dcnum.feat.feat_background.base

Attributes

mp_spawn

Classes

Background

Base class for background computation

Functions

get_available_background_methods()

Return dictionary of background computation methods

Module Contents

dcnum.feat.feat_background.base.mp_spawn = None

class dcnum.feat.feat_background.base.Background(input_data, output_path, compress=True, num_cpus=None, **kwargs)

Bases: abc.ABC

Base class for background computation

Parameters:

• input_data (array-like or pathlib.Path) – The input data can be either a path to an HDF5 file with the “evtens/image” dataset or an array-like object that behaves like an image stack (first axis enumerates events)

• output_path (pathlib.Path) – Path to the output file. If input_data is a path, you can set output_path to the same path to write directly to the input file. The data are written in the “events/image_bg” dataset in the output file.

• compress (bool) – Whether to compress background data. Set this to False for faster processing.

• num_cpus (int) – Number of CPUs to use for median computation. Defaults to dcnum.common.cpu_count().

• kwargs – Additional keyword arguments passed to the subclass.

logger

output_path

kwargs

background keyword arguments

num_cpus = None

number of CPUs used

image_proc

fraction of images that have been processed

hdin = None

HDF5Data instance for input data

h5in = None

input h5py.File

h5out = None

output h5py.File

paths_ref = []

reference paths for logging to the output .rtdc file

image_shape

shape of event images

image_count

number of images in the input data

writer

__enter__()

__exit__(type, value, tb)

abstractmethod check_user_kwargs(**kwargs)

Implement this to check the kwargs during init

get_ppid()

Return a unique background pipeline identifier

The pipeline identifier is universally applicable and must be backwards-compatible (future versions of dcnum will correctly acknowledge the ID).

The segmenter pipeline ID is defined as:

KEY:KW_BACKGROUND

Where KEY is e.g. “sparsemed” or “rollmed”, and KW_BACKGROUND is a list of keyword arguments for check_user_kwargs, e.g.:

kernel_size=100^batch_size=10000

which may be abbreviated to:

k=100^b=10000

classmethod get_ppid_code()

classmethod get_ppid_from_ppkw(kwargs)

Return the PPID based on given keyword arguments for a subclass

static get_ppkw_from_ppid(bg_ppid)

Return keyword arguments for any subclass from a PPID string

get_progress()

Return progress of background computation, float in [0,1]

process()

Perform the background computation

This irreversibly removes/overrides any “image_bg” and “bg_off” features defined in the output file self.h5out.

abstractmethod process_approach()

The actual background computation approach

dcnum.feat.feat_background.base.get_available_background_methods()

Return dictionary of background computation methods