[refactoring2016] Moved the load functions to the to the high level implementations

parent a02fcfdb
Pipeline #3695 passed with stages
in 173 minutes and 55 seconds
......@@ -2,7 +2,7 @@ from .utils import *
from . import preprocessor
from . import extractor
from . import algorithm
from . import database
from . import test
def get_config():
......
from .database import VideoBioFile
from .mobio import MobioBioDatabase
from .youtube import YoutubeBioDatabase
# gets sphinx autodoc done right - don't remove it
__all__ = [_ for _ in dir() if not _.startswith('_')]
......@@ -8,6 +8,7 @@
"""
from bob.bio.base.database.file import BioFile
from bob.bio.video.utils.FrameSelector import FrameSelector
class VideoBioFile(BioFile):
......@@ -20,4 +21,8 @@ class VideoBioFile(BioFile):
self.__f = f
def load(self, directory=None, extension='.avi'):
return FrameSelector()(self.make_path(directory, extension))
......@@ -12,6 +12,21 @@
from .database import VideoBioFile
from bob.bio.base.database import ZTBioDatabase, BioFile
from bob.bio.video.utils import FrameContainer
import os
import bob.io.base
class YoutubeBioFile(VideoBioFile):
def load(self, directory=None, extension='.jpg'):
files = os.listdir(self.make_path(directory, ''))
fc = FrameContainer()
for f in files:
if extension == os.path.splitext(f)[1]:
file_name = os.path.join(self.make_path(directory, ''), f)
fc.add(os.path.basename(file_name), bob.io.base.load(file_name))
return fc
class YoutubeBioDatabase(ZTBioDatabase):
......@@ -38,12 +53,12 @@ class YoutubeBioDatabase(ZTBioDatabase):
def objects(self, groups=None, protocol=None, purposes=None, model_ids=None, **kwargs):
retval = self.__db.objects(groups=groups, protocol=protocol, purposes=purposes, model_ids=model_ids, **kwargs)
return [VideoBioFile(client_id=f.client_id, path=f.path, file_id=f.id) for f in retval]
return [YoutubeBioFile(BioFile(client_id=f.client_id, path=f.path, file_id=f.id)) for f in retval]
def tobjects(self, groups=None, protocol=None, model_ids=None, **kwargs):
retval = self.__db.tobjects(groups=groups, protocol=protocol, model_ids=model_ids, **kwargs)
return [VideoBioFile(client_id=f.client_id, path=f.path, file_id=f.id) for f in retval]
return [YoutubeBioFile(BioFile(client_id=f.client_id, path=f.path, file_id=f.id)) for f in retval]
def zobjects(self, groups=None, protocol=None, **kwargs):
retval = self.__db.zobjects(groups=groups, protocol=protocol, **kwargs)
return [VideoBioFile(client_id=f.client_id, path=f.path, file_id=f.id) for f in retval]
return [YoutubeBioFile(BioFile(client_id=f.client_id, path=f.path, file_id=f.id)) for f in retval]
......@@ -2,195 +2,169 @@
# vim: set fileencoding=utf-8 :
import bob.bio.base
import numpy
import glob
import os
import bob.io.base
from .. import utils
class Wrapper (bob.bio.base.preprocessor.Preprocessor):
"""Wrapper class to run image preprocessing algorithms on video data.
This class provides functionality to read original video data from several databases.
So far, the video content from :py:class:`bob.db.mobio` and the image list content from :py:class:`bob.db.youtube` are supported.
Furthermore, frames are extracted from these video data, and a ``preprocessor`` algorithm is applied on all selected frames.
The preprocessor can either be provided as a registered resource, i.e., one of :ref:`bob.bio.face.preprocessors`, or an instance of a preprocessing class.
Since most of the databases do not provide annotations for all frames of the videos, commonly the preprocessor needs to apply face detection.
The ``frame_selector`` can be chosen to select some frames from the video.
