diff --git a/bob/bio/base/__init__.py b/bob/bio/base/__init__.py
index 5b2461a9b9400164f5010f4413fbabf26d2c17b3..48dbde118eeb3b217a39ed298c8f7c45e6065dfc 100644
--- a/bob/bio/base/__init__.py
+++ b/bob/bio/base/__init__.py
@@ -1,5 +1,4 @@
from .utils import *
-from . import database
from . import preprocessor
from . import extractor
from . import algorithm
diff --git a/bob/bio/base/database/Database.py b/bob/bio/base/database/Database.py
deleted file mode 100644
index cb9cc675149c819307f025922e467fbd5cd41e04..0000000000000000000000000000000000000000
--- a/bob/bio/base/database/Database.py
+++ /dev/null
@@ -1,490 +0,0 @@
-class Database:
- """This class represents the basic API for database access.
- Please use this class as a base class for your database access classes.
- Do not forget to call the constructor of this base class in your derived class.
-
- **Parameters:**
-
- name : str
- A unique name for the database.
-
- original_directory : str
- The directory where the original data of the database are stored.
-
- original_extension : str
- The file name extension of the original data.
-
- annotation_directory : str
- The directory where the image annotations of the database are stored, if any.
-
- annotation_extension : str
- The file name extension of the annotation files.
-
- annotation_type : str
- The type of the annotation file to read, see :py:func:`bob.db.verification.utils.read_annotation_file` for accepted formats.
-
- protocol : str or ``None``
- The name of the protocol that defines the default experimental setup for this database.
-
- .. todo:: Check if the ``None`` protocol is supported.
-
- training_depends_on_protocol : bool
- Specifies, if the training set used for training the extractor and the projector depend on the protocol.
- This flag is used to avoid re-computation of data when running on the different protocols of the same database.
-
- models_depend_on_protocol : bool
- Specifies, if the models depend on the protocol.
- This flag is used to avoid re-computation of models when running on the different protocols of the same database.
-
- kwargs
- Ignored extra arguments.
- """
-
- def __init__(
- self,
- name,
- original_directory = None,
- original_extension = None,
- annotation_directory = None,
- annotation_extension = '.pos',
- annotation_type = None,
- protocol = 'Default',
- training_depends_on_protocol = False,
- models_depend_on_protocol = False,
- **kwargs
- ):
- assert isinstance(name, str)
-
- self.name = name
- self.original_directory = original_directory
- self.original_extension = original_extension
- self.annotation_directory = annotation_directory
- self.annotation_extension = annotation_extension
- self.annotation_type = annotation_type
- self.protocol = protocol
- self.training_depends_on_protocol = training_depends_on_protocol
- self.models_depend_on_protocol = models_depend_on_protocol
-
-
- def __str__(self):
- """__str__() -> info
-
- This function returns all parameters of this class.
-
- **Returns:**
-
- info : str
- A string containing the full information of all parameters of this class.
- """
- params = "name=%s, protocol=%s, original_directory=%s, original_extension=%s" % (self.name, self.protocol, self.original_directory, self.original_extension)
- if self.annotation_type is not None:
- params += ", annotation_type=%s" % annotation_type
- if self.annotation_directory: params += ", annotation_directory=%s" % self.annotation_directory
- params += ", annotation_extension=%s" % self.annotation_extension
- params += ", training_depends_on_protocol=%s, models_depend_on_protocol=%s" % (self.training_depends_on_protocol, self.models_depend_on_protocol)
- return "%s(%s)" % (str(self.__class__), params)
-
-
- ###########################################################################
- ### Helper functions that you might want to use in derived classes
- ###########################################################################
- def sort(self, files):
- """sort(files) -> sorted
-
- Returns a sorted version of the given list of File's (or other structures that define an 'id' data member).
- The files will be sorted according to their id, and duplicate entries will be removed.
-
- **Parameters:**
-
- files : [:py:class:`File`]
- The list of files to be uniquified and sorted.
-
- **Returns:**
-
- sorted : [:py:class:`File`]
- The sorted list of files, with duplicate :py:attr:`File.id`\s being removed.
- """
- # sort files using their sort function
- sorted_files = sorted(files)
- # remove duplicates
- return [f for i,f in enumerate(sorted_files) if not i or sorted_files[i-1].id != f.id]
-
-
- def arrange_by_client(self, files):
- """arrange_by_client(files) -> files_by_client
-
- Arranges the given list of files by client id.
- This function returns a list of lists of File's.
-
- **Parameters:**
-
- files : :py:class:`File`
- A list of files that should be split up by :py:attr:`File.client_id`.
-
- **Returns:**
-
- files_by_client : [[:py:class:`File`]]
- The list of lists of files, where each sub-list groups the files with the same :py:attr:`File.client_id`
- """
- client_files = {}
- for file in files:
- if file.client_id not in client_files:
- client_files[file.client_id] = []
- client_files[file.client_id].append(file)
-
- files_by_clients = []
- for client in sorted(client_files.keys()):
- files_by_clients.append(client_files[client])
- return files_by_clients
-
-
- def annotations(self, file):
- """annotations(file) -> annots
-
- Returns the annotations for the given File object, if available.
- It uses :py:func:`bob.db.verification.utils.read_annotation_file` to load the annotations.
-
- **Parameters:**
-
- file : :py:class:`File`
- The file for which annotations should be returned.
-
- **Returns:**
-
- annots : dict or None
- The annotations for the file, if available.
- """
- if self.annotation_directory:
- try:
- import bob.db.verification.utils
- annotation_path = os.path.join(self.annotation_directory, file.path + self.annotation_extension)
- return bob.db.verification.utils.read_annotation_file(annotation_path, self.annotation_type)
- except ImportError as e:
- from .. import utils
- utils.error("Cannot import bob.db.verification.utils: '%s'. No annotation is read." % e)
-
- return None
-
-
- def uses_probe_file_sets(self):
- """Defines if, for the current protocol, the database uses several probe files to generate a score.
- By default, ``False`` is returned. Overwrite the default if you need different behavior."""
- return False
-
-
- def file_names(self, files, directory, extension):
- """file_names(files, directory, extension) -> paths
-
- Returns the full path of the given File objects.
-
- **Parameters:**
-
- files : [:py:class:`File`]
- The list of file object to retrieve the file names for.
-
- directory : str
- The base directory, where the files can be found.
-
- extension : str
- The file name extension to add to all files.
-
- **Returns:**
-
- paths : [str] or [[str]]
- The paths extracted for the files, in the same order.
- If this database provides file sets, a list of lists of file names is returned, one sub-list for each file set.
- """
- # return the paths of the files
- if self.uses_probe_file_sets() and files and hasattr(files[0], 'files'):
- # List of Filesets: do not remove duplicates
- return [[f.make_path(directory, extension) for f in file_set.files] for file_set in files]
- else:
- # List of files, do not remove duplicates
- return [f.make_path(directory, extension) for f in files]
-
- def original_file_names(self, files):
- """original_file_names(files) -> paths
-
- Returns the full path of the original data of the given File objects.
-
- **Parameters:**
-
- files : [:py:class:`File`]
- The list of file object to retrieve the original data file names for.
-
- **Returns:**
-
- paths : [str] or [[str]]
- The paths extracted for the files, in the same order.
- If this database provides file sets, a list of lists of file names is returned, one sub-list for each file set.
- """
- assert self.original_directory is not None
- assert self.original_extension is not None
- return self.file_names(files, self.original_directory, self.original_extension)
-
-
- ###########################################################################
- ### Interface functions that you need to implement in your class.
- ###########################################################################
-
- def all_files(self, groups = None):
- """all_files(groups=None) -> files
-
- Returns all files of the database.
- This function needs to be implemented in derived class implementations.
-
- **Parameters:**
-
- groups : some of ``('world', 'dev', 'eval')`` or ``None``
- The groups to get the data for.
