`mmagic.datasets.transforms.aug_frames`¶

Module Contents¶

`RandomMirrorSequence`	Extend short sequences (e.g. Vimeo-90K) by mirroring the sequences.
`MirrorSequence`	Extend short sequences (e.g. Vimeo-90K) by mirroring the sequences.
`TemporalReverse`	Reverse frame lists for temporal augmentation.

class mmagic.datasets.transforms.aug_frames.RandomMirrorSequence(keys, fix_center=None, mirror_ratio=0.5, shuffle=False)[source]¶

Bases: mmcv.transforms.BaseTransform

Extend short sequences (e.g. Vimeo-90K) by mirroring the sequences.

Given a sequence with N frames (x1, …, xN), extend the sequence to (x1, …, xN, xN, …, x1).

Required Keys:

Modified Keys:

CFG:

dict(type=’RandomMirrorSequence’, keys=[‘img’], fix_center=’gt’, mirror_ratio=0.5, shuffle=True)

fix the center frame as gt after shuffle the framelist.

transform(results)[source]¶

transform function.

Parameters: results (dict) – A dict containing the necessary information and data for augmentation.
Returns: A dict containing the processed data and information.
Return type: dict

class mmagic.datasets.transforms.aug_frames.MirrorSequence(keys)[source]¶

Bases: mmcv.transforms.BaseTransform

Extend short sequences (e.g. Vimeo-90K) by mirroring the sequences.

Given a sequence with N frames (x1, …, xN), extend the sequence to (x1, …, xN, xN, …, x1).

Required Keys:

Modified Keys:

transform(results)[source]¶

transform function.

Parameters: results (dict) – A dict containing the necessary information and data for augmentation.
Returns: A dict containing the processed data and information.
Return type: dict

class mmagic.datasets.transforms.aug_frames.TemporalReverse(keys, reverse_ratio=0.5)[source]¶

Bases: mmcv.transforms.BaseTransform

Reverse frame lists for temporal augmentation.

Required keys are the keys in attributes “lq” and “gt”, added or modified keys are “lq”, “gt” and “reverse”.

Parameters

keys (list[str]) – The frame lists to be reversed.
reverse_ratio (float) – The probability to reverse the frame lists. Default: 0.5.

transform(results)[source]¶

transform function.

Parameters: results (dict) – A dict containing the necessary information and data for augmentation.
Returns: A dict containing the processed data and information.
Return type: dict