By default, a few frames spread over the whole video sequence are selected.
class Wrapper(bob.bio.base.preprocessor.Preprocessor):
"""Wrapper class to run image preprocessing algorithms on video data.
The ``quality_function`` is used to assess the quality of the frame.
If no ``quality_function`` is given, the quality is based on the face detector, or simply left as ``None``.
So far, the quality of the frames are not used, but it is foreseen to select frames based on quality.
This class provides functionality to read original video data from several databases.
So far, the video content from :py:class:`bob.db.mobio` and the image list content from :py:class:`bob.db.youtube` are supported.
**Parameters:**
Furthermore, frames are extracted from these video data, and a ``preprocessor`` algorithm is applied on all selected frames.
The preprocessor can either be provided as a registered resource, i.e., one of :ref:`bob.bio.face.preprocessors`, or an instance of a preprocessing class.
Since most of the databases do not provide annotations for all frames of the videos, commonly the preprocessor needs to apply face detection.
preprocessor : str or :py:class:`bob.bio.base.preprocessor.Preprocessor` instance
The preprocessor to be used to preprocess the frames.
The ``frame_selector`` can be chosen to select some frames from the video.
By default, a few frames spread over the whole video sequence are selected.
frame_selector : :py:class:`bob.bio.video.FrameSelector`
A frame selector class to define, which frames of the video to use.
The ``quality_function`` is used to assess the quality of the frame.
If no ``quality_function`` is given, the quality is based on the face detector, or simply left as ``None``.
So far, the quality of the frames are not used, but it is foreseen to select frames based on quality.
quality_function : function or ``None``
A function assessing the quality of the preprocessed image.
If ``None``, no quality assessment is performed.
If the preprocessor contains a ``quality`` attribute, this is taken instead.
compressed_io : bool
Use compression to write the resulting preprocessed HDF5 files.
This is experimental and might cause trouble.
Use this flag with care.
"""
**Parameters:**
def __init__(self,
preprocessor = 'landmark-detect',
frame_selector = utils.FrameSelector(),
quality_function = None,
compressed_io = False
):
preprocessor : str or :py:class:`bob.bio.base.preprocessor.Preprocessor` instance
The preprocessor to be used to preprocess the frames.
# load preprocessor configuration
if isinstance(preprocessor, str):
self.preprocessor = bob.bio.base.load_resource(preprocessor, "preprocessor")
elif isinstance(preprocessor, bob.bio.base.preprocessor.Preprocessor):
self.preprocessor = preprocessor
else:
raise ValueError("The given preprocessor could not be interpreted")
frame_selector : :py:class:`bob.bio.video.FrameSelector`
A frame selector class to define, which frames of the video to use.
bob.bio.base.preprocessor.Preprocessor.__init__(
self,
preprocessor=preprocessor,
frame_selector=frame_selector,
compressed_io=compressed_io
)
quality_function : function or ``None``
A function assessing the quality of the preprocessed image.
If ``None``, no quality assessment is performed.
If the preprocessor contains a ``quality`` attribute, this is taken instead.
self.frame_selector = frame_selector
self.quality_function = quality_function
self.compressed_io = compressed_io
compressed_io : bool
Use compression to write the resulting preprocessed HDF5 files.
This is experimental and might cause trouble.
Use this flag with care.
"""
def _check_data(self, frames):
"""Checks if the given video is in the desired format."""
assert isinstance(frames, utils.FrameContainer)
def __init__(self,
preprocessor='landmark-detect',
frame_selector=utils.FrameSelector(),
quality_function=None,
compressed_io=False,
read_original_data=lambda biofile, directory, extension: biofile.load(directory, extension)
):
# load preprocessor configuration
if isinstance(preprocessor, str):
self.preprocessor = bob.bio.base.load_resource(preprocessor, "preprocessor")
elif isinstance(preprocessor, bob.bio.base.preprocessor.Preprocessor):
self.preprocessor = preprocessor
else:
raise ValueError("The given preprocessor could not be interpreted")
bob.bio.base.preprocessor.Preprocessor.__init__(
self,
preprocessor=preprocessor,
frame_selector=frame_selector,
compressed_io=compressed_io,
read_original_data=read_original_data
)
def __call__(self, frames, annotations = None):
"""__call__(frames, annotations = None) -> preprocessed
self.frame_selector = frame_selector
self.quality_function = quality_function
self.compressed_io = compressed_io
Preprocesses the given frames using the desired ``preprocessor``.