- If ``None``, data for all groups is returned.
-
- **Returns:**
-
- files : [:py:class:`File`]
- The sorted and unique list of all files of the database.
- """
- raise NotImplementedError("Please implement this function in derived classes")
-
-
- def training_files(self, step = None, arrange_by_client = False):
- """training_files(step = None, arrange_by_client = False) -> files
-
- Returns all training File objects for the given step, and arranges them by client, if desired.
- This function needs to be implemented in derived class implementations.
-
- **Parameters:**
-
- step : one of ``('train_extractor', 'train_projector', 'train_enroller')`` or ``None``
- The step for which the training data should be returned.
- Might be ignored in derived class implementations.
-
- arrange_by_client : bool
- Should the training files be arranged by client?
-
- .. note::
- You can use :py:meth:`arrange_by_client` in derived class implementations to arrange the files.
-
- **Returns:**
-
- files : [:py:class:`File`] or [[:py:class:`File`]]
- The (arranged) list of files used for the training of the given step.
- """
- raise NotImplementedError("Please implement this function in derived classes")
-
-
- def model_ids(self, group = 'dev'):
- """model_ids(group = 'dev') -> ids
-
- Returns a list of model ids for the given group.
- This function needs to be implemented in derived class implementations.
-
- **Parameters:**
-
- group : one of ``('dev', 'eval')``
- The group to get the model ids for.
-
- **Returns:**
-
- ids : [int] or [str]
- The list of (unique) model ids for the given group.
- """
- raise NotImplementedError("Please implement this function in derived classes")
-
-
- def client_id_from_model_id(self, model_id, group = 'dev'):
- """client_id_from_model_id(model_id, group = 'dev') -> client_id
-
- In some databases, each client can contain several models.
- Hence, client and model ids differ.
- This function converts the given model id into its according the client id.
- This function needs to be implemented in derived class implementations.
-
- **Parameters:**
-
- model_id : int or str
- A unique ID that identifies the model for the client.
-
- group : one of ``('dev', 'eval')``
- The group to get the client ids for.
-
- **Returns:**
-
- client_id : [int] or [str]
- A unique ID that identifies the client, to which the model belongs.
- """
- raise NotImplementedError("Please implement this function in derived classes")
-
-
- def enroll_files(self, model_id, group = 'dev'):
- """enroll_files(model_id, group = 'dev') -> files
-
- Returns a list of File objects that should be used to enroll the model with the given model id from the given group.
- This function needs to be implemented in derived class implementations.
-
- **Parameters:**
-
- model_id : int or str
- A unique ID that identifies the model.
-
- group : one of ``('dev', 'eval')``
- The group to get the enrollment files for.
-
- **Returns:**
-
- files : [:py:class:`File`]
- The list of files used for to enroll the model with the given model id.
- """
- raise NotImplementedError("Please implement this function in derived classes")
-
-
- def probe_files(self, model_id = None, group = 'dev'):
- """probe_files(model_id = None, group = 'dev') -> files
-
- Returns a list of probe File objects.
- If a ``model_id`` is specified, only the probe files that should be compared with the given model id are returned (for most databases, these are all probe files of the given group).
- Otherwise, all probe files of the given group are returned.
- This function needs to be implemented in derived class implementations.
-
- **Parameters:**
-
- model_id : int or str or ``None``
- A unique ID that identifies the model.
-
- group : one of ``('dev', 'eval')``
- The group to get the enrollment files for.
-
- **Returns:**
-
- files : [:py:class:`File`]
- The list of files used for to probe the model with the given model id.
- """
- raise NotImplementedError("Please implement this function in derived classes")
-
-
- def probe_file_sets(self, model_id = None, group = 'dev'):
- """probe_file_sets(model_id = None, group = 'dev') -> files
-
- Returns a list of probe FileSet objects.
- If a ``model_id`` is specified, only the probe files that should be compared with the given model id are returned (for most databases, these are all probe files of the given group).
- Otherwise, all probe files of the given group are returned.
- This function needs to be implemented in derived class implementations, if the :py:meth:`uses_probe_file_sets` returns ``True``.
-
- **Parameters:**
-
- model_id : int or str or ``None``
- A unique ID that identifies the model.
-
- group : one of ``('dev', 'eval')``
- The group to get the enrollment files for.
-
- **Returns:**
-
- files : [:py:class:`FileSet`]
- The list of file sets used to probe the model with the given model id."""
- raise NotImplementedError("Please implement this function in derived classes")
-
-
-
-class DatabaseZT (Database):
- """This class defines additional API functions that are required to compute ZT score normalization.
- This class does not define a constructor.
- During construction of a derived class, please call the constructor of the base class :py:class:`Database` directly."""
-
- def t_model_ids(self, group = 'dev'):
- """t_model_ids(group = 'dev') -> ids
-
- Returns a list of model ids of T-Norm models for the given group.
- This function needs to be implemented in derived class implementations.
-
- **Parameters:**
-
- group : one of ``('dev', 'eval')``
- The group to get the model ids for.
-
- **Returns:**
-
- ids : [int] or [str]
- The list of (unique) model ids for T-Norm models of the given group.
- """
- raise NotImplementedError("Please implement this function in derived classes")
-
-
- def client_id_from_t_model_id(self, t_model_id, group = 'dev'):
- """client_id_from_t_model_id(t_model_id, group = 'dev') -> client_id
-
- Returns the client id for the given T-Norm model id.
- In this base class implementation, we just use the :py:meth:`client_id_from_model_id` function.
- Overload this function if you need another behavior.
-
- **Parameters:**
-
- t_model_id : int or str
- A unique ID that identifies the T-Norm model.
-
- group : one of ``('dev', 'eval')``
- The group to get the client ids for.
-
- **Returns:**
-
- client_id : [int] or [str]
- A unique ID that identifies the client, to which the T-Norm model belongs.
- """
- return self.client_id_from_model_id(t_model_id, group)
-
- def t_enroll_files(self, t_model_id, group = 'dev'):
- """t_enroll_files(t_model_id, group = 'dev') -> files
-
- Returns a list of File objects that should be used to enroll the T-Norm model with the given model id from the given group.
- This function needs to be implemented in derived class implementations.
-
- **Parameters:**
-
- t_model_id : int or str
- A unique ID that identifies the model.
-
- group : one of ``('dev', 'eval')``
- The group to get the enrollment files for.
-
- **Returns:**
-
- files : [:py:class:`File`]
- The list of files used for to enroll the model with the given model id.
- """
- raise NotImplementedError("Please implement this function in derived classes")
-
- def z_probe_files(self, group = 'dev'):
- """z_probe_files(group = 'dev') -> files
-
- Returns a list of probe File objects used to compute the Z-Norm.
- This function needs to be implemented in derived class implementations.
-
- **Parameters:**
-
- group : one of ``('dev', 'eval')``
- The group to get the Z-norm probe files for.
-
- **Returns:**
-
- files : [:py:class:`File`]
- The unique list of files used to compute the Z-norm.
- """
- raise NotImplementedError("Please implement this function in derived classes")
-
- def z_probe_file_sets(self, group = 'dev'):
- """z_probe_file_sets(group = 'dev') -> files
-
- Returns a list of probe FileSet objects used to compute the Z-Norm.
- This function needs to be implemented in derived class implementations.
-
- **Parameters:**
-
- group : one of ``('dev', 'eval')``
- The group to get the Z-norm probe files for.
-
- **Returns:**
-
- files : [:py:class:`FileSet`]
- The unique list of file sets used to compute the Z-norm.
