mmagic.datasets.transforms.random_down_sampling

Module Contents

Classes

RandomDownSampling

Generate LQ image from GT (and crop), which will randomly pick a scale.

Functions

resize_fn(img, size[, interpolation, backend])

Resize the given image to a given size.

class mmagic.datasets.transforms.random_down_sampling.RandomDownSampling(scale_min=1.0, scale_max=4.0, patch_size=None, interpolation='bicubic', backend='pillow')

Bases: mmcv.transforms.BaseTransform

Generate LQ image from GT (and crop), which will randomly pick a scale.

Parameters

• scale_min (float) – The minimum of upsampling scale, inclusive. Default: 1.0.

• scale_max (float) – The maximum of upsampling scale, exclusive. Default: 4.0.

• patch_size (int) – The cropped lr patch size. Default: None, means no crop.

• interpolation (str) – Interpolation method, accepted values are “nearest”, “bilinear”, “bicubic”, “area”, “lanczos” for ‘cv2’ backend, “nearest”, “bilinear”, “bicubic”, “box”, “lanczos”, “hamming” for ‘pillow’ backend. Default: “bicubic”.

• backend (str | None) – The image resize backend type. Options are cv2, pillow, None. If backend is None, the global imread_backend specified by mmcv.use_backend() will be used. Default: “pillow”.

• [scale_min (Scale will be picked in the range of) –

• scale_max). –

transform(results)

transform function.

Parameters

results (dict) – A dict containing the necessary information and data for augmentation. ‘gt’ is required.

Returns

A dict containing the processed data and information.

modified ‘gt’, supplement ‘lq’ and ‘scale’ to keys.

Return type

dict

__repr__()

Return repr(self).

mmagic.datasets.transforms.random_down_sampling.resize_fn(img, size, interpolation='bicubic', backend='pillow')

Resize the given image to a given size.

Parameters

• img (np.ndarray | torch.Tensor) – The input image.

• size (int | tuple[int]) – Target size w or (w, h).

• interpolation (str) – Interpolation method, accepted values are “nearest”, “bilinear”, “bicubic”, “area”, “lanczos” for ‘cv2’ backend, “nearest”, “bilinear”, “bicubic”, “box”, “lanczos”, “hamming” for ‘pillow’ backend. Default: “bicubic”.

• backend (str | None) – The image resize backend type. Options are cv2, pillow, None. If backend is None, the global imread_backend specified by mmcv.use_backend() will be used. Default: “pillow”.

Returns

resized_img, whose type is same as img.

Return type

np.ndarray | Tensor