def _check_data(self, frames):
"""Checks if the given video is in the desired format."""
assert isinstance(frames, utils.FrameContainer)
Faces are extracted for all frames in the given frame container, using the ``preprocessor`` specified in the constructor.
def __call__(self, frames, annotations=None):
"""__call__(frames, annotations = None) -> preprocessed
If given, the annotations need to be in a dictionary.
The key is either the frame number (for video data) or the image name (for image list data).
The value is another dictionary, building the relation between facial landmark names and their location, e.g. ``{'leye' : (le_y, le_x), 'reye' : (re_y, re_x)}``
Preprocesses the given frames using the desired ``preprocessor``.
The annotations for the according frames, if present, are passed to the preprocessor.
Please assure that your database interface provides the annotations in the desired format.
Faces are extracted for all frames in the given frame container, using the ``preprocessor`` specified in the constructor.
**Parameters:**
If given, the annotations need to be in a dictionary.
The key is either the frame number (for video data) or the image name (for image list data).
The value is another dictionary, building the relation between facial landmark names and their location, e.g. ``{'leye' : (le_y, le_x), 'reye' : (re_y, re_x)}``
frames : :py:class:`bob.bio.video.FrameContainer`
The pre-selected frames, as returned by :py:meth:`read_original_data`.
The annotations for the according frames, if present, are passed to the preprocessor.
Please assure that your database interface provides the annotations in the desired format.
annotations : dict or ``None``
The annotations for the frames, if any.
**Parameters:**
**Returns:**
frames : :py:class:`bob.bio.video.FrameContainer`
The pre-selected frames, as returned by :py:meth:`read_original_data`.
preprocessed : :py:class:`bob.bio.video.FrameContainer`
A frame container that contains the preprocessed frames.
"""
if not isinstance(frames, utils.FrameContainer):
frames = self.frame_selector(frames)
annots = None
fc = utils.FrameContainer()
for index, frame, _ in frames:
# if annotations are given, we take them
if annotations is not None: annots = annotations[index]
# preprocess image (by default: detect a face)
preprocessed = self.preprocessor(frame, annots)
if preprocessed is not None:
# compute the quality of the detection
if self.quality_function is not None:
quality = self.quality_function(preprocessed)
elif hasattr(self.preprocessor, 'quality'):
quality = self.preprocessor.quality
else:
quality = None
# add image to frame container
fc.add(index, preprocessed, quality)
annotations : dict or ``None``
The annotations for the frames, if any.
return fc
**Returns:**
preprocessed : :py:class:`bob.bio.video.FrameContainer`
A frame container that contains the preprocessed frames.
"""
if not isinstance(frames, utils.FrameContainer):
frames = self.frame_selector(frames)
def read_original_data(self, data):
"""read_original_data(data) -> frames
annots = None
fc = utils.FrameContainer()
Reads the original data from file and selects some frames using the desired ``frame_selector``.
for index, frame, _ in frames:
# if annotations are given, we take them
if annotations is not None: annots = annotations[index]
Currently, two types of data is supported:
# preprocess image (by default: detect a face)
preprocessed = self.preprocessor(frame, annots)
if preprocessed is not None:
# compute the quality of the detection
if self.quality_function is not None:
quality = self.quality_function(preprocessed)
elif hasattr(self.preprocessor, 'quality'):
quality = self.preprocessor.quality
else:
quality = None
# add image to frame container
fc.add(index, preprocessed, quality)
1. video data, which is stored in a 3D or 4D :py:class:`numpy.ndarray`, which will be read using :py:func:`bob.io.base.load`
2. image lists, which is given as a list of strings of image file names. Each image will be read with :py:func:`bob.io.base.load`
return fc
**Parameters:**
data : 3D or 4D :py:class:`numpy.ndarray`, or [str]
The original data to read.
def read_data(self, filename):
"""read_data(filename) -> frames
**Returns:**
Reads the preprocessed data from file and returns them in a frame container.
