birl.bm_template module

All other benchmarks should be deviated this way so the core functionality of the benchmarks such as loading or evaluation is not overwritten

INSTALLATION:

1. …

Sample run:

mkdir ./results
touch sample-config.yaml
python birl/bm_template.py         -t ./data-images/pairs-imgs-lnds_histol.csv         -d ./data-images         -o ./results         --visual --unique         -cfg ./sample-config.yaml

Copyright (C) 2017-2019 Jiri Borovec <jiri.borovec@fel.cvut.cz>

class birl.bm_template.BmTemplate(params)

Bases: birl.benchmark.ImRegBenchmark

Basic template showing utilization by inheriting general workflow. This case serves as an example of using the general image regist. benchmark.

Parameters

params (dict) – dictionary with experiment configuration, the required options are names in REQUIRED_PARAMS, note that the basic parameters are inherited

General methods that should be overwritten:

• _check_required_params

• _prepare_img_registration

• _execute_img_registration/_generate_regist_command

• _extract_warped_image_landmarks

• _extract_execution_time

• _clear_after_registration

Note

The actual implementation simulates the “WORSE” registration while it blindly copies the moving landmarks as results of the registration. It also copies the moving images so there is correct “warping” between image and landmarks. It means that there was no registration performed.

Examples

>>> # Running in single thread:
>>> from birl.utilities.data_io import create_folder, update_path
>>> path_out = create_folder('temp_results')
>>> path_csv = os.path.join(update_path('data-images'), 'pairs-imgs-lnds_mix.csv')
>>> open('sample_config.yaml', 'w').close()
>>> BmTemplate.main({
...       'path_table': path_csv,
...       'path_out': path_out,
...       'nb_workers': 1,
...       'unique': False,
...       'visual': True,
...       'path_config': 'sample_config.yaml'
... })  
({...}, '...BmTemplate')
>>> import shutil
>>> shutil.rmtree(path_out, ignore_errors=True)
>>> os.remove('sample_config.yaml')

>>> # Running in multiple parallel threads:
>>> from birl.utilities.data_io import create_folder, update_path
>>> path_out = create_folder('temp_results')
>>> path_csv = os.path.join(update_path('data-images'), 'pairs-imgs-lnds_mix.csv')
>>> params = {'path_table': path_csv,
...           'path_out': path_out,
...           'nb_workers': 2,
...           'unique': False,
...           'visual': True,
...           'path_config': ''}
>>> benchmark = BmTemplate(params)
>>> benchmark.run()
True
>>> del benchmark
>>> import shutil
>>> shutil.rmtree(path_out, ignore_errors=True)

initialise benchmark

Parameters

params (dict) – parameters

_clear_after_registration(item)

clean unnecessarily files after the registration

Parameters

item (dict) – dictionary with regist. information

Return dict

the same or updated regist. info

_extract_execution_time(item)

if needed update the execution time

Parameters

item (dict) – dictionary with registration params

Return float|None

time in minutes

_extract_warped_image_landmarks(item)

get registration results - warped registered images and landmarks

Parameters

item (dict) – dictionary with registration params

Return dict

paths to warped images/landmarks

_generate_regist_command(item)

generate the registration command(s)

Parameters

item (dict) – dictionary with registration params

Return str|list(str)

the execution commands

_prepare()

Prepare the experiment folder.

_prepare_img_registration(item)

prepare the experiment folder if it is required, eq. copy some extra files

Parameters

item (dict) – dictionary with regist. params

Return dict

the same or updated registration info

static extend_parse(arg_parser)

extent the basic arg parses by some extra required parameters

Return object

>>> parser = BmTemplate.extend_parse(create_basic_parser())
>>> type(parser)
<class 'argparse.ArgumentParser'>

REQUIRED_PARAMS = ['path_out', 'path_table', 'path_config']

required experiment parameters