diff --git a/bob/bio/base/tools/command_line.py b/bob/bio/base/tools/command_line.py
index cf65ff6782c5ed085f02e68c3b9bf089a6b7780d..00693033d2eb4778a1bc1d6a07c0a82e6beeffb6 100644
--- a/bob/bio/base/tools/command_line.py
+++ b/bob/bio/base/tools/command_line.py
@@ -1,3 +1,6 @@
+"""Execute biometric recognition algorithms on a certain biometric database.
+"""
+
import argparse
import os
import sys
@@ -11,23 +14,79 @@ logger = bob.core.log.setup("bob.bio.base")
from .. import utils
from . import FileSelector
-"""Execute biometric recognition algorithms on a certain biometric database.
-"""
def is_idiap():
return os.path.isdir("/idiap") and "USER" in os.environ
+
+def command_line_config_group(parser, package_prefix='bob.bio.', exclude_resources_from=[]):
+ """
+ Generic configuration command lines that can be used by different toolchains, e.g., in bob.bio or bob.pad.
+ :param parser: Parser to which this argument group should be added
+ :param package_prefix: prefix of a package, in which these arguments should be use, e.g., in bob.bio. or bob.pad.
+ :param exclude_resources_from: resources that should be excluded from the commandline
+ :return: new config argument group added to the parser
+ """
+
+ config_group = parser.add_argument_group(
+ '\nParameters defining the experiment. Most of these parameters can be a registered '
+ 'resource, a configuration file, or even a string that defines a newly created object')
+ config_group.add_argument('configuration_file', metavar='PATH', nargs='*',
+ help='A configuration file containing one or more of "database", "preprocessor", '
+ '"extractor", "algorithm" and/or "grid"')
+ config_group.add_argument('-H', '--create-configuration-file', metavar='PATH',
+ help='If selected, an empty configuration file will be created')
+ config_group.add_argument('-d', '--database', metavar='x', nargs='+',
+ help='Database and the protocol; registered databases are: %s' % utils.resource_keys(
+ 'database', exclude_resources_from, package_prefix=package_prefix))
+ config_group.add_argument('-p', '--preprocessor', metavar='x', nargs='+',
+ help='Data preprocessing; registered preprocessors are: %s' % utils.resource_keys(
+ 'preprocessor', exclude_resources_from, package_prefix=package_prefix))
+ config_group.add_argument('-e', '--extractor', metavar='x', nargs='+',
+ help='Feature extraction; registered feature extractors are: %s' % utils.resource_keys(
+ 'extractor', exclude_resources_from, package_prefix=package_prefix))
+ config_group.add_argument('-a', '--algorithm', metavar='x', nargs='+',
+ help='Algorithm of the experiment; registered algorithms are: %s' % utils.resource_keys(
+ 'algorithm', exclude_resources_from, package_prefix=package_prefix))
+ config_group.add_argument('-g', '--grid', metavar='x', nargs='+',
+ help='Configuration for the grid setup; if not specified, the commands are executed '
+ 'sequentially on the local machine; registered grid resources are %s.' %
+ utils.resource_keys('grid', exclude_resources_from, package_prefix=package_prefix))
+ config_group.add_argument('-I', '--imports', metavar='LIB', nargs='+', default=[package_prefix + 'base'],
+ help='If one of your configuration files is an actual command, please specify the '
+ 'lists of required libraries (imports) to execute this command')
+ config_group.add_argument('-W', '--preferred-package', metavar='LIB',
+ help='If resources with identical names are defined in several packages, prefer the '
+ 'one from the given package')
+ config_group.add_argument('-s', '--sub-directory', metavar='DIR',
+ help='The sub-directory where the files of the current experiment should be stored. '
+ 'Please specify a directory name with a name describing your experiment')
+ config_group.add_argument('--groups', metavar='GROUP', nargs='+', default=['dev'],
+ help="The groups (i.e., 'dev', 'eval') for which the models and scores should be "
+ "generated; by default, only the 'dev' group is evaluated")
+ config_group.add_argument('-P', '--protocol', metavar='PROTOCOL',
+ help='Overwrite the protocol that is stored in the database by the given one '
+ '(might not by applicable for all databases).')
