transform_convert_image_dtype: Convert a tensor image to the given 'dtype' and scale the...

In torchvision: Models, Datasets and Transformations for Images

Convert a tensor image to the given dtype and scale the values accordingly

Description

Convert a tensor image to the given dtype and scale the values accordingly

Usage

transform_convert_image_dtype(img, dtype = torch::torch_float())

Arguments

img	A magick-image, array or torch_tensor.
dtype	(torch.dtype): Desired data type of the output.

Note

When converting from a smaller to a larger integer dtype the maximum values are not mapped exactly. If converted back and forth, this mismatch has no effect.

See Also

Other transforms: transform_adjust_brightness(), transform_adjust_contrast(), transform_adjust_gamma(), transform_adjust_hue(), transform_adjust_saturation(), transform_affine(), transform_center_crop(), transform_color_jitter(), transform_crop(), transform_five_crop(), transform_grayscale(), transform_hflip(), transform_linear_transformation(), transform_normalize(), transform_pad(), transform_perspective(), transform_random_affine(), transform_random_apply(), transform_random_choice(), transform_random_crop(), transform_random_erasing(), transform_random_grayscale(), transform_random_horizontal_flip(), transform_random_order(), transform_random_perspective(), transform_random_resized_crop(), transform_random_rotation(), transform_random_vertical_flip(), transform_resized_crop(), transform_resize(), transform_rgb_to_grayscale(), transform_rotate(), transform_ten_crop(), transform_to_tensor(), transform_vflip()

torchvision documentation built on April 14, 2023, 5:08 p.m.