piscis.utils ============ .. py:module:: piscis.utils Attributes ---------- .. autoapisummary:: piscis.utils.vmap_deformable_max_pool piscis.utils.vmap_deformable_softmax_pool piscis.utils.vmap_deformable_sum_pool piscis.utils.vmap_peak_local_softmax Functions --------- .. autoapisummary:: piscis.utils.compute_spot_coordinates piscis.utils.deformable_max_pool piscis.utils.deformable_softmax_pool piscis.utils.deformable_sum_pool piscis.utils.peak_local_softmax piscis.utils.pad_and_stack piscis.utils.pad piscis.utils.remove_duplicate_coords piscis.utils._match_coords piscis.utils.snap_coords piscis.utils.fit_coords piscis.utils._gaussian Module Contents --------------- .. py:function:: compute_spot_coordinates(labels: numpy.ndarray, deltas: numpy.ndarray, threshold: float, min_distance: int) -> numpy.ndarray Compute spot coordinates from labels and deltas. :Parameters: **labels** : np.ndarray Labels. **deltas** : np.ndarray Displacement vectors. **threshold** : float Detection threshold between 0 and 1. **min_distance** : int Minimum distance between spots. :Returns: **coords** : np.ndarray Coordinates of detected spots. .. !! processed by numpydoc !! .. py:function:: deformable_max_pool(labels: torch.Tensor, deltas: torch.Tensor, kernel_size: Sequence[int] = (3, 3)) -> torch.Tensor Max pool labels using deltas. :Parameters: **labels** : torch.Tensor Labels. **deltas** : torch.Tensor Displacement vectors. **kernel_size** : Sequence[int], optional Kernel size or window size of the max pooling operation. Default is (3, 3). :Returns: **pooled_labels** : torch.Tensor Pooled labels. .. !! processed by numpydoc !! .. py:data:: vmap_deformable_max_pool .. py:function:: deformable_softmax_pool(labels: torch.Tensor, deltas: torch.Tensor, x: torch.Tensor = None, kernel_size: Sequence[int] = (3, 3), temperature: float = 0.05) -> torch.Tensor Softmax pool labels or another tensor using deltas. :Parameters: **labels** : torch.Tensor Labels. **deltas** : torch.Tensor Displacement vectors. **x** : torch.Tensor, optional Tensor to be pooled. Default is None. **kernel_size** : Sequence[int], optional Kernel size or window size of the softmax pooling operation. Default is (3, 3). **temperature** : float Temperature parameter for softmax. Default is 0.05. :Returns: **pooled_labels** : torch.Tensor Pooled labels. .. !! processed by numpydoc !! .. py:data:: vmap_deformable_softmax_pool .. py:function:: deformable_sum_pool(labels: torch.Tensor, deltas: torch.Tensor, kernel_size: Sequence[int] = (3, 3)) -> torch.Tensor Sum pool labels using deltas. :Parameters: **labels** : torch.Tensor Labels. **deltas** : torch.Tensor Displacement vectors. **kernel_size** : Sequence[int], optional Kernel size or window size of the sum pooling operation. Default is (3, 3). :Returns: **pooled_labels** : torch.Tensor Pooled labels. .. !! processed by numpydoc !! .. py:data:: vmap_deformable_sum_pool .. py:function:: peak_local_softmax(labels: torch.Tensor, kernel_size: Sequence[int] = (3, 3), temperature: float = 0.05) -> torch.Tensor Smooth variant of `peak_local_max` with softmax pooling to find peaks in labels. :Parameters: **labels** : torch.Tensor Labels. **kernel_size** : Sequence[int], optional Kernel size or window size of the softmax pooling operation. Default is (3, 3). **temperature** : float Temperature parameter for softmax. Default is 0.05. :Returns: **peaked_labels** : torch.Tensor Peaked labels. .. !! processed by numpydoc !! .. py:data:: vmap_peak_local_softmax .. py:function:: pad_and_stack(images: Sequence[numpy.ndarray]) -> numpy.ndarray Pad and stack images. :Parameters: **images** : Sequence[np.ndarray] List