CLI for inference using fastai models

Remove all transformations so predict_segmentation works with any image size and returns same sized output than input.

source

DataLoader.set_base_transforms

 DataLoader.set_base_transforms ()

Removes all transforms with a size parameter

source

Pipeline.remove

 Pipeline.remove (t)

Remove an instance of t from self if present

source

predict_segmentation

 predict_segmentation (path_to_model:str, path_to_image:str, outfile:str,
                       processing_dir:str='temp', tile_size:int=400,
                       tile_overlap:int=100, use_tta:bool=False)

Segment image into land cover classes with a pretrained models TODO save also information about label and class TODO add test-time augmentations

source

predict_segmentation_fastai

 predict_segmentation_fastai (path_to_model:str, path_to_image:str,
                              outfile:str, processing_dir:str='temp',
                              tile_size:int=400, tile_overlap:int=100,
                              use_tta:bool=False)

CLI for semantic segmentation with fastai

	Type	Default	Details
path_to_model	str		Path to pretrained model file
path_to_image	str		Path to image to annotate
outfile	str		Path and filename for output raster
processing_dir	str	temp	Directory to save the intermediate tiles. Deleted after use
tile_size	int	400	Tile size to use. Default 400x400px tiles
tile_overlap	int	100	Tile overlap to use. Default 100px
use_tta	bool	False	Use test-time augmentation