+
+ config_group.add_argument('--package-prefix', default=package_prefix, help=argparse.SUPPRESS)
+
+ return config_group
+
+
def command_line_parser(description=__doc__, exclude_resources_from=[]):
"""command_line_parser(description=__doc__, exclude_resources_from=[]) -> parsers
- Creates an :py:class:`argparse.ArgumentParser` object that includes the minimum set of command line options (which is not so few).
+ Creates an :py:class:`argparse.ArgumentParser` object that includes the minimum set of command
+ line options (which is not so few).
The ``description`` can be overwritten, but has a (small) default.
Included in the parser, several groups are defined.
Each group specifies a set of command line options.
- For the configurations, registered resources are listed, which can be limited by the ``exclude_resources_from`` list of extensions.
+ For the configurations, registered resources are listed, which can be limited by the
+ ``exclude_resources_from`` list of extensions.
- It returns a dictionary, containing the parser object itself (in the ``'main'`` keyword), and a list of command line groups.
+ It returns a dictionary, containing the parser object itself (in the ``'main'`` keyword),
+ and a list of command line groups.
**Parameters:**
@@ -43,33 +102,13 @@ def command_line_parser(description=__doc__, exclude_resources_from=[]):
A dictionary of parser groups, with the main parser under the 'main' key.
Feel free to add more options to any of the parser groups.
"""
- parser = argparse.ArgumentParser(description=description, formatter_class=argparse.ArgumentDefaultsHelpFormatter, conflict_handler='resolve')
+ parser = argparse.ArgumentParser(description=description, formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+ conflict_handler='resolve')
#######################################################################################
############## options that are required to be specified #######################
- config_group = parser.add_argument_group('\nParameters defining the experiment. Most of these parameters can be a registered resource, a configuration file, or even a string that defines a newly created object')
- config_group.add_argument('configuration_file', metavar='PATH', nargs='*', help = 'A configuration file containing one or more of "database", "preprocessor", "extractor", "algorithm" and/or "grid"')
- config_group.add_argument('-H', '--create-configuration-file', metavar='PATH', help = 'If selected, an empty configuration file will be created')
- config_group.add_argument('-d', '--database', metavar = 'x', nargs = '+',
- help = 'Database and the protocol; registered databases are: %s' % utils.resource_keys('database', exclude_resources_from))
- config_group.add_argument('-p', '--preprocessor', metavar = 'x', nargs = '+',
- help = 'Data preprocessing; registered preprocessors are: %s' % utils.resource_keys('preprocessor', exclude_resources_from))
- config_group.add_argument('-e', '--extractor', metavar = 'x', nargs = '+',
- help = 'Feature extraction; registered feature extractors are: %s' % utils.resource_keys('extractor', exclude_resources_from))
- config_group.add_argument('-a', '--algorithm', metavar = 'x', nargs = '+',
- help = 'Biometric recognition; registered algorithms are: %s' % utils.resource_keys('algorithm', exclude_resources_from))
- config_group.add_argument('-g', '--grid', metavar = 'x', nargs = '+',
- help = 'Configuration for the grid setup; if not specified, the commands are executed sequentially on the local machine; registered grid resources are %s.' % utils.resource_keys('grid', exclude_resources_from))
- config_group.add_argument('-I', '--imports', metavar = 'LIB', nargs = '+', default = ['bob.bio.base'],
- help = 'If one of your configuration files is an actual command, please specify the lists of required libraries (imports) to execute this command')
- config_group.add_argument('-W', '--preferred-package', metavar = 'LIB',
- help = 'If resources with identical names are defined in several packages, prefer the one from the given package')
- config_group.add_argument('-s', '--sub-directory', metavar = 'DIR',
- help = 'The sub-directory where the files of the current experiment should be stored. Please specify a directory name with a name describing your experiment')
- config_group.add_argument('--groups', metavar = 'GROUP', nargs = '+', default = ['dev'],
- help = "The groups (i.e., 'dev', 'eval') for which the models and scores should be generated; by default, only the 'dev' group is evaluated")
- config_group.add_argument('-P', '--protocol', metavar='PROTOCOL',
- help = 'Overwrite the protocol that is stored in the database by the given one (might not by applicable for all databases).')
