelOutput](/docs/transformers/v5.5.4/ko/main_classes/output#transformers.modeling_outputs.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](/docs/transformers/v5.5.4/ko/model_doc/swin2sr#transformers.Swin2SRConfig)) and inputs.
The [Swin2SRModel](/docs/transformers/v5.5.4/ko/model_doc/swin2sr#transformers.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:

```python
```

**Parameters:**

config ([Swin2SRModel](/docs/transformers/v5.5.4/ko/model_doc/swin2sr#transformers.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()](/docs/transformers/v5.5.4/ko/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[BaseModelOutput](/docs/transformers/v5.5.4/ko/main_classes/output#transformers.modeling_outputs.BaseModelOutput) or `tuple(torch.FloatTensor)``

A [BaseModelOutput](/docs/transformers/v5.5.4/ko/main_classes/output#transformers.modeling_outputs.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](/docs/transformers/v5.5.4/ko/model_doc/swin2sr#transformers.Swin2SRConfig)) and inputs.

## Swin2SRForImageSuperResolution [[transformers.Swin2SRForImageSuperResolution]][[transformers.Swin2SRForImageSuperResolution]]

#### transformers.Swin2SRForImageSuperResolution[[transformers.Swin2SRForImageSuperResolution]]

[Source](https://github.com/huggingface/transformers/blob/v5.5.4/src/transformers/models/swin2sr/modeling_swin2sr.py#L954)

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

This model inherits from [PreTrainedModel](/docs/transformers/v5.5.4/ko/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.Swin2SRForImageSuperResolution.forwardhttps://github.com/huggingface/transformers/blob/v5.5.4/src/transformers/models/swin2sr/modeling_swin2sr.py#L981[{"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": "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
  [Swin2SRImageProcessor](/docs/transformers/v5.5.4/ko/model_doc/swin2sr#transformers.Swin2SRImageProcessor). See `Swin2SRImageProcessor.__call__()` for details (`processor_class` uses
  [Swin2SRImageProcessor](/docs/transformers/v5.5.4/ko/model_doc/swin2sr#transformers.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](/docs/transformers/v5.5.4/ko/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.0`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](/docs/transformers/v5.5.4/ko/model_doc/swin2sr#transformers.Swin2SRConfig)) and inputs.
The [Swin2SRForImageSuperResolution](/docs/transformers/v5.5.4/ko/model_doc/swin2sr#transformers.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:
```python
>>> 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`
```

**Parameters:**

config ([Swin2SRForImageSuperResolution](/docs/transformers/v5.5.4/ko/model_doc/swin2sr#transformers.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()](/docs/transformers/v5.5.4/ko/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**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](/docs/transformers/v5.5.4/ko/model_doc/swin2sr#transformers.Swin2SRConfig)) and inputs.