r""" LayerNorm that supports two data formats: channels_last (default) or channels_first. The ordering of the dimensions in the inputs. channels_

Subclass torch's LayerNorm to handle fp16.

A data structure interface of MMagic. They are used as interfaces between different components, e.g., model, visualizer, evaluator, etc. Typic

ConvNeXt V2 Args: in_chans (int): Number of input image channels. Default: 3 num_classes (int): Number of classes for cl

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

ConvNeXt V2 Args: in_chans (int): Number of input image channels. Default: 3 num_classes (int): Number of classes for cl

r""" ConvNeXt A PyTorch impl of : `A ConvNet for the 2020s` - https://arxiv.org/pdf/2201.03545.pdf Args: in_chans (int)

MLP Regression Head for VQA. Args: in_channels: input channels for MLP hidden_channels: hidden channels for MLP dropout_ra

Residual blocks with a convolution in front. Args: in_channels (int): Number of input channels of the first conv. out_channels (i

RealBasicVSR model for real-world video super-resolution. Ref: Investigating Tradeoffs in Real-World Video Super-Resolution, arXiv Args:

r""" ConvNeXt A PyTorch impl of : `A ConvNet for the 2020s` - https://arxiv.org/pdf/2201.03545.pdf Args: in_chans (int)

GRN (Global Response Normalization) layer

VGG network used in calculating perceptual loss. In this implementation, we allow users to choose whether use normalization in the input feat

Pixel Shuffle upsample layer. Args: in_channels (int): Number of input channels. out_channels (int): Number of output channels.

Swin Transformer backbone. A PyTorch impl of : `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows` - https://

A basic Swin Transformer layer for one stage. Args: dim (int): Number of feature channels depth (int): Depths of this stage.

A basic Swin Transformer layer for one stage. Args: dim (int): Number of feature channels depth (int): Depths of this stage.

A basic Swin Transformer layer for one stage. Args: dim (int): Number of feature channels depth (int): Depths of this stage.

BasicVSR model for video super-resolution. Note that this model is used for IconVSR. Paper: BasicVSR: The Search for Essential Compo

r""" ConvNeXt Block. There are two equivalent implementations: (1) DwConv -> LayerNorm (channels_first) -> 1x1 Conv -> GELU -> 1x1 Conv; all in (N

r""" ConvNeXt Block. There are two equivalent implementations: (1) DwConv -> LayerNorm (channels_first) -> 1x1 Conv -> GELU -> 1x1 Conv; all in (N

Merge patches into image

Splitting image into patches

ConvNeXtV2 Block. Args: dim (int): Number of input channels. drop_path (float): Stochastic depth rate. Default: 0.0

ConvNeXtV2 Block. Args: dim (int): Number of input channels. drop_path (float): Stochastic depth rate. Default: 0.0

Dequantize CbCr channel

JPEG Quantization for CbCr channels Args: rounding(function): rounding function to use

Chroma subsampling on CbCr channels

Upsample chroma layers

Full JPEG compression algorithm Args: rounding(function): rounding function to use

Discrete Cosine Transformation

Full JPEG decompression algorithm Args: rounding(function): rounding function to use

This JPEG algorithm result is slightly different from cv2. DiffJPEG supports batch processing. Args: differentiable(bool): If True, us

A Gaussian filter which blurs a given tensor with a two-dimensional gaussian kernel by convolving it along each channel. Batch operation is su

MLP Regression Head for IQA. Args: in_channels: input channels for MLP hidden_channels: hidden channels for MLP dropout_ra