+ config_group = command_line_config_group(parser, package_prefix='bob.bio.',
+ exclude_resources_from=exclude_resources_from)
#######################################################################################
############## options to modify default directories or file names ####################
@@ -85,7 +124,9 @@ def command_line_parser(description=__doc__, exclude_resources_from=[]):
dir_group.add_argument('-R', '--result-directory', metavar = 'DIR',
help = 'The directory for resulting score files; if --result-directory is not specified, "%s" is used' % results)
- file_group = parser.add_argument_group('\nName (maybe including a path relative to the --temp-directory, if not specified otherwise) of files that will be generated. Note that not all files will be used by all algorithms')
+ file_group = parser.add_argument_group('\nName (maybe including a path relative to the --temp-directory, '
+ 'if not specified otherwise) of files that will be generated. '
+ 'Note that not all files will be used by all algorithms')
file_group.add_argument('--extractor-file', metavar = 'FILE', default = 'Extractor.hdf5',
help = 'Name of the file to write the feature extractor into.')
file_group.add_argument('--projector-file', metavar = 'FILE', default = 'Projector.hdf5',
@@ -93,13 +134,20 @@ def command_line_parser(description=__doc__, exclude_resources_from=[]):
file_group.add_argument('--enroller-file' , metavar = 'FILE', default = 'Enroller.hdf5',
help = 'Name of the file to write the model enroller into.')
file_group.add_argument('-G', '--gridtk-database-file', metavar = 'FILE', default = 'submitted.sql3',
- help = 'The database file in which the submitted jobs will be written; relative to the current directory (only valid with the --grid option).')
+ help = 'The database file in which the submitted jobs will be written; relative to the current directory '
+ '(only valid with the --grid option).')
file_group.add_argument('--experiment-info-file', metavar = 'FILE', default = 'Experiment.info',
- help = 'The file where the configuration of all parts of the experiments are written; relative to te --result-directory.')
+ help = 'The file where the configuration of all parts of the experiments are written; '
+ 'relative to te --result-directory.')
file_group.add_argument('-D', '--database-directories-file', metavar = 'FILE', default = database_replacement,
help = 'An optional file, where database directories are stored (to avoid changing the database configurations)')
- sub_dir_group = parser.add_argument_group('\nSubdirectories of certain parts of the tool chain. You can specify directories in case you want to reuse parts of the experiments (e.g. extracted features) in other experiments. Please note that these directories are relative to the --temp-directory, but you can also specify absolute paths')
+
+ sub_dir_group = parser.add_argument_group('\nSubdirectories of certain parts of the tool chain. '
+ 'You can specify directories in case you want to reuse parts of '
+ 'the experiments (e.g. extracted features) in other experiments. '
+ 'Please note that these directories are relative to the --temp-directory, '
+ 'but you can also specify absolute paths')
sub_dir_group.add_argument('--preprocessed-directory', metavar = 'DIR', default = 'preprocessed',
help = 'Name of the directory of the preprocessed data.')