- """
- raise NotImplementedError("Please implement this function in derived classes")
diff --git a/bob/bio/base/database/DatabaseBob.py b/bob/bio/base/database/DatabaseBob.py
deleted file mode 100644
index 38d7857770324d9d7d9eb7616ef5307b3fb6610a..0000000000000000000000000000000000000000
--- a/bob/bio/base/database/DatabaseBob.py
+++ /dev/null
@@ -1,505 +0,0 @@
-from .Database import Database, DatabaseZT
-import os
-
-import bob.db.verification.utils
-
-class DatabaseBob (Database):
- """This class can be used whenever you have a database that follows the Bob verification database interface, which is defined in :py:class:`bob.db.verification.utils.Database`
-
- **Parameters:**
-
- database : derivative of :py:class:`bob.db.verification.utils.Database`
- The database instance (such as a :py:class:`bob.db.atnt.Database`) that provides the actual interface, see :ref:`verification_databases` for a list.
-
- all_files_options : dict
- Dictionary of options passed to the :py:meth:`bob.db.verification.utils.Database.objects` database query when retrieving all data.
-
- extractor_training_options : dict
- Dictionary of options passed to the :py:meth:`bob.db.verification.utils.Database.objects` database query used to retrieve the files for the extractor training.
-
- projector_training_options : dict
- Dictionary of options passed to the :py:meth:`bob.db.verification.utils.Database.objects` database query used to retrieve the files for the projector training.
-
- enroller_training_options : dict
- Dictionary of options passed to the :py:meth:`bob.db.verification.utils.Database.objects` database query used to retrieve the files for the enroller training.
-
- check_original_files_for_existence : bool
- Enables to test for the original data files when querying the database.
-
- kwargs : ``key=value`` pairs
- The arguments of the :py:class:`Database` base class constructor.
-
- .. note:: Usually, the ``name``, ``protocol``, ``training_depends_on_protocol`` and ``models_depend_on_protocol`` keyword parameters of the base class constructor need to be specified.
- """
-
- def __init__(
- self,
- database, # The bob database that is used
- all_files_options = {}, # additional options for the database query that can be used to extract all files
- extractor_training_options = {}, # additional options for the database query that can be used to extract the training files for the extractor training
- projector_training_options = {}, # additional options for the database query that can be used to extract the training files for the extractor training
- enroller_training_options = {}, # additional options for the database query that can be used to extract the training files for the extractor training
- check_original_files_for_existence = False,
- **kwargs # The default parameters of the base class
- ):
-
- Database.__init__(
- self,
- **kwargs
- )
-
- assert isinstance(database, bob.db.verification.utils.Database), "Only databases derived from bob.db.verification.utils.Database are supported by this interface. Please implement your own bob.bio.base.database.Database interface."
-
- self.database = database
- self.original_directory = database.original_directory
- try:
- self.annotation_directory = database.annotation_directory
- except AttributeError:
- pass
-
- self.all_files_options = all_files_options
- self.extractor_training_options = extractor_training_options
- self.projector_training_options = projector_training_options
- self.enroller_training_options = enroller_training_options
- self.check_existence = check_original_files_for_existence
-
- self._kwargs = kwargs
-
-
- def __str__(self):
- """__str__() -> info
-
- This function returns all parameters of this class (and its derived class).
-
- **Returns:**
-
- info : str
- A string containing the full information of all parameters of this (and the derived) class.
- """
- params = ", ".join(["%s=%s" % (key, value) for key, value in self._kwargs.items()])
- params += ", original_directory=%s, original_extension=%s" % (self.original_directory, self.original_extension)
- if self.all_files_options: params += ", all_files_options=%s"%self.all_files_options
- if self.extractor_training_options: params += ", extractor_training_options=%s"%self.extractor_training_options
- if self.projector_training_options: params += ", projector_training_options=%s"%self.projector_training_options
- if self.enroller_training_options: params += ", enroller_training_options=%s"%self.enroller_training_options
-
- return "%s(%s)" % (str(self.__class__), params)
-
-
- def replace_directories(self, replacements = None):
- """This helper function replaces the ``original_directory`` and the ``annotation_directory`` of the database with the directories read from the given replacement file.
-
- This function is provided for convenience, so that the database configuration files do not need to be modified.
- Instead, this function uses the given dictionary of replacements to change the original directory and the original extension (if given).
-
- The given ``replacements`` can be of type ``dict``, including all replacements, or a file name (as a ``str``), in which case the file is read.
- The structure of the file should be:
-
- .. code-block:: text
-
- # Comments starting with # and empty lines are ignored
-
- [YOUR_..._DATA_DIRECTORY] = /path/to/your/data
- [YOUR_..._ANNOTATION_DIRECTORY] = /path/to/your/annotations
-
- If no annotation files are available (e.g. when they are stored inside the ``database``), the annotation directory can be left out.
-
- **Parameters:**
-
- replacements : dict or str
- A dictionary with replacements, or a name of a file to read the dictionary from.
- If the file name does not exist, no directories are replaced.
- """
- if replacements is None:
- return
- if isinstance(replacements, str):
- if not os.path.exists(replacements):
- return
- # Open the database replacement file and reads its content
- with open(replacements) as f:
- replacements = {}
- for line in f:
- if line.strip() and not line.startswith("#"):
- splits = line.split("=")
- assert len(splits) == 2
- replacements[splits[0].strip()] = splits[1].strip()
-
- assert isinstance(replacements, dict)
-
- if self.original_directory in replacements:
- self.original_directory = replacements[self.original_directory]
- self.database.original_directory = replacements[self.database.original_directory]
-
- try:
- if self.annotation_directory in replacements:
- self.annotation_directory = replacements[self.annotation_directory]
- self.database.annotation_directory = replacements[self.database.annotation_directory]
- except AttributeError:
- pass
-
-
- def uses_probe_file_sets(self):
- """Defines if, for the current protocol, the database uses several probe files to generate a score."""
- return self.database.provides_file_set_for_protocol(self.protocol)
-
-
- def all_files(self, groups = None):
- """all_files(groups=None) -> files
-
- Returns all files of the database, respecting the current protocol.
- The files can be limited using the ``all_files_options`` in the constructor.
-
- **Parameters:**
-
- groups : some of ``('world', 'dev', 'eval')`` or ``None``
- The groups to get the data for.
- If ``None``, data for all groups is returned.
-
- **Returns:**
-
- files : [:py:class:`bob.db.verification.utils.File`]
- The sorted and unique list of all files of the database.
- """
- return self.sort(self.database.objects(protocol = self.protocol, groups = groups, **self.all_files_options))
-
-
- def training_files(self, step = None, arrange_by_client = False):
- """training_files(step = None, arrange_by_client = False) -> files
-
- Returns all training files for the given step, and arranges them by client, if desired, respecting the current protocol.
- The files for the steps can be limited using the ``..._training_options`` defined in the constructor.
-
- **Parameters:**
-
- step : one of ``('train_extractor', 'train_projector', 'train_enroller')`` or ``None``
- The step for which the training data should be returned.
-
- arrange_by_client : bool
- Should the training files be arranged by client?
- If set to ``True``, training files will be returned in [[:py:class:`bob.db.verification.utils.File`]], where each sub-list contains the files of a single client.
- Otherwise, all files will be stored in a simple [:py:class:`bob.db.verification.utils.File`].
-
- **Returns:**
-
- files : [:py:class:`bob.db.verification.utils.File`] or [[:py:class:`bob.db.verification.utils.File`]]
- The (arranged) list of files used for the training of the given step.
- """
- if step is None:
- training_options = self.all_files_options
- elif step == 'train_extractor':
- training_options = self.extractor_training_options
- elif step == 'train_projector':
- training_options = self.projector_training_options
- elif step == 'train_enroller':
- training_options = self.enroller_training_options
- else:
- raise ValueError("The given step '%s' must be one of ('train_extractor', 'train_projector', 'train_enroller')" % step)
-
- files = self.sort(self.database.objects(protocol = self.protocol, groups = 'world', **training_options))
- if arrange_by_client:
- return self.arrange_by_client(files)
- else:
- return files
-
- def test_files(self, groups = ['dev']):
- """test_files(groups = ['dev']) -> files
-
- Returns all test files (i.e., files used for enrollment and probing) for the given groups, respecting the current protocol.