The preprocessors ``read_data`` function is used to read the data for each frame.
frames : :py:class:`bob.bio.video.FrameContainer`
The selected frames, stored in a frame container.
"""
return self.frame_selector(data)
**Parameters:**
filename : str
The name of the preprocessed data file.
def read_data(self, filename):
"""read_data(filename) -> frames
**Returns:**
Reads the preprocessed data from file and returns them in a frame container.
The preprocessors ``read_data`` function is used to read the data for each frame.
**Parameters:**
filename : str
The name of the preprocessed data file.
**Returns:**
frames : :py:class:`bob.bio.video.FrameContainer`
The read frames, stored in a frame container.
"""
if self.compressed_io:
return utils.load_compressed(filename, self.preprocessor.read_data)
else:
return utils.FrameContainer(bob.io.base.HDF5File(filename), self.preprocessor.read_data)
frames : :py:class:`bob.bio.video.FrameContainer`
The read frames, stored in a frame container.
"""
if self.compressed_io:
return utils.load_compressed(filename, self.preprocessor.read_data)
else:
return utils.FrameContainer(bob.io.base.HDF5File(filename), self.preprocessor.read_data)
def write_data(self, frames, filename):
"""Writes the preprocessed data to file.
def write_data(self, frames, filename):
"""Writes the preprocessed data to file.
The preprocessors ``write_data`` function is used to write the data for each frame.
The preprocessors ``write_data`` function is used to write the data for each frame.
**Parameters:**
**Parameters:**
frames : :py:class:`bob.bio.video.FrameContainer`
The preprocessed frames, as returned by the :py:meth:`__call__` function.
frames : :py:class:`bob.bio.video.FrameContainer`
The preprocessed frames, as returned by the :py:meth:`__call__` function.
filename : str
The name of the preprocessed data file to write.
"""
self._check_data(frames)
filename : str
The name of the preprocessed data file to write.
"""
self._check_data(frames)
if self.compressed_io:
return utils.save_compressed(frames, filename, self.preprocessor.write_data)
else:
frames.save(bob.io.base.HDF5File(filename, 'w'), self.preprocessor.write_data)
if self.compressed_io:
return utils.save_compressed(frames, filename, self.preprocessor.write_data)
else:
frames.save(bob.io.base.HDF5File(filename, 'w'), self.preprocessor.write_data)
from bob.bio.base.database import ZTBioDatabase
from bob.bio.base.test.utils import atnt_database_directory
from bob.bio.base.database.file import BioFile
from bob.bio.video.database import VideoBioFile
from bob.bio.video.utils import FrameContainer
import bob.io.base
import os
class DummyBioFile(VideoBioFile):
def load(self, directory=None, extension='.avi'):
file_name = self.make_path(directory, extension)
fc = FrameContainer()
fc.add(os.path.basename(file_name), bob.io.base.load(file_name))
return fc
class DummyDatabase(ZTBioDatabase):
......@@ -17,11 +30,14 @@ class DummyDatabase(ZTBioDatabase):
import bob.db.atnt
self.__db = bob.db.atnt.Database()
def _make_bio(self, files):
return [DummyBioFile(BioFile(client_id=f.client_id, path=f.path, file_id=f.id)) for f in files]
def model_ids_with_protocol(self, groups=None, protocol=None, **kwargs):
return self.__db.model_ids(groups, protocol)
def objects(self, groups=None, protocol=None, purposes=None, model_ids=None, **kwargs):
return self.__db.objects(model_ids, groups, purposes, protocol, **kwargs)
return self._make_bio(self.__db.objects(model_ids, groups, purposes, protocol, **kwargs))
def tobjects(self, groups=None, protocol=None, model_ids=None, **kwargs):
return []
......@@ -39,8 +55,9 @@ class DummyDatabase(ZTBioDatabase):
return self.probe_files(None, group)
# override all_files to return a one-element lists of files
def all_files(self, groups):
return [[n] for n in super(DummyDatabase, self).all_files(groups)]
#def all_files(self, groups):
#return [[n] for n in super(DummyDatabase, self).all_files(groups)]
#return [[n] for n in super(DummyDatabase, self).all_files(groups)]
def file_names(self, files, directory, extension):
if isinstance(files[0], list):
......