sub_dir_group.add_argument('--extracted-directory', metavar = 'DIR', default = 'extracted',
@@ -110,10 +158,13 @@ def command_line_parser(description=__doc__, exclude_resources_from=[]):
help = 'Name of the directory where the models (and T-Norm models) should be stored')
sub_dir_group.add_argument('--score-directories', metavar = 'DIR', nargs = '+', default = ['nonorm', 'ztnorm'],
help = 'Name of the directory (relative to --result-directory) where to write the results to')
- sub_dir_group.add_argument('--zt-directories', metavar = 'DIR', nargs = 5, default = ['zt_norm_A', 'zt_norm_B', 'zt_norm_C', 'zt_norm_D', 'zt_norm_D_sameValue'],
- help = 'Name of the directories (of --temp-directory) where to write the ZT-norm values; only used with --zt-norm')
+ sub_dir_group.add_argument('--zt-directories', metavar = 'DIR', nargs = 5,
+ default = ['zt_norm_A', 'zt_norm_B', 'zt_norm_C', 'zt_norm_D', 'zt_norm_D_sameValue'],
+ help = 'Name of the directories (of --temp-directory) where to write the ZT-norm values; '
+ 'only used with --zt-norm')
sub_dir_group.add_argument('--grid-log-directory', metavar = 'DIR', default = 'gridtk_logs',
- help = 'Name of the directory (relative to --temp-directory) where to log files are written; only used with --grid')
+ help = 'Name of the directory (relative to --temp-directory) where to log files are written; '
+ 'only used with --grid')
flag_group = parser.add_argument_group('\nFlags that change the behavior of the experiment')
bob.core.log.add_command_line_option(flag_group)
@@ -130,21 +181,27 @@ def command_line_parser(description=__doc__, exclude_resources_from=[]):
flag_group.add_argument('-B', '--timer', choices=('real', 'system', 'user'), nargs = '*',
help = 'Measure and report the time required by the execution of the tool chain (only on local machine)')
flag_group.add_argument('-L', '--run-local-scheduler', action='store_true',
- help = 'Starts the local scheduler after submitting the jobs to the local queue (by default, local jobs must be started by hand, e.g., using jman --local -vv run-scheduler -x)')
+ help = 'Starts the local scheduler after submitting the jobs to the local queue (by default, '
+ 'local jobs must be started by hand, e.g., using ./bin/jman --local -vv run-scheduler -x)')
flag_group.add_argument('-N', '--nice', type=int, default=10,
help = 'Runs the local scheduler with the given nice value')
flag_group.add_argument('-D', '--delete-jobs-finished-with-status', choices = ('all', 'failure', 'success'),
- help = 'If selected, local scheduler jobs that finished with the given status are deleted from the --gridtk-database-file; otherwise the jobs remain in the database')
+ help = 'If selected, local scheduler jobs that finished with the given status are deleted from '
+ 'the --gridtk-database-file; otherwise the jobs remain in the database')
flag_group.add_argument('-C', '--calibrate-scores', action='store_true',
help = 'Performs score calibration after the scores are computed.')
flag_group.add_argument('-z', '--zt-norm', action='store_true',
help = 'Enable the computation of ZT norms')
flag_group.add_argument('-A', '--allow-missing-files', action='store_true',
- help = "If given, missing files will not stop the processing; this is helpful if not all files of the database can be processed; missing scores will be NaN.")
+ help = "If given, missing files will not stop the processing; this is helpful if not all files of the "
+ "database can be processed; missing scores will be NaN.")
flag_group.add_argument('-r', '--parallel', type=int,
- help = 'This flag is a shortcut for running the commands on the local machine with the given amount of parallel threads; equivalent to --grid bob.bio.base.grid.Grid("local", number_of_parallel_threads=X) --run-local-scheduler --stop-on-failure.')
+ help = 'This flag is a shortcut for running the commands on the local machine with the given amount of '
+ 'parallel threads; equivalent to --grid bob.bio.base.grid.Grid("local", '
+ 'number_of_parallel_threads=X) --run-local-scheduler --stop-on-failure.')
- flag_group.add_argument('-t', '--environment', dest='env', nargs='*', default=[], help='Passes specific environment variables to the job.')
+ flag_group.add_argument('-t', '--environment', dest='env', nargs='*', default=[],
+ help='Passes specific environment variables to the job.')
return {
'main' : parser,
@@ -156,46 +213,143 @@ def command_line_parser(description=__doc__, exclude_resources_from=[]):
}
-def _take_from_config_or_command_line(args, config, keyword, default, required=True, is_resource=True):
+def command_line_skip_group(parsers, command_line_parameters, skips):
+ # add execute-only flags to command line options
+ if skips is not None:
+ #######################################################################################
+ ################# options for skipping parts of the toolchain #########################
+ skip_group = parsers['main'].add_argument_group(
+ '\nFlags that allow to skip certain parts of the experiments. This does only make sense when the '
+ 'generated files are already there (e.g. when reusing parts of other experiments)')
+ for skip in skips:
+ skip_group.add_argument('--skip-%s' % skip, action='store_true', help='Skip the %s step.' % skip)
+ skip_group.add_argument('-o', '--execute-only', nargs='+', choices=skips,
+ help='If specified, executes only the given parts of the tool chain.')
