ResizeEdge

class mmpretrain.datasets.transforms.ResizeEdge(scale, edge='short', backend='cv2', interpolation='bilinear')

Resize images along the specified edge.

Required Keys:

• img

Modified Keys:

• img

• img_shape

Added Keys:

• scale

• scale_factor

Parameters:

• scale (int) – The edge scale to resizing.

• edge (str) – The edge to resize. Defaults to ‘short’.

• backend (str) – Image resize backend, choices are ‘cv2’ and ‘pillow’. These two backends generates slightly different results. Defaults to ‘cv2’.

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

transform(results)

Transform function to resize images.

Parameters:

results (dict) – Result dict from loading pipeline.

Returns:

Resized results, ‘img’, ‘scale’, ‘scale_factor’, ‘img_shape’ keys are updated in result dict.

Return type:

dict