delta.data.predictGenerator_seg

delta.data.predictGenerator_seg(files_path: str, files_list: Optional[Union[List[str], Tuple[str, ...]]] = None, target_size: Tuple[int, int] = (256, 32), crop: bool = False) → Iterator[ndarray]

Get a generator for predicting segmentation on new image files once the segmentation U-Net has been trained.

Parameters

files_pathstring

Path to image files folder.

files_listlist/tuple of strings, optional

List of file names to read in the folder. If empty, all files in the folder will be read. The default is [].

target_sizetuple of 2 ints, optional

Size for the images to be resized. The default is (256,32).

Returns

mygengenerator

Generator that will yield single image files as 4D numpy arrays of size (1, target_size[0], target_size[1], 1).