+
+ # parse the arguments
+ parser = parsers['main']
+ args = parser.parse_args(command_line_parameters)
+ return args
+
+
+def take_from_config_or_command_line(args, config, keyword, default, required=True, is_resource=True):
if getattr(args, keyword) is not None and getattr(args, keyword) != default:
if is_resource:
- setattr(args, keyword, utils.load_resource(' '.join(getattr(args, keyword)), keyword, imports = args.imports, preferred_package = args.preferred_package))
+ setattr(args, keyword, utils.load_resource(' '.join(getattr(args, keyword)), keyword,
+ imports=args.imports, package_prefix=args.package_prefix,
+ preferred_package=args.preferred_package))
elif config is not None and hasattr(config, keyword):
val = getattr(config, keyword)
if isinstance(val, str) and is_resource:
- val = utils.load_resource(val, keyword, imports = args.imports, preferred_package = args.preferred_package)
+ val = utils.load_resource(val, keyword, imports = args.imports, package_prefix=args.package_prefix,
+ preferred_package = args.preferred_package)
setattr(args, keyword, val)
elif default is not None:
if is_resource:
- setattr(args, keyword, utils.load_resource(' '.join(default), keyword, imports = args.imports, preferred_package = args.preferred_package))
+ setattr(args, keyword, utils.load_resource(' '.join(default), keyword,
+ imports=args.imports, package_prefix=args.package_prefix,
+ preferred_package=args.preferred_package))
elif required:
- raise ValueError("Please specify a %s either on command line (via --%s) or in a configuration file" %(keyword, keyword))
+ raise ValueError("Please specify a %s either on command line (via --%s) or in a configuration file" %
+ (keyword, keyword))
if config is not None and hasattr(config, keyword):
setattr(config, keyword, None)
-def _check_config_consumed(config):
+
+def check_config_consumed(config):
if config is not None:
import inspect
for keyword in dir(config):
if not keyword.startswith('_') and not keyword.isupper():
attr = getattr(config,keyword)
if attr is not None and not inspect.isclass(attr) and not inspect.ismodule(attr):
- logger.warn("The variable '%s' in a configuration file is not known or not supported; use all uppercase variable names (e.g., '%s') to suppress this warning.", keyword, keyword.upper())
+ logger.warn("The variable '%s' in a configuration file is not known or not supported; use all "
+ "uppercase variable names (e.g., '%s') to suppress this warning.", keyword, keyword.upper())
+
+
+def parse_config_file(parsers, args, args_dictionary, keywords, skips):
+ parser = parsers['main']
+ # check if the "create_configuration_file" function was requested
+ if args.create_configuration_file is not None:
+ # update list of options to be written into the config file
+ set_required_common_optional_arguments(required=args_dictionary['required'],
+ common=args_dictionary['common'],
+ optional=args_dictionary['optional'])
+ # this will exit at the end
+ create_configuration_file(parsers, args)
+
+ # first, read the configuration file and set everything from the config file to the args -- as
+ # long as not overwritten on command line
+ config = utils.read_config_file(args.configuration_file) if args.configuration_file else None
+ for keyword in ("database", "preprocessor", "extractor", "algorithm"):
+ take_from_config_or_command_line(args, config, keyword,
+ parser.get_default(keyword))
+
+ take_from_config_or_command_line(args, config, "grid",
+ parser.get_default('grid'), required=False)
+
+ take_from_config_or_command_line(args, config, "sub_directory",
+ parser.get_default("sub_directory"), is_resource=False)
+
+ skip_keywords = tuple(['skip_' + k.replace('-', '_') for k in skips])
+
+ for keyword in keywords + skip_keywords:
+ take_from_config_or_command_line(args, config, keyword,
+ parser.get_default(keyword), required=False, is_resource=False)
+
+ # check that all variables in the config file are consumed by the above options
+ check_config_consumed(config)
+
+ # evaluate skips
+ if skips is not None and args.execute_only is not None:
+ for skip in skips:
+ if skip not in args.execute_only:
+ setattr(args, "skip_%s" % skip.replace("-", "_"), True)
+ return args
+
+
+def set_extra_flags(args):
+ if args.parallel is not None:
+ args.grid = bob.bio.base.grid.Grid("local", number_of_parallel_processes=args.parallel)
+ args.run_local_scheduler = True
+ args.stop_on_failure = True
+
+ # logging
+ bob.core.log.set_verbosity_level(logger, args.verbose)
+
+ # timer
+ if args.timer is not None and not len(args.timer):
+ args.timer = ('real', 'system', 'user')
+
+ # set base directories
+ if args.temp_directory is None:
+ args.temp_directory = "/idiap/temp/%s/%s" % (os.environ["USER"], args.database.name) if is_idiap() else "temp"
+ if args.result_directory is None:
+ args.result_directory = "/idiap/user/%s/%s" % (
+ os.environ["USER"], args.database.name) if is_idiap() else "results"
+
+ args.temp_directory = os.path.join(args.temp_directory, args.sub_directory)
+ args.result_directory = os.path.join(args.result_directory, args.sub_directory)
+ args.grid_log_directory = os.path.join(args.temp_directory, args.grid_log_directory)
+
+ return args
def initialize(parsers, command_line_parameters = None, skips = []):
"""initialize(parsers, command_line_parameters = None, skips = []) -> args
Parses the command line and arranges the arguments accordingly.
