Module: tfm.vision.spatial_transform_ops

Spatial transform ops.

Functions

bbox2mask(...): Converts bounding boxes to bitmasks.

bilinear_resize(...): Bilinear resizes the images.

bilinear_resize_to_bbox(...): Bilinear resizes the images to fit into the bounding boxes in the output.

bilinear_resize_with_crop_and_pad(...): Bilinear resizes the images, then crops and finally pads to output size.

bilinear_resize_with_pad(...): Bilinear resizes the images, then pads to output size.

crop_mask_in_target_box(...): Crop masks in target boxes.

multilevel_crop_and_resize(...): Crop and resize on multilevel feature pyramid.

nearest_upsampling(...): Nearest neighbor upsampling implementation.