......@@ -9,70 +9,88 @@ import bob.io.video
import bob.bio.base
import bob.bio.video
import bob.db.base
import pkg_resources
from bob.bio.video.test.dummy.database import DummyBioFile
regenerate_refs = False
def test_annotations():
# use annotations to grep
image_files = [pkg_resources.resource_filename("bob.bio.face.test", "data/testimage.jpg")]
annotations = {os.path.basename(image_files[0]) : bob.db.base.read_annotation_file(pkg_resources.resource_filename("bob.bio.face.test", "data/testimage.pos"), 'named')}
original_path = pkg_resources.resource_filename("bob.bio.face.test", "")
image_files = DummyBioFile(bob.bio.base.database.BioFile(client_id=1, file_id=1, path="data/testimage"))
# use annotations to grep
annotations = {os.path.basename(image_files.make_path(original_path, ".jpg")): bob.db.base.read_annotation_file(
pkg_resources.resource_filename("bob.bio.face.test", "data/testimage.pos"), 'named')}
# video preprocessor using a face crop preprocessor
frame_selector = bob.bio.video.FrameSelector(selection_style="all")
preprocessor = bob.bio.video.preprocessor.Wrapper('face-crop-eyes', frame_selector, compressed_io=False)
# video preprocessor using a face crop preprocessor
frame_selector = bob.bio.video.FrameSelector(selection_style="all")
preprocessor = bob.bio.video.preprocessor.Wrapper('face-crop-eyes', frame_selector, compressed_io=False)
# read original data
original = preprocessor.read_original_data(image_files)
assert isinstance(original, bob.bio.video.FrameContainer)
assert len(original) == 1
assert original[0][0] == os.path.basename(image_files[0])
# read original data
original = preprocessor.read_original_data(image_files, original_path, ".jpg")
# preprocess data including annotations
preprocessed = preprocessor(original, annotations)
assert isinstance(preprocessed, bob.bio.video.FrameContainer)
assert len(preprocessed) == 1
assert preprocessed[0][0] == os.path.basename(image_files[0])
assert preprocessed[0][2] is None
assert numpy.allclose(preprocessed[0][1], bob.io.base.load(pkg_resources.resource_filename("bob.bio.face.test", "data/cropped.hdf5")))
assert isinstance(original, bob.bio.video.FrameContainer)
assert len(original) == 1
assert original[0][0] == os.path.basename(image_files.make_path(original_path, ".jpg"))
# preprocess data including annotations
preprocessed = preprocessor(original, annotations)
assert isinstance(preprocessed, bob.bio.video.FrameContainer)
assert len(preprocessed) == 1
assert preprocessed[0][0] == os.path.basename(image_files.make_path(original_path, ".jpg"))
assert preprocessed[0][2] is None
assert numpy.allclose(preprocessed[0][1],
bob.io.base.load(pkg_resources.resource_filename("bob.bio.face.test", "data/cropped.hdf5")))
def test_detect():
# load test video
video_file = pkg_resources.resource_filename("bob.bio.video.test", "data/testvideo.avi")
frame_selector = bob.bio.video.FrameSelector(max_number_of_frames=3, selection_style="spread")
preprocessor = bob.bio.video.preprocessor.Wrapper('face-detect', frame_selector, compressed_io=False)
video = preprocessor.read_original_data(video_file)
assert isinstance(video, bob.bio.video.FrameContainer)
def read_original_data(video_object, original_path, original_extension):
return frame_selector(video_object.make_path(original_path, original_extension))
# load test video
original_path = pkg_resources.resource_filename("bob.bio.video.test", "")