- Afterward, it loads the resources for the database, preprocessor, extractor, algorithm and grid (if specified), and stores the results into the returned args.
+ Afterward, it loads the resources for the database, preprocessor, extractor, algorithm and grid (if specified),
+ and stores the results into the returned args.
- This function also initializes the :py:class:`FileSelector` instance by arranging the directories and files according to the command line parameters.
+ This function also initializes the :py:class:`FileSelector` instance by arranging the directories and
+ files according to the command line parameters.
If the ``skips`` are given, an '--execute-only' parameter is added to the parser, according skips are selected.
@@ -217,118 +371,56 @@ def initialize(parsers, command_line_parameters = None, skips = []):
args : namespace
A namespace of arguments as read from the command line.
- .. note:: The database, preprocessor, extractor, algorithm and grid (if specified) are actual instances of the according classes.
+ .. note:: The database, preprocessor, extractor, algorithm and grid (if specified) are actual instances
+ of the according classes.
"""
from bob.bio.base.database import BioDatabase
- # add execute-only flags to command line options
- if skips is not None:
- #######################################################################################
- ################# options for skipping parts of the toolchain #########################
- skip_group = parsers['main'].add_argument_group('\nFlags that allow to skip certain parts of the experiments. This does only make sense when the generated files are already there (e.g. when reusing parts of other experiments)')
- for skip in skips:
- skip_group.add_argument('--skip-%s' % skip, action='store_true', help = 'Skip the %s step.' % skip)
- skip_group.add_argument('-o', '--execute-only', nargs = '+', choices = skips, help = 'If specified, executes only the given parts of the tool chain.')
+ args = command_line_skip_group(parsers, command_line_parameters, skips)
+ args_dictionary = {'required': ['database', 'preprocessor', 'extractor', 'algorithm', 'sub_directory'],
+ 'common': ['protocol', 'grid', 'parallel', 'verbose', 'groups', 'temp_directory',
+ 'result_directory', 'zt_norm', 'allow_missing_files', 'dry_run', 'force'],
+ 'optional': ['preprocessed_directory', 'extracted_directory', 'projected_directory',
+ 'model_directories', 'extractor_file', 'projector_file', 'enroller_file']
+ }
+ keywords = (
+ "protocol",
+ "groups",
+ "parallel",
+ "preferred_package",
+ "temp_directory",
+ "result_directory",
+ "extractor_file",
+ "projector_file",
+ "enroller_file",
+ "gridtk_database_file",
+ "experiment_info_file",
+ "database_directories_file",
+ "preprocessed_directory",
+ "extracted_directory",
+ "projected_directory",
+ "model_directories",
+ "score_directories",
+ "zt_directories",
+ "grid_log_directory",
+ "verbose",
+ "dry_run",
+ "force",
+ "write_compressed_score_files",
+ "stop_on_failure",
+ "run_local_scheduler",
+ "external_dependencies",
+ "timer",
+ "nice",
+ "delete_jobs_finished_with_status",
+ "calibrate_scores",
+ "zt_norm",
+ "allow_missing_files",
+ "env",
+ )
+ args = parse_config_file(parsers, args, args_dictionary, keywords, skips)
- # parse the arguments
- parser = parsers['main']
- args = parser.parse_args(command_line_parameters)
-
-
- # check if the "create_configuration_file" function was requested
- if args.create_configuration_file is not None:
- # update list of options to be written into the config file
- set_required_common_optional_arguments(
- required = ['database', 'preprocessor', 'extractor', 'algorithm', 'sub_directory'],