- The files for the steps can be limited using the ``all_files_options`` defined in the constructor.
-
- **Parameters:**
-
- groups : some of ``('dev', 'eval')``
- The groups to get the data for.
-
- **Returns:**
-
- files : [:py:class:`bob.db.verification.utils.File`]
- The sorted and unique list of test files of the database.
- """
- return self.sort(self.database.test_files(protocol = self.protocol, groups = groups, **self.all_files_options))
-
- def model_ids(self, group = 'dev'):
- """model_ids(group = 'dev') -> ids
-
- Returns a list of model ids for the given group, respecting the current protocol.
-
- **Parameters:**
-
- group : one of ``('dev', 'eval')``
- The group to get the model ids for.
-
- **Returns:**
-
- ids : [int] or [str]
- The list of (unique) model ids for the given group.
- """
- return sorted(self.database.model_ids(protocol = self.protocol, groups = group))
-
-
- def client_id_from_model_id(self, model_id, group = 'dev'):
- """client_id_from_model_id(model_id, group = 'dev') -> client_id
-
- Uses :py:meth:`bob.db.verification.utils.Database.get_client_id_from_model_id` to retrieve the client id for the given model id.
-
- **Parameters:**
-
- model_id : int or str
- A unique ID that identifies the model for the client.
-
- group : one of ``('dev', 'eval')``
- The group to get the client ids for.
-
- **Returns:**
-
- client_id : [int] or [str]
- A unique ID that identifies the client, to which the model belongs.
- """
- return self.database.get_client_id_from_model_id(model_id)
-
-
- def enroll_files(self, model_id, group = 'dev'):
- """enroll_files(model_id, group = 'dev') -> files
-
- Returns a list of File objects that should be used to enroll the model with the given model id from the given group, respecting the current protocol.
-
- **Parameters:**
-
- model_id : int or str
- A unique ID that identifies the model.
-
- group : one of ``('dev', 'eval')``
- The group to get the enrollment files for.
-
- **Returns:**
-
- files : [:py:class:`bob.db.verification.utils.File`]
- The list of files used for to enroll the model with the given model id.
- """
- return self.sort(self.database.objects(protocol = self.protocol, groups = group, model_ids = (model_id,), purposes = 'enroll', **self.all_files_options))
-
-
- def probe_files(self, model_id = None, group = 'dev'):
- """probe_files(model_id = None, group = 'dev') -> files
-
- Returns a list of probe File objects, respecting the current protocol.
- If a ``model_id`` is specified, only the probe files that should be compared with the given model id are returned (for most databases, these are all probe files of the given group).
- Otherwise, all probe files of the given group are returned.
-
- **Parameters:**
-
- model_id : int or str or ``None``
- A unique ID that identifies the model.
-
- group : one of ``('dev', 'eval')``
- The group to get the enrollment files for.
-
- **Returns:**
-
- files : [:py:class:`bob.db.verification.utils.File`]
- The list of files used for to probe the model with the given model id.
- """
- if model_id is not None:
- files = self.database.objects(protocol = self.protocol, groups = group, model_ids = (model_id,), purposes = 'probe', **self.all_files_options)
- else:
- files = self.database.objects(protocol = self.protocol, groups = group, purposes = 'probe', **self.all_files_options)
- return self.sort(files)
-
-
- def probe_file_sets(self, model_id = None, group = 'dev'):
- """probe_file_sets(model_id = None, group = 'dev') -> files
-
- Returns a list of probe FileSet objects, respecting the current protocol.
- If a ``model_id`` is specified, only the probe files that should be compared with the given model id are returned (for most databases, these are all probe files of the given group).
- Otherwise, all probe files of the given group are returned.
-
- **Parameters:**
-
- model_id : int or str or ``None``
- A unique ID that identifies the model.
-
- group : one of ``('dev', 'eval')``
- The group to get the enrollment files for.
-
- **Returns:**
-
- files : [:py:class:`FileSet`] or something similar
- The list of file sets used to probe the model with the given model id."""
- if model_id is not None:
- file_sets = self.database.object_sets(protocol = self.protocol, groups = group, model_ids = (model_id,), purposes = 'probe', **self.all_files_options)
- else:
- file_sets = self.database.object_sets(protocol = self.protocol, groups = group, purposes = 'probe', **self.all_files_options)
- return self.sort(file_sets)
-
-
- def annotations(self, file):
- """annotations(file) -> annots
-
- Returns the annotations for the given File object, if available.
-
- **Parameters:**
-
- file : :py:class:`bob.db.verification.utils.File`
- The file for which annotations should be returned.
-
- **Returns:**
-
- annots : dict or None
- The annotations for the file, if available.
- """
- return self.database.annotations(file)
-
-
- def original_file_names(self, files):
- """original_file_names(files) -> paths
-
- Returns the full path of the original data of the given File objects, as returned by :py:meth:`bob.db.verification.utils.Database.original_file_names`.
-
- **Parameters:**
-
- files : [:py:class:`bob.db.verification.utils.File`]
- The list of file object to retrieve the original data file names for.
-
- **Returns:**
-
- paths : [str]
- The paths extracted for the files, in the same order.
- """
- return self.database.original_file_names(files, self.check_existence)
-
-
-
-class DatabaseBobZT (DatabaseBob, DatabaseZT):
- """This class can be used whenever you have a database that follows the Bob ZT-norm verification database interface, which is defined in :py:class:`bob.db.verification.utils.ZTDatabase`.
-
- **Parameters:**
-
- database : derivative of :py:class:`bob.db.verification.utils.ZTDatabase`
- The database instance (such as a :py:class:`bob.db.mobio.Database`) that provides the actual interface, see :ref:`verification_databases` for a list.
-
- z_probe_options : dict
- Dictionary of options passed to the :py:meth:`bob.db.verification.utils.ZTDatabase.z_probe_files` database query when retrieving files for Z-probing.
-
- kwargs : ``key=value`` pairs
- The arguments of the :py:class:`DatabaseBob` base class constructor.
-
- .. note:: Usually, the ``name``, ``protocol``, ``training_depends_on_protocol`` and ``models_depend_on_protocol`` keyword parameters of the :py:class:`Database` base class constructor need to be specified.
- """
-
- def __init__(
- self,
- database,
- z_probe_options = {}, # Limit the z-probes
- **kwargs
- ):
-# assert isinstance(database, bob.db.verification.utils.ZTDatabase) // fails in tests
- # call base class constructor, passing all the parameters to it
- DatabaseBob.__init__(self, database = database, z_probe_options = z_probe_options, **kwargs)
-
- self.z_probe_options = z_probe_options
-
-
- def all_files(self, groups = ['dev']):
- """all_files(groups=None) -> files
-
- Returns all files of the database, including those for ZT norm, respecting the current protocol.
- The files can be limited using the ``all_files_options`` and the the ``z_probe_options`` in the constructor.
-
- **Parameters:**
-
- groups : some of ``('world', 'dev', 'eval')`` or ``None``
- The groups to get the data for.
- If ``None``, data for all groups is returned.
-
- **Returns:**
-
- files : [:py:class:`bob.db.verification.utils.File`]
- The sorted and unique list of all files of the database.
- """
- files = self.database.objects(protocol = self.protocol, groups = groups, **self.all_files_options)
-
- # add all files that belong to the ZT-norm
- for group in groups:
- if group == 'world': continue
- files += self.database.tobjects(protocol = self.protocol, groups = group, model_ids = None)
- files += self.database.zobjects(protocol = self.protocol, groups = group, **self.z_probe_options)
- return self.sort(files)
-
-
- def t_model_ids(self, group = 'dev'):
- """t_model_ids(group = 'dev') -> ids
-
- Returns a list of model ids of T-Norm models for the given group, respecting the current protocol.
-
- **Parameters:**
-
- group : one of ``('dev', 'eval')``
- The group to get the model ids for.
