Convert the type and range of the input image. It converts the input image to np.float32 type and range of [0, 1]. It is mainly used for pre-p

Convert the type and range of the image according to dst_type. It converts the image to desired type and range. If `dst_type` is np.uint8, ima

Args: x: (B, C, H, W) Returns: x: (B, H, W, C)

Augment: horizontal flips OR rotate (0, 90, 180, 270 degrees). We use vertical flip and transpose for rotation implementation. All the images

Decomposes a batch of images into a complex steerable pyramid. The pyramid typically has ~4 levels and 4-8 orientations. Args:

Build dataloader. Args: dataset (torch.utils.data.Dataset): Dataset. dataset_opt (dict): Dataset options. It contains the followi

Build loss from options. Args: opt (dict): Configuration. It must contain: type (str): Model type.

Constructs a transformation pipeline based on the specified image preparation method. Parameters: - image_prep (str): A string describin

1x1 convolution

3x3 convolution with padding

Create dataloader. Args: dataset (torch.utils.data.Dataset): Dataset. dataset_opt (dict): Dataset options. It contains the follow

Create dataset. Args: dataset_opt (dict): Configuration for dataset. It constains: name (str): Dataset name. type

Recover from quantized flow. Args: dx (ndarray): Quantized dx. dy (ndarray): Quantized dy. max_val (float): Maximum value

Convert distribution prediction to mos score. For datasets with detailed score labels, such as AVA Args: dist_score (tensor): (*, C),

Extracts 2D patches from a 4D tensor. Args: - x (torch.Tensor): Input tensor of shape (batch_size, channels, height, width).

Extract inception features. Args: data_generator (generator): A data generator. inception (nn.Module): Inception model. l

r"""General gaussian distribution estimation. Args: block_seg: maximum number of blocks in parallel to avoid OOM

Check whether it is rank 0.

Read an image from bytes. Args: content (bytes): Image bytes got from files or other streams. flag (str): Flags specifying the co

Read an image from bytes. Args: content (bytes): Image bytes got from files or other streams. flag (str): Flags specifying the co

Read image to tensor. Args: img_source (str, bytes, or PIL.Image): image filepath string, image contents as a bytearray or a PIL Image in

Load a CLIP model Parameters ---------- name : str A model name listed by `clip.available_models()`, or the path to a model checkp

Load the SnowMaster model Args: model_path (str): Path to model checkpoint device (str): Device for inference, default i

mkdirs. If path exists, rename it with timestamp, create a new one, and move it to archive folder. Args: path (str): Folder path.

mkdirs. If path exists, rename it with timestamp and create a new one. Args: path (str): Folder path.

Generate paired paths from folders. Args: folders (list[str]): A list of folder path. The order of list should be [input_fold

Generate paired paths from lmdb files. Contents of lmdb. Taking the `lq.lmdb` for example, the file structure is: lq.lmdb ├── data.mdb

Generate paired paths from an meta information file. Each line in the meta information file contains the image names and image shape (usually

r"""Convert a batch of RGB images to a batch of YIQ images Args: x: Batch of images with shape (N, 3, H, W). RGB colour space. Retur

r"""Safe sqrt with EPS to ensure numeric stability. Args: x (torch.Tensor): should be non-negative

Convert torch Tensors into image numpy arrays. After clamping to [min, max], values will be normalized to [0, 1]. Args: tensor (Tens

new_x_shape = x.size()[:-1] + ( self.num_heads, self.attention_head_size, ) print(new_x_shape)

new_x_shape = x.size()[:-1] + ( self.num_heads, self.attention_head_size, ) print(new_x_shape)

Validation function. Args: dataloader (torch.utils.data.DataLoader): Validation dataloader. current_iter (int): Curre

Validation function. Args: dataloader (torch.utils.data.DataLoader): Validation dataloader. current_iter (int): Curre

Validation function. Args: dataloader (torch.utils.data.DataLoader): Validation dataloader. current_iter (int): Curre

r'''Construct a steerable pyramid on image. Args: image: A tensor. Shape :math:`(N, C, H, W)`. height (int): Number of pyramid lev