- common = ['protocol', 'grid', 'parallel', 'verbose', 'groups', 'temp_directory', 'result_directory', 'zt_norm', 'allow_missing_files', 'dry_run', 'force'],
- optional = ['preprocessed_directory', 'extracted_directory', 'projected_directory', 'model_directories', 'extractor_file', 'projector_file', 'enroller_file']
- )
- # this will exit at the end
- _create_configuration_file(parsers, args)
-
- # first, read the configuration file and set everything from the config file to the args -- as long as not overwritten on command line
- config = utils.read_config_file(args.configuration_file) if args.configuration_file else None
- for keyword in ("database", "preprocessor", "extractor", "algorithm"):
- _take_from_config_or_command_line(args, config, keyword,
- parser.get_default(keyword))
-
- _take_from_config_or_command_line(args, config, "grid",
- parser.get_default('grid'), required=False)
-
- _take_from_config_or_command_line(args, config, "sub_directory",
- parser.get_default("sub_directory"), is_resource=False)
-
- skip_keywords = tuple(['skip_' + k.replace('-', '_') for k in skips])
-
- for keyword in (
- "protocol",
- "groups",
- "parallel",
- "preferred_package",
- "temp_directory",
- "result_directory",
- "extractor_file",
- "projector_file",
- "enroller_file",
- "gridtk_database_file",
- "experiment_info_file",
- "database_directories_file",
- "preprocessed_directory",
- "extracted_directory",
- "projected_directory",
- "model_directories",
- "score_directories",
- "zt_directories",
- "grid_log_directory",
- "verbose",
- "dry_run",
- "force",
- "write_compressed_score_files",
- "stop_on_failure",
- "run_local_scheduler",
- "external_dependencies",
- "timer",
- "nice",
- "delete_jobs_finished_with_status",
- "calibrate_scores",
- "zt_norm",
- "allow_missing_files",
- "env",
- ) + skip_keywords:
- _take_from_config_or_command_line(args, config, keyword,
- parser.get_default(keyword), required=False, is_resource=False)
-
- # check that all variables in the config file are consumed by the above options
- _check_config_consumed(config)
-
- # evaluate skips
- if skips is not None and args.execute_only is not None:
- for skip in skips:
- if skip not in args.execute_only:
- setattr(args, "skip_%s" % skip.replace("-", "_"), True)
-
- if args.parallel is not None:
- args.grid = bob.bio.base.grid.Grid("local", number_of_parallel_processes = args.parallel)
- args.run_local_scheduler = True
- args.stop_on_failure = True
-
- # logging
- bob.core.log.set_verbosity_level(logger, args.verbose)
-
- # timer
- if args.timer is not None and not len(args.timer):
- args.timer = ('real', 'system', 'user')
-
-
- # set base directories
- if args.temp_directory is None:
- args.temp_directory = "/idiap/temp/%s/%s" % (os.environ["USER"], args.database.name) if is_idiap() else "temp"
- if args.result_directory is None:
- args.result_directory = "/idiap/user/%s/%s" % (os.environ["USER"], args.database.name) if is_idiap() else "results"
-
- args.temp_directory = os.path.join(args.temp_directory, args.sub_directory)
- args.result_directory = os.path.join(args.result_directory, args.sub_directory)
- args.grid_log_directory = os.path.join(args.temp_directory, args.grid_log_directory)
+ args = set_extra_flags(args)
# protocol command line override
if args.protocol is not None:
@@ -340,9 +432,12 @@ def initialize(parsers, command_line_parameters = None, skips = []):
args.info_file = os.path.join(args.result_directory, protocol, args.experiment_info_file)
# sub-directorues that depend on the database
- extractor_sub_dir = protocol if args.database.training_depends_on_protocol and args.extractor.requires_training else '.'