-
- **Returns:**
-
- ids : [int] or [str]
- The list of (unique) model ids for T-Norm models of the given group.
- """
- return sorted(self.database.t_model_ids(protocol = self.protocol, groups = group))
-
-
- def t_enroll_files(self, t_model_id, group = 'dev'):
- """t_enroll_files(t_model_id, group = 'dev') -> files
-
- Returns a list of File objects that should be used to enroll the T-Norm model with the given model id from the given group, respecting the current protocol.
-
- **Parameters:**
-
- t_model_id : int or str
- A unique ID that identifies the model.
-
- group : one of ``('dev', 'eval')``
- The group to get the enrollment files for.
-
- **Returns:**
-
- files : [:py:class:`bob.db.verification.utils.File`]
- The sorted list of files used for to enroll the model with the given model id.
- """
- return self.sort(self.database.t_enroll_files(protocol = self.protocol, groups = group, model_id = t_model_id))
-
-
- def z_probe_files(self, group = 'dev'):
- """z_probe_files(group = 'dev') -> files
-
- Returns a list of probe files used to compute the Z-Norm, respecting the current protocol.
- The Z-probe files can be limited using the ``z_probe_options`` in the query to :py:meth:`bob.db.verification.utils.ZTDatabase.z_probe_files`
-
- **Parameters:**
-
- group : one of ``('dev', 'eval')``
- The group to get the Z-norm probe files for.
-
- **Returns:**
-
- files : [:py:class:`bob.db.verification.utils.File`]
- The unique list of files used to compute the Z-norm.
- """
- files = self.database.z_probe_files(protocol = self.protocol, groups = group, **self.z_probe_options)
- return self.sort(files)
-
-
- def z_probe_file_sets(self, group = 'dev'):
- """z_probe_file_sets(group = 'dev') -> files
-
- Returns a list of probe FileSet objects used to compute the Z-Norm.
- The Z-probe files can be limited using the ``z_probe_options`` in the query to
-
- **Parameters:**
-
- group : one of ``('dev', 'eval')``
- The group to get the Z-norm probe files for.
-
- **Returns:**
-
- files : [:py:class:`FileSet`] or similar
- The unique list of file sets used to compute the Z-norm.
- """
- file_sets = self.database.z_probe_file_sets(protocol = self.protocol, groups = group, **self.z_probe_options)
- return self.sort(file_sets)
diff --git a/bob/bio/base/database/DatabaseFileList.py b/bob/bio/base/database/DatabaseFileList.py
deleted file mode 100644
index e78bf9465633f8295cb6f539e4d160b6614ec55c..0000000000000000000000000000000000000000
--- a/bob/bio/base/database/DatabaseFileList.py
+++ /dev/null
@@ -1,168 +0,0 @@
-#!/usr/bin/env python
-# vim: set fileencoding=utf-8 :
-# @author: Manuel Guenther <Manuel.Guenther@idiap.ch>
-# @date: Wed Oct 3 10:31:51 CEST 2012
-#
-# Copyright (C) 2011-2012 Idiap Research Institute, Martigny, Switzerland
-#
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, version 3 of the License.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-
-from .DatabaseBob import DatabaseBobZT
-import bob.db.verification.filelist
-
-class DatabaseFileList (DatabaseBobZT):
- """This class can be used whenever you have a database that uses the Bob filelist database interface, which is defined in :py:class:`bob.db.verification.filelist.Database`
-
- **Parameters:**
-
- database : a :py:class:`bob.db.verification.filelist.Database`
- The database instance that provides the actual interface.
-
- kwargs : ``key=value`` pairs
- The arguments of the :py:class:`DatabaseBobZT` or :py:class:`DatabaseBob` base class constructors.
-
- .. note:: Usually, the ``name``, ``protocol``, ``training_depends_on_protocol`` and ``models_depend_on_protocol`` keyword parameters of the base class constructor need to be specified.
- """
-
- def __init__(
- self,
- database, # The bob database that is used
- **kwargs # The default parameters of the base class
- ):
-
- DatabaseBobZT.__init__(
- self,
- database = database,
- **kwargs
- )
-
- assert isinstance(database, bob.db.verification.filelist.Database)
-
-
- def all_files(self, groups = ['dev']):
- """all_files(groups=None) -> files
-
- Returns all files of the database, respecting the current protocol.
- If the current protocol is ``'None'``, ``None`` will be used instead.
- When the underlying file list database provides files for ZT score normalization, these files are returned as well.
- The files can be limited using the ``all_files_options`` in the constructor.
-
- **Parameters:**
-
- groups : some of ``('world', 'dev', 'eval')`` or ``None``
- The groups to get the data for.
- If ``None``, data for all groups is returned.
-
- **Returns:**
-
- files : [:py:class:`bob.db.verification.filelist.File`]
- The sorted and unique list of all files of the database.
- """
- protocol = self.protocol if self.protocol != 'None' else None
- files = self.database.objects(protocol = protocol, groups = groups, **self.all_files_options)
-
- # add all files that belong to the ZT-norm
- for group in groups:
- if group == 'world': continue
- if self.database.implements_zt(protocol = protocol, groups = group):
- files += self.database.tobjects(protocol = protocol, groups = group, model_ids = None)
- files += self.database.zobjects(protocol = protocol, groups = group, **self.z_probe_options)
- return self.sort(files)
-
-
- def uses_probe_file_sets(self):
- """File sets are not (yet) supported in the :py:class:`bob.db.verification.filelist.Database`, so this function returns ``False`` throughout."""
- return False
-
-
- def model_ids(self, group = 'dev'):
- """model_ids(group = 'dev') -> ids
-
- Returns a list of model ids for the given group, respecting the current protocol.
- If the current protocol is ``'None'``, ``None`` will be used instead.
-
- **Parameters:**
-
- group : one of ``('dev', 'eval')``
- The group to get the model ids for.
-
- **Returns:**
-
- ids : [str]
- The list of (unique) model ids for the given group.
- """
- return sorted(self.database.model_ids(protocol = self.protocol if self.protocol != 'None' else None, groups = group))
-
-
- def client_id_from_model_id(self, model_id, group = 'dev'):
- """client_id_from_model_id(model_id, group = 'dev') -> client_id
-
- Uses :py:meth:`bob.db.verification.filelist.Database.get_client_id_from_model_id` to retrieve the client id for the given model id.
- If the current protocol is ``'None'``, ``None`` will be used instead.
-
- **Parameters:**
-
- model_id : str
- A unique ID that identifies the model for the client.
-
- group : one of ``('dev', 'eval')``
- The group to get the client ids for.
-
- **Returns:**
-
- client_id : str
- A unique ID that identifies the client, to which the model belongs.
- """
- return self.database.get_client_id_from_model_id(model_id, groups = group, protocol = self.protocol if self.protocol != 'None' else None)
-
-
- def client_id_from_t_model_id(self, t_model_id, group = 'dev'):
- """client_id_from_t_model_idt_(model_id, group = 'dev') -> client_id
-
- Uses :py:meth:`bob.db.verification.filelist.Database.get_client_id_from_t_model_id` to retrieve the client id for the T-norm given model id.
- If the current protocol is ``'None'``, ``None`` will be used instead.
-
- **Parameters:**
-
- t_model_id : str
- A unique ID that identifies the T-Norm model.
-
- group : one of ``('dev', 'eval')``
- The group to get the client ids for.
-
- **Returns:**
-
- client_id : str
- A unique ID that identifies the client, to which the T-Norm model belongs.
- """
- return self.database.get_client_id_from_tmodel_id(t_model_id, groups = group, protocol = self.protocol if self.protocol != 'None' else None)
-
-
- def t_model_ids(self, group = 'dev'):
- """t_model_ids(group = 'dev') -> ids
-
- Returns a list of model ids of T-Norm models for the given group, respecting the current protocol.