of images to pad and stack. :Returns: **stacked_images** : np.ndarray Stacked images. .. !! processed by numpydoc !! .. py:function:: pad(images: Sequence[numpy.ndarray]) -> Sequence[numpy.ndarray] Pad images to the same size. :Parameters: **images** : Sequence[np.ndarray] List of images to pad. :Returns: **padded_images** : Sequence[np.ndarray] List of padded images. .. !! processed by numpydoc !! .. py:function:: remove_duplicate_coords(coords: numpy.ndarray, threshold: int = 1) -> numpy.ndarray Remove duplicate coordinates within a distance threshold. :Parameters: **coords** : np.ndarray Coordinates. **threshold** : int, optional Distance threshold. Default is 1. :Returns: **new_coords** : np.ndarray Coordinates without duplicates. .. !! processed by numpydoc !! .. py:function:: _match_coords(coords: numpy.ndarray, i: int, set_id: int, coord_set_ids: Dict[int, int], checked: List[int], threshold: int) -> List[int] Match coordinates within a distance threshold and assign them to the same set. :Parameters: **coords** : np.ndarray Coordinates. **i** : int Coordinate index. **set_id** : int Set id. **coord_set_ids** : Dict[int, int] Dictionary to keep track of the set id of each coordinate. **checked** : List[int] List to keep track of coordinates that have been checked. **threshold** : int Distance threshold. :Returns: **matches** : List[int] List of matched coordinates. .. !! processed by numpydoc !! .. py:function:: snap_coords(coords: numpy.ndarray, image: numpy.ndarray, window_size: int = 3) -> numpy.ndarray Snap each coordinate to the local maxima of an image in a window around the coordinate. :Parameters: **coords** : np.ndarray Coordinates. **image** : np.ndarray Image. **window_size** : int, optional Window size. Must be an odd integer. Default is 3. :Returns: **snapped_coords** : np.ndarray Snapped coordinates. :Raises: ValueError If `window_size` is not an odd integer. .. !! processed by numpydoc !! .. py:function:: fit_coords(coords: numpy.ndarray, image: numpy.ndarray, window_size: int = 3, max_gaussian_amplitude: float = 2.0, keep_failed_fits: bool = False) -> numpy.ndarray Fit a Gaussian to the image in a window around each coordinate and return the center of the Gaussian. :Parameters: **coords** : np.ndarray Coordinates. **image** : np.ndarray Image. **window_size** : int, optional Window size. Must be an odd integer. Default is 3. **max_gaussian_amplitude** : float, optional Maximum amplitude of the Gaussian used to fit the normalized image within a window. Default is 2.0. **keep_failed_fits** : bool, optional Whether to keep the original coordinates when the Gaussian fit fails. Default is False. :Returns: **fitted_coords** : np.ndarray Fitted coordinates. :Raises: ValueError If `window_size` is not an odd integer. .. !! processed by numpydoc !! .. py:function:: _gaussian(xy: Tuple[numpy.ndarray, numpy.ndarray], amplitude: float, x0: float, y0: float, sigma_x: float, sigma_y: float, theta: float, offset: float) -> numpy.ndarray 2D Gaussian function. :Parameters: **xy** : Tuple[np.ndarray, np.ndarray] x and y values at which to evaluate the Gaussian. **amplitude** : float Amplitude of the Gaussian. **x0** : float x-coordinate of the center of the Gaussian. **y0** : float y-coordinate of the center of the Gaussian. **sigma_x** : float Standard deviation of the Gaussian in the x-direction. **sigma_y** : float Standard deviation of the Gaussian in the y-direction. **theta** : float Rotation angle of the Gaussian. **offset** : float Offset of the Gaussian in the z-direction. :Returns: **g** : np.ndarray Gaussian at the given x and y values. .. !! processed by numpydoc !!