- projector_sub_dir = protocol if args.database.training_depends_on_protocol and args.algorithm.requires_projector_training else extractor_sub_dir
- enroller_sub_dir = protocol if args.database.training_depends_on_protocol and args.algorithm.requires_enroller_training else projector_sub_dir
+ extractor_sub_dir = protocol if args.database.training_depends_on_protocol and \
+ args.extractor.requires_training else '.'
+ projector_sub_dir = protocol if args.database.training_depends_on_protocol and \
+ args.algorithm.requires_projector_training else extractor_sub_dir
+ enroller_sub_dir = protocol if args.database.training_depends_on_protocol and \
+ args.algorithm.requires_enroller_training else projector_sub_dir
model_sub_dir = protocol if args.database.models_depend_on_protocol else enroller_sub_dir
# Database directories, which should be automatically replaced
@@ -373,7 +468,8 @@ def groups(args):
"""groups(args) -> groups
Returns the groups, for which the files must be preprocessed, and features must be extracted and projected.
- This function should be used in order to eliminate the training files (the ``'world'`` group), when no training is required in this experiment.
+ This function should be used in order to eliminate the training files (the ``'world'`` group),
+ when no training is required in this experiment.
**Parameters:**
@@ -386,7 +482,8 @@ def groups(args):
A list of groups, for which data needs to be treated.
"""
groups = args.groups[:]
- if args.extractor.requires_training or args.algorithm.requires_projector_training or args.algorithm.requires_enroller_training:
+ if args.extractor.requires_training or args.algorithm.requires_projector_training or \
+ args.algorithm.requires_enroller_training:
groups.append('world')
return groups
@@ -395,7 +492,8 @@ def command_line(cmdline):
"""command_line(cmdline) -> str
Converts the given options to a string that can be executed in a terminal.
- Parameters are enclosed into ``'...'`` quotes so that the command line can interpret them (e.g., if they contain spaces or special characters).
+ Parameters are enclosed into ``'...'`` quotes so that the command line can interpret them (e.g.,
+ if they contain spaces or special characters).
**Parameters:**
@@ -429,7 +527,7 @@ def write_info(args, command_line_parameters, executable):
If ``None``, the parameters specified by the user on command line are considered.
executable : str
- The name of the executable (such as ``'verify.py'``) that is used to run the experiments.
+ The name of the executable (such as ``'./bin/verify.py'``) that is used to run the experiments.
"""
if command_line_parameters is None:
command_line_parameters = sys.argv[1:]
@@ -458,7 +556,7 @@ def set_required_common_optional_arguments(required = [], common = [], optional
_common_list.update(common)
_optional_list.update(optional)
-def _create_configuration_file(parsers, args):
+def create_configuration_file(parsers, args):
"""This function writes an empty configuration file with all possible options."""
logger.info("Writing configuration file %s", args.create_configuration_file)
import datetime
diff --git a/bob/bio/base/utils/resources.py b/bob/bio/base/utils/resources.py
index f49652ff833863aa5bf125a4e0fd9c9b0b3735a9..1b4264d25cca02256b3eab8691e017efb3de1c14 100644
--- a/bob/bio/base/utils/resources.py
+++ b/bob/bio/base/utils/resources.py
@@ -240,9 +240,10 @@ def extensions(keywords=valid_keywords, package_prefix='bob.bio.'):
def resource_keys(keyword, exclude_packages=[], package_prefix='bob.bio.', strip=['dummy']):
"""Reads and returns all resources that are registered with the given keyword.
Entry points from the given ``exclude_packages`` are ignored."""
- return sorted([entry_point.name for entry_point in
+ ret_list = [entry_point.name for entry_point in
_get_entry_points(keyword, strip=strip, package_prefix=package_prefix)
- if entry_point.dist.project_name not in exclude_packages])
+ if entry_point.dist.project_name not in exclude_packages]
+ return sorted(ret_list)
def list_resources(keyword, strip=['dummy'], package_prefix='bob.bio.', verbose=False, packages=None):