- If the current protocol is ``'None'``, ``None`` will be used instead.
-
- **Parameters:**
-
- group : one of ``('dev', 'eval')``
- The group to get the model ids for.
-
- **Returns:**
-
- ids : [int] or [str]
- The list of (unique) model ids for T-Norm models of the given group.
- """
- return sorted(self.database.tmodel_ids(protocol = self.protocol if self.protocol != 'None' else None, groups = group))
diff --git a/bob/bio/base/database/__init__.py b/bob/bio/base/database/__init__.py
deleted file mode 100644
index 945cd33ebec6cc299460208f41a20b86ee0eeea6..0000000000000000000000000000000000000000
--- a/bob/bio/base/database/__init__.py
+++ /dev/null
@@ -1,8 +0,0 @@
-from .utils import File, FileSet
-
-from .Database import Database, DatabaseZT
-from .DatabaseBob import DatabaseBob, DatabaseBobZT
-from .DatabaseFileList import DatabaseFileList
-
-# gets sphinx autodoc done right - don't remove it
-__all__ = [_ for _ in dir() if not _.startswith('_')]
diff --git a/bob/bio/base/database/utils.py b/bob/bio/base/database/utils.py
deleted file mode 100644
index 8473d07ef4123a15287e587318b57999da7818de..0000000000000000000000000000000000000000
--- a/bob/bio/base/database/utils.py
+++ /dev/null
@@ -1,97 +0,0 @@
-import os
-
-class File:
- """This class defines the minimum interface of a database file that needs to be exported.
-
- Each file has a path, an id and an associated client (aka. identity, person, user).
- Usually, this file is part of a database, which has a common directory for all files.
- The path of this file is usually *relative* to that common directory, and it is usually stored *without* filename extension.
- The file id can be anything hashable, but needs to be unique all over the database.
- The client id can be anything hashable, but needs to be identical for different files of the same client, and different between clients.
-
- **Parameters:**
-
- file_id : str or int
- A unique ID that identifies the file.
- This ID might be identical to the ``path``, though integral IDs perform faster.
-
- client_id : str or int
- A unique ID that identifies the client (user) to which this file belongs.
- This ID might be the name of the person, though integral IDs perform faster.
-
- path : str
- The file path of the file, which is relative to the common database directory, and without filename extension.
- """
-
- def __init__(self, file_id, client_id, path):
- # The **unique** id of the file
- self.id = file_id
- # The id of the client that is attached to the file
- self.client_id = client_id
- # The **relative** path of the file according to the base directory of the database, without file extension
- self.path = path
-
- def __lt__(self, other):
- """Defines an order between files by using the order of the file ids."""
- # compare two File objects by comparing their IDs
- return self.id < other.id
-
- def make_path(self, directory = None, extension = None):
- """make_path(directory = None, extension = None) -> path
-
- Generates the full path using the given directory and filename extension.
-
- **Parameters:**
-
- directory : str or ``None``
- The directory to prepend.
- If ``None``, no directory will be preprended.
-
- extension : str or ``None``
- The filename extension to append.
- If ``None``, no file name extension will be appended.
-
- **Returns:**
-
- path : str
- The full path including directory and extension.
- """
- if directory is None: directory = '.'
- if extension is None: extension = ''
-
- return os.path.join(directory, self.path + extension)
-
-
-class FileSet:
- """This class defines the minimum interface of a set of database files that needs to be exported.
-
- Use this class, whenever the database provides several files that belong to the same probe.
-
- Each file set has an id, and a list of associated files, which are of type :py:class:`File` of the same client.
- The file set id can be anything hashable, but needs to be unique all over the database.
-
- **Parameters:**
-
- file_set_id : str or int
- A unique ID that identifies the file set.
-
- files : [:py:class:`File`]
- A list of File objects that should be stored inside this file.
- All files of that list need to have the same client ID.
- """
-
- def __init__(self, file_set_id, files, path=None):
- # The **unique** id of the file set
- self.id = file_set_id
- # The id of the client that is attached to the file
- assert len(files)
- self.client_id = files[0].client_id
- assert all(f.client_id == self.client_id for f in files)
- # The list of files contained in this set
- self.files = files
- self.path = "+".join(f.path for f in files)
-
- def __lt__(self, other):
- """Defines an order between file sets by using the order of the file set ids."""
- # compare two File set objects by comparing their IDs
- return self.id < other.id
diff --git a/bob/bio/base/test/dummy/database.py b/bob/bio/base/test/dummy/database.py
index 90c440ea290a024c93fe3fbc5648556fca6f7d0b..c79f36e33a57d45b955d1b20fe2e4f6c0321e696 100644
--- a/bob/bio/base/test/dummy/database.py
+++ b/bob/bio/base/test/dummy/database.py
@@ -1,34 +1,40 @@
-import bob.db.atnt
-import os
-
-from bob.bio.base.database import DatabaseBob, DatabaseBobZT
+from bob.bio.db import ZTBioDatabase, AtntBioDatabase
from bob.bio.base.test.utils import atnt_database_directory
-class DummyDatabase (DatabaseBobZT):
- def __init__(self):
- # call base class constructor with useful parameters
- DatabaseBobZT.__init__(
- self,
- database = bob.db.atnt.Database(
- original_directory = atnt_database_directory()
- ),
- name = 'test',
- check_original_files_for_existence = True,
- training_depends_on_protocol = False,
- models_depend_on_protocol = False
- )
+class DummyDatabase(ZTBioDatabase):
+
+ def __init__(self):
+ # call base class constructor with useful parameters
+ super(DummyDatabase, self).__init__(
+ name='test',
+ original_directory=atnt_database_directory(),
+ original_extension='.pgm',
+ check_original_files_for_existence=True,
+ training_depends_on_protocol=False,
+ models_depend_on_protocol=False
+ )
+ self.__db = AtntBioDatabase()
+
+ def model_ids(self, group=None, protocol=None, gender=None):
+ return self.__db.model_ids(group, protocol, gender)
+
+ def objects(self, groups=None, protocol=None, purposes=None, model_ids=None, **kwargs):
+ return self.__db.objects(groups, protocol, purposes, model_ids, **kwargs)
+
+ def tobjects(self, groups=None, protocol=None, model_ids=None, **kwargs):
+ return []
- def all_files(self, groups = ['dev']):
- return DatabaseBob.all_files(self, groups)
+ def zobjects(self, groups=None, protocol=None, **kwargs):
+ return []
- def t_model_ids(self, group = 'dev'):
- return self.model_ids(group)
+ def tmodel_ids(self, protocol=None, groups=None, **kwargs):
+ return self.__db.model_ids(groups)
- def t_enroll_files(self, t_model_id, group = 'dev'):
- return self.enroll_files(t_model_id, group)
+ def t_enroll_files(self, t_model_id, group='dev'):
+ return self.__db.enroll_files(t_model_id, group)
- def z_probe_files(self, group = 'dev'):
- return self.probe_files(None, group)
+ def z_probe_files(self, group='dev'):
+ return self.__db.probe_files(None, group)
database = DummyDatabase()
diff --git a/bob/bio/base/test/dummy/filelist.py b/bob/bio/base/test/dummy/filelist.py
deleted file mode 100644
index dc59e4a170147bf32fe1e3f274668127df248f32..0000000000000000000000000000000000000000
--- a/bob/bio/base/test/dummy/filelist.py
+++ /dev/null
@@ -1,25 +0,0 @@
-import bob.db.verification.filelist
-from bob.bio.base.database import DatabaseFileList
-from bob.bio.base.test.utils import atnt_database_directory
-import pkg_resources
-
-database = DatabaseFileList(
- database = bob.db.verification.filelist.Database(
- base_dir = pkg_resources.resource_filename('bob.bio.base.test', 'data/atnt'),
- original_directory = atnt_database_directory(),
- original_extension = ".pgm",
- dev_subdir = '.',
- eval_subdir = '.',
- world_filename = 'world.lst',
- models_filename = 'models.lst',
- probes_filename = 'probes.lst',
- tnorm_filename = 'models.lst',
- znorm_filename = 'probes.lst',
- keep_read_lists_in_memory = True
- ),
- name = 'test_filelist',
- protocol = None,
- check_original_files_for_existence = True,
- training_depends_on_protocol = False,
- models_depend_on_protocol = False
-)
diff --git a/bob/bio/base/test/dummy/fileset.py b/bob/bio/base/test/dummy/fileset.py
index 17fb51b7f171001d5d8ade8b2f958ebd5e153e14..bfc6172c10d7a2ab3fbfb9dd836830311e9a724b 100644
--- a/bob/bio/base/test/dummy/fileset.py
+++ b/bob/bio/base/test/dummy/fileset.py
@@ -1,53 +1,60 @@
-import bob.db.atnt
-import os
-
-from bob.bio.base.database import DatabaseBob, DatabaseBobZT, File, FileSet
+from bob.bio.db import ZTBioDatabase, BioFileSet, BioFile, AtntBioDatabase
from bob.bio.base.test.utils import atnt_database_directory
-class FileSetDatabase (DatabaseBobZT):
-
- def __init__(self):
- # call base class constructor with useful parameters
- DatabaseBobZT.__init__(
- self,
- database = bob.db.atnt.Database(
- original_directory = atnt_database_directory(),
- ),
- name = 'test_fileset',
- check_original_files_for_existence = True,
- training_depends_on_protocol = False,
- models_depend_on_protocol = False
- )
-
- def uses_probe_file_sets(self):
- return True
-
- def probe_file_sets(self, model_id = None, group = 'dev'):
- """Returns the list of probe File objects (for the given model id, if given)."""