video_object = bob.bio.video.database.VideoBioFile(bob.bio.base.database.BioFile(
client_id=1, file_id=1, path="data/testvideo"))
preprocessed_video = preprocessor(video)
assert isinstance(preprocessed_video, bob.bio.video.FrameContainer)
frame_selector = bob.bio.video.FrameSelector(max_number_of_frames=3, selection_style="spread")
preprocessor = bob.bio.video.preprocessor.Wrapper('face-detect', frame_selector, compressed_io=False,
read_original_data=read_original_data)
reference_file = pkg_resources.resource_filename("bob.bio.video.test", "data/preprocessed.hdf5")
if regenerate_refs:
preprocessed_video.save(bob.io.base.HDF5File(reference_file, 'w'))
reference_data = bob.bio.video.FrameContainer(bob.io.base.HDF5File(reference_file, 'r'))
video = preprocessor.read_original_data(video_object, original_path,".avi")
assert isinstance(video, bob.bio.video.FrameContainer)
assert preprocessed_video.is_similar_to(reference_data)
preprocessed_video = preprocessor(video)
assert isinstance(preprocessed_video, bob.bio.video.FrameContainer)
reference_file = pkg_resources.resource_filename("bob.bio.video.test", "data/preprocessed.hdf5")
if regenerate_refs:
preprocessed_video.save(bob.io.base.HDF5File(reference_file, 'w'))
reference_data = bob.bio.video.FrameContainer(bob.io.base.HDF5File(reference_file, 'r'))
assert preprocessed_video.is_similar_to(reference_data)
def test_flandmark():
video_file = pkg_resources.resource_filename("bob.bio.video.test", "data/testvideo.avi")
frame_selector = bob.bio.video.FrameSelector(max_number_of_frames=3, selection_style="spread")
def read_original_data(video_object, original_path, original_extension):
return frame_selector(video_object.make_path(original_path, original_extension))
original_path = pkg_resources.resource_filename("bob.bio.video.test", "")
video_object = bob.bio.video.database.VideoBioFile(bob.bio.base.database.BioFile(
client_id=1, file_id=1, path="data/testvideo"))
frame_selector = bob.bio.video.FrameSelector(max_number_of_frames=3, selection_style="spread")
preprocessor = bob.bio.video.preprocessor.Wrapper('landmark-detect', frame_selector, compressed_io=False)
video = preprocessor.read_original_data(video_file)
assert isinstance(video, bob.bio.video.FrameContainer)
preprocessor = bob.bio.video.preprocessor.Wrapper('landmark-detect', frame_selector, compressed_io=False,
read_original_data=read_original_data)
video = preprocessor.read_original_data(video_object, original_path, ".avi")
assert isinstance(video, bob.bio.video.FrameContainer)
preprocessed_video = preprocessor(video)
assert isinstance(preprocessed_video, bob.bio.video.FrameContainer)
preprocessed_video = preprocessor(video)
assert isinstance(preprocessed_video, bob.bio.video.FrameContainer)
reference_file = pkg_resources.resource_filename("bob.bio.video.test", "data/preprocessed-flandmark.hdf5")
if regenerate_refs:
preprocessed_video.save(bob.io.base.HDF5File(reference_file, 'w'))
reference_data = bob.bio.video.FrameContainer(bob.io.base.HDF5File(reference_file, 'r'))
reference_file = pkg_resources.resource_filename("bob.bio.video.test", "data/preprocessed-flandmark.hdf5")
if regenerate_refs:
preprocessed_video.save(bob.io.base.HDF5File(reference_file, 'w'))
reference_data = bob.bio.video.FrameContainer(bob.io.base.HDF5File(reference_file, 'r'))
assert preprocessed_video.is_similar_to(reference_data)
assert preprocessed_video.is_similar_to(reference_data)
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment