resize_batch

composer.functional.resize_batch(input, target, scale_factor, mode='resize', resize_targets=False)

Resize inputs and optionally outputs by cropping or interpolating.

Parameters

• input (Tensor) – input tensor of shape (N, C, H, W). Resizing will be done along dimensions H and W using the constant factor scale_factor.

• target (Tensor) – output tensor of shape (N, H, W) or (N, C, H, W) that will also be resized if resize_targets is True,

• scale_factor (float) – scaling coefficient for the height and width of the input/output tensor. 1.0 keeps the original size.

• mode (str, optional) – type of scaling to perform. Value must be one of 'crop' or 'resize'. 'crop' performs a random crop, whereas 'resize' performs a nearest neighbor interpolation. Default: "resize".

• resize_targets (bool, optional) – whether to resize the targets, y. Default: False.

Returns

• X_sized – resized input tensor of shape (N, C, H * scale_factor, W * scale_factor).

• y_sized – if resized_targets is True, resized output tensor of shape (N, H * scale_factor, W * scale_factor) or (N, C, H * scale_factor, W * scale_factor). Depending on the input y. Otherwise returns original y.

Example

from composer.algorithms.progressive_resizing import resize_batch
X_resized, y_resized = resize_batch(X_example,
                                    y_example,
                                    scale_factor=0.5,
                                    mode='resize',
                                    resize_targets=False)