- files = self.arrange_by_client(self.sort(self.database.objects(protocol = None, groups = group, purposes = 'probe')))
- # arrange files by clients
- file_sets = []
- for client_files in files:
- # convert into our File objects (so that they are tested as well)
- our_files = [File(f.id, f.client_id, f.path) for f in client_files]
- # generate file set for each client
- file_set = FileSet(our_files[0].client_id, our_files)
- file_sets.append(file_set)
- return file_sets
-
- def all_files(self, groups = ['dev']):
- return DatabaseBob.all_files(self, groups)
-
- def t_model_ids(self, group = 'dev'):
- return self.model_ids(group)
-
- def t_enroll_files(self, t_model_id, group = 'dev'):
- return self.enroll_files(t_model_id, group)
-
- def z_probe_files(self, group = 'dev'):
- return self.probe_files(None, group)
-
- def z_probe_file_sets(self, group = 'dev'):
- return self.probe_file_sets(None, group)
-
-database = FileSetDatabase()
+
+class DummyDatabase(ZTBioDatabase):
+
+ def __init__(self):
+ # call base class constructor with useful parameters
+ super(DummyDatabase, self).__init__(
+ name='test_fileset',
+ original_directory=atnt_database_directory(),
+ original_extension='.pgm',
+ check_original_files_for_existence=True,
+ training_depends_on_protocol=False,
+ models_depend_on_protocol=False
+ )
+ self.__db = AtntBioDatabase()
+
+ def uses_probe_file_sets(self):
+ return True
+
+ def probe_file_sets(self, model_id=None, group='dev'):
+ """Returns the list of probe File objects (for the given model id, if given)."""
+ # import ipdb; ipdb.set_trace()
+ files = self.arrange_by_client(self.sort(self.objects(protocol=None, groups=group, purposes='probe')))
+ # arrange files by clients
+ file_sets = []
+ for client_files in files:
+ # convert into our File objects (so that they are tested as well)
+ our_files = [BioFile(f.client_id, f.path, f.id) for f in client_files]
+ # generate file set for each client
+ file_set = BioFileSet(our_files[0].client_id, our_files)
+ file_sets.append(file_set)
+ return file_sets
+
+ def model_ids(self, group=None, protocol=None, gender=None):
+ return self.__db.model_ids(group, protocol, gender)
+
+ def objects(self, groups=None, protocol=None, purposes=None, model_ids=None, **kwargs):
+ return self.__db.objects(groups, protocol, purposes, model_ids, **kwargs)
+
+ def tobjects(self, groups=None, protocol=None, model_ids=None, **kwargs):
+ return []
+
+ def zobjects(self, groups=None, protocol=None, **kwargs):
+ return []
+
+ def tmodel_ids(self, protocol=None, groups=None, **kwargs):
+ return self.__db.model_ids(groups)
+
+ def t_enroll_files(self, t_model_id, group='dev'):
+ return self.__db.enroll_files(t_model_id, group)
+
+ def z_probe_files(self, group='dev'):
+ return self.__db.probe_files(None, group)
+
+ def z_probe_file_sets(self, group='dev'):
+ return self.probe_file_sets(None, group)
+
+database = DummyDatabase()
diff --git a/bob/bio/base/test/test_databases.py b/bob/bio/base/test/test_databases.py
deleted file mode 100644
index 8691421ba4464073da3992b99a8f2939d43e91af..0000000000000000000000000000000000000000
--- a/bob/bio/base/test/test_databases.py
+++ /dev/null
@@ -1,64 +0,0 @@
-#!/usr/bin/env python
-# vim: set fileencoding=utf-8 :
-# @author: Manuel Guenther <Manuel.Guenther@idiap.ch>
-# @date: Thu May 24 10:41:42 CEST 2012
-#
-# Copyright (C) 2011-2012 Idiap Research Institute, Martigny, Switzerland
-#
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation, version 3 of the License.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program. If not, see <http://www.gnu.org/licenses/>.
-
-
-import os
-from nose.plugins.skip import SkipTest
-
-import bob.bio.base
-
-import pkg_resources
-dummy_dir = pkg_resources.resource_filename('bob.bio.base', 'test/dummy')
-
-def test_verification_filelist():
- try:
- db1 = bob.bio.base.load_resource(os.path.join(dummy_dir, 'database.py'), 'database')
- except Exception as e:
- raise SkipTest("This test is skipped since the atnt database is not available.")
- try:
- db2 = bob.bio.base.load_resource(os.path.join(dummy_dir, 'filelist.py'), 'database')
- except Exception as e:
- raise SkipTest("This test is skipped since the verification.filelist database is not available.")
- # The test of the verification.filelist database is a bit different.
- # here, we test the output of two different ways of querying the AT&T database
- # where actually both ways are uncommon...
