Method segment_batch

netdissect/segmenter.py:23–34

Returns a multilabel segmentation for the given batch of (RGB [-1...1]) images. Each pixel of the result is a torch.long indicating a predicted class number. Multiple classes can be predicted for the same pixel: output shape is (n, multipred, y, x), where m

(self, tensor_images, downsample=1)

        raise NotImplemented()

    def segment_batch(self, tensor_images, downsample=1):
        '''
        Returns a multilabel segmentation for the given batch of (RGB [-1...1])
        images.  Each pixel of the result is a torch.long indicating a
        predicted class number.  Multiple classes can be predicted for
        the same pixel: output shape is (n, multipred, y, x), where
        multipred is 3, 5, or 6, for how many different predicted labels can
        be given for each pixel (depending on whether subdivision is being
        used).  If downsample is specified, then the output y and x dimensions
        are downsampled from the original image.
        '''
        raise NotImplemented()

    def predict_single_class(self, tensor_images, classnum, downsample=1):
        '''