-
- # assure that different kind of queries result in the same file lists
- assert set([str(id) for id in db1.model_ids()]) == set(db2.model_ids())
- assert set([str(id) for id in db1.t_model_ids()]) == set(db2.t_model_ids())
-
- def _check_files(f1, f2):
- assert set([file.path for file in f1]) == set([file.path for file in f2])
-
- _check_files(db1.all_files(), db2.all_files())
- _check_files(db1.training_files('train_extractor'), db2.training_files('train_extractor'))
- _check_files(db1.enroll_files(model_id=22), db2.enroll_files(model_id='22'))
- _check_files(db1.probe_files(model_id=22), db2.probe_files(model_id='22'))
-
- _check_files(db1.t_enroll_files(t_model_id=22), db2.t_enroll_files(t_model_id='22'))
- _check_files(db1.z_probe_files(), db2.z_probe_files())
-
- f1 = db1.all_files()[0]
- f2 = [f for f in db2.all_files() if f.path == f1.path][0]
-
- assert f1.make_path(directory='xx', extension='.yy') == f2.make_path(directory='xx', extension='.yy')
-
- m1 = sorted([str(id) for id in db1.model_ids()])[0]
- m2 = sorted([str(id) for id in db2.model_ids()])[0]
- assert str(db1.client_id_from_model_id(m1)) == db2.client_id_from_model_id(m2)
diff --git a/bob/bio/base/test/test_scripts.py b/bob/bio/base/test/test_scripts.py
index 57e10b908c820eca96b008dc9a41fd48eb96dcb2..20cb89a943c4fc1a1b5bfeae42bb5bc9d7f44eba 100644
--- a/bob/bio/base/test/test_scripts.py
+++ b/bob/bio/base/test/test_scripts.py
@@ -214,57 +214,6 @@ def test_verify_fileset():
_verify(parameters, test_dir, 'test_fileset', ref_modifier="-fileset")
-
-def test_verify_filelist():
- try:
- import bob.db.verification.filelist
- except ImportError:
- raise SkipTest("Skipping test since bob.db.verification.filelist is not available")
- test_dir = tempfile.mkdtemp(prefix='bobtest_')
- # define dummy parameters
- parameters = [
- '-d', os.path.join(dummy_dir, 'filelist.py'),
- '-p', 'dummy',
- '-e', 'dummy',
- '-a', 'dummy',
- '--zt-norm',
- '-vs', 'test_filelist',
- '--temp-directory', test_dir,
- '--result-directory', test_dir,
- '--preferred-package', 'bob.bio.base'
- ]
-
- print (bob.bio.base.tools.command_line(parameters))
-
- try:
- from bob.bio.base.script.verify import main
- main(parameters)
-
- # assert that the score file exists
- score_files = [os.path.join(test_dir, 'test_filelist', 'None', norm, 'scores-dev') for norm in ('nonorm', 'ztnorm')]
- assert os.path.exists(score_files[0]), "Score file %s does not exist" % score_files[0]
- assert os.path.exists(score_files[1]), "Score file %s does not exist" % score_files[1]
-
- # assert that the scores are are identical (might be in a different order, though
- reference_files = [os.path.join(data_dir, 'scores-%s-dev' % norm) for norm in ('nonorm', 'ztnorm')]
-
- for i in (0,1):
- # load scores
- a1, b1 = bob.measure.load.split_four_column(score_files[i])
- a2, b2 = bob.measure.load.split_four_column(reference_files[i])
- # sort scores
- a1 = sorted(a1); a2 = sorted(a2); b1 = sorted(b1); b2 = sorted(b2)
-
- # assert that scores are almost equal
- for i in range(len(a1)):
- abs(a1[i] - a2[i]) < 1e-6
- for i in range(len(b1)):
- abs(b1[i] - b2[i]) < 1e-6
-
- finally:
- shutil.rmtree(test_dir)
-
-
def test_verify_missing():
test_dir = tempfile.mkdtemp(prefix='bobtest_')
# define dummy parameters
diff --git a/bob/bio/base/tools/FileSelector.py b/bob/bio/base/tools/FileSelector.py
index 2a3e56df2983f7390a8faa7dc1ad28d835b04b96..9dbc23dc7cd801277ab2971cb576e121b3c68233 100644
--- a/bob/bio/base/tools/FileSelector.py
+++ b/bob/bio/base/tools/FileSelector.py
@@ -110,6 +110,10 @@ class FileSelector:
"""Returns the list of original data that can be used for preprocessing."""
return self.database.original_file_names(self.database.all_files(groups=groups))
+ def original_data_list_files(self, groups = None):
+ """Returns the list of original data that can be used for preprocessing."""
+ return (self.database.all_files(groups=groups), self.database.original_directory, self.database.original_extension)
+
def annotation_list(self, groups = None):
"""Returns the list of annotations objects."""
return self.database.all_files(groups=groups)
diff --git a/bob/bio/base/tools/command_line.py b/bob/bio/base/tools/command_line.py
index ffad31af0fd6d3b7ae993a7dff2aaeb43fdcb058..3749b36e29f7cb224371e75bcad321c7c55cce5e 100644
--- a/bob/bio/base/tools/command_line.py
+++ b/bob/bio/base/tools/command_line.py
@@ -8,7 +8,7 @@ logger = bob.core.log.setup("bob.bio.base")
from .. import utils
from . import FileSelector
-from .. import database
+from bob.bio.db import BioDatabase
"""Execute biometric recognition algorithms on a certain biometric database.
"""
@@ -249,7 +249,7 @@ def initialize(parsers, command_line_parameters = None, skips = []):
model_sub_dir = protocol if args.database.models_depend_on_protocol else enroller_sub_dir
# Database directories, which should be automatically replaced
- if isinstance(args.database, database.DatabaseBob):
+ if isinstance(args.database, BioDatabase):
args.database.replace_directories(args.database_directories_file)
# initialize the file selector
diff --git a/bob/bio/base/tools/preprocessor.py b/bob/bio/base/tools/preprocessor.py
index 01dea478a7976255216d159ba4d1653d9c1e05b5..86ec390c0f10f2adc4935841a31777341a6a019b 100644
--- a/bob/bio/base/tools/preprocessor.py
+++ b/bob/bio/base/tools/preprocessor.py
@@ -42,7 +42,7 @@ def preprocess(preprocessor, groups = None, indices = None, allow_missing_files
fs = FileSelector.instance()
# get the file lists
- data_files = fs.original_data_list(groups=groups)
+ data_files, original_directory, original_extension = fs.original_data_list_files(groups=groups)
preprocessed_data_files = fs.preprocessed_data_list(groups=groups)
# select a subset of keys to iterate
@@ -60,12 +60,16 @@ def preprocess(preprocessor, groups = None, indices = None, allow_missing_files
# iterate over the selected files
for i in index_range:
preprocessed_data_file = preprocessed_data_files[i]
- file_name = data_files[i]
+ file_object = data_files[i]
+ file_name = file_object.make_path(original_directory, original_extension)
# check for existence
if not utils.check_file(preprocessed_data_file, force, 1000):
logger.debug("... Processing original data file '%s'", file_name)
- data = preprocessor.read_original_data(file_name)
+ if hasattr(file_object, 'load'):
+ data = file_object.load(original_directory, original_extension)
+ else:
+ data = preprocessor.read_original_data(file_name)
# create output directory before reading the data file (is sometimes required, when relative directories are specified, especially, including a .. somewhere)
bob.io.base.create_directories_safe(os.path.dirname(preprocessed_data_file))
diff --git a/buildout.cfg b/buildout.cfg
index 026c9c5b43130b84cad35f1baf92784666c3bd78..e77e863af0476b326dfb64ef7db5e9e57ea8853b 100644
--- a/buildout.cfg
+++ b/buildout.cfg
@@ -21,8 +21,7 @@ develop = src/bob.extension
src/bob.learn.em
src/bob.measure
src/bob.db.base
- src/bob.db.verification.utils
- src/bob.db.verification.filelist
+ src/bob.bio.db
src/bob.db.atnt
src/bob.io.image
.
@@ -44,8 +43,7 @@ bob.learn.linear = git https://github.com/bioidiap/bob.learn.linear
bob.learn.em = git https://github.com/bioidiap/bob.learn.em
bob.measure = git https://github.com/bioidiap/bob.measure
bob.db.base = git https://github.com/bioidiap/bob.db.base
-bob.db.verification.utils = git https://github.com/bioidiap/bob.db.verification.utils
-bob.db.verification.filelist = git https://github.com/bioidiap/bob.db.verification.filelist
+bob.bio.db = git https://gitlab.idiap.ch/biometric/bob.bio.db
bob.db.atnt = git https://github.com/bioidiap/bob.db.atnt
bob.io.image = git https://github.com/bioidiap/bob.io.image
diff --git a/requirements.txt b/requirements.txt
index 71eba5d0fcc37c4bceaa124f02d6e95bcfcb255a..73661d793cbe832cc400f2f8c66c8692af8b9df0 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -11,8 +11,7 @@ bob.sp
bob.learn.em
bob.measure
bob.db.base
-bob.db.verification.utils
-bob.db.verification.filelist
+bob.bio.db
bob.db.atnt # for test purposes
bob.io.image # for test purposes
matplotlib # for plotting