def _get_extractor(self, exclude_gpus):
""" Obtain a Mask extractor plugin and launch it
Parameters
----------
exclude_gpus: list or ``None``
A list of indices correlating to connected GPUs that Tensorflow should not use. Pass
``None`` to not exclude any GPUs.
Returns
-------
:class:`plugins.extract.pipeline.Extractor`:
The launched Extractor
"""
if self._update_type == "output":
logger.debug(
"Update type `output` selected. Not launching extractor")
return None
logger.debug("masker: %s", self._mask_type)
extractor = Extractor(None,
None,
self._mask_type,
exclude_gpus=exclude_gpus,
image_is_aligned=self._input_is_faces)
extractor.launch()
logger.debug(extractor)
return extractor
def __init__(self, arguments):
logger.debug("Initializing %s: (args: %s", self.__class__.__name__,
arguments)
self._args = arguments
self._output_dir = None if self._args.skip_saving_faces else get_folder(
self._args.output_dir)
logger.info("Output Directory: %s", self._args.output_dir)
self._images = ImagesLoader(self._args.input_dir, fast_count=True)
self._alignments = Alignments(self._args, True, self._images.is_video)
self._existing_count = 0
self._set_skip_list()
self._post_process = PostProcess(arguments)
configfile = self._args.configfile if hasattr(self._args,
"configfile") else None
normalization = None if self._args.normalization == "none" else self._args.normalization
maskers = ["components", "extended"]
maskers += self._args.masker if self._args.masker else []
self._extractor = Extractor(self._args.detector,
self._args.aligner,
maskers,
configfile=configfile,
multiprocess=not self._args.singleprocess,
exclude_gpus=self._args.exclude_gpus,
rotate_images=self._args.rotate_images,
min_size=self._args.min_size,
normalize_method=normalization,
re_feed=self._args.re_feed)
self._threads = list()
self._verify_output = False
logger.debug("Initialized %s", self.__class__.__name__)
def _load_extractor(self):
""" Load the CV2-DNN Face Extractor Chain.
For On-The-Fly conversion we use a CPU based extractor to avoid stacking the GPU.
Results are poor.
Returns
-------
:class:`plugins.extract.Pipeline.Extractor`
The face extraction chain to be used for on-the-fly conversion
"""
logger.debug("Loading extractor")
logger.warning("On-The-Fly conversion selected. This will use the inferior cv2-dnn for "
"extraction and will produce poor results.")
logger.warning("It is recommended to generate an alignments file for your destination "
"video with Extract first for superior results.")
extractor = Extractor(detector="cv2-dnn",
aligner="cv2-dnn",
masker="none",
multiprocess=True,
rotate_images=None,
min_size=20)
extractor.launch()
logger.debug("Loaded extractor")
return extractor
def __init__(self, arguments):
logger.debug("Initializing %s: (args: %s", self.__class__.__name__,
arguments)
self.args = arguments
Utils.set_verbosity(self.args.loglevel)
self.output_dir = get_folder(self.args.output_dir)
logger.info("Output Directory: %s", self.args.output_dir)
self.images = Images(self.args)
self.alignments = Alignments(self.args, True, self.images.is_video)
self.post_process = PostProcess(arguments)
configfile = self.args.configfile if hasattr(self.args,
"configfile") else None
normalization = None if self.args.normalization == "none" else self.args.normalization
self.extractor = Extractor(self.args.detector,
self.args.aligner,
self.args.loglevel,
configfile=configfile,
multiprocess=not self.args.singleprocess,
rotate_images=self.args.rotate_images,
min_size=self.args.min_size,
normalize_method=normalization)
self.save_queue = queue_manager.get_queue("extract_save")
self.verify_output = False
self.save_interval = None
if hasattr(self.args, "save_interval"):
self.save_interval = self.args.save_interval
logger.debug("Initialized %s", self.__class__.__name__)
def __init__(self, arguments):
logger.debug("Initializing %s: (args: %s", self.__class__.__name__,
arguments)
self._args = arguments
self._output_dir = str(get_folder(self._args.output_dir))
logger.info("Output Directory: %s", self._args.output_dir)
self._images = ImagesLoader(self._args.input_dir,
load_with_hash=False,
fast_count=True)
self._alignments = Alignments(self._args, True, self._images.is_video)
self._existing_count = 0
self._set_skip_list()
self._post_process = PostProcess(arguments)
configfile = self._args.configfile if hasattr(self._args,
"configfile") else None
normalization = None if self._args.normalization == "none" else self._args.normalization
self._extractor = Extractor(self._args.detector,
self._args.aligner,
self._args.masker,
configfile=configfile,
multiprocess=not self._args.singleprocess,
rotate_images=self._args.rotate_images,
min_size=self._args.min_size,
normalize_method=normalization)
self._threads = list()
self._verify_output = False
logger.debug("Initialized %s", self.__class__.__name__)
def align_faces(self, detector_name, aligner_name, multiprocess):
""" Use the requested detectors to retrieve landmarks for filter images """
extractor = Extractor(detector_name,
aligner_name,
multiprocess=multiprocess)
self.run_extractor(extractor)
del extractor
self.load_aligned_face()
def _get_extractor(self):
""" Obtain a Mask extractor plugin and launch it
Returns
-------
:class:`plugins.extract.pipeline.Extractor`:
The launched Extractor
"""
if self._update_type == "output":
logger.debug("Update type `output` selected. Not launching extractor")
return None
logger.debug("masker: %s", self._mask_type)
extractor = Extractor(None, None, self._mask_type,
image_is_aligned=self._input_is_faces)
extractor.launch()
logger.debug(extractor)
return extractor
def _load_extractor(self):
""" Load the CV2-DNN Face Extractor Chain.
For On-The-Fly conversion we use a CPU based extractor to avoid stacking the GPU.
Results are poor.
Returns
-------
:class:`plugins.extract.Pipeline.Extractor`
The face extraction chain to be used for on-the-fly conversion
"""
if not self._alignments.have_alignments_file and not self._args.on_the_fly:
logger.error(
"No alignments file found. Please provide an alignments file for your "
"destination video (recommended) or enable on-the-fly conversion (not "
"recommended).")
sys.exit(1)
if self._alignments.have_alignments_file:
if self._args.on_the_fly:
logger.info(
"On-The-Fly conversion selected, but an alignments file was found. "
"Using pre-existing alignments file: '%s'",
self._alignments.file)
else:
logger.debug("Alignments file found: '%s'",
self._alignments.file)
return None
logger.debug("Loading extractor")
logger.warning(
"On-The-Fly conversion selected. This will use the inferior cv2-dnn for "
"extraction and will produce poor results.")
logger.warning(
"It is recommended to generate an alignments file for your destination "
"video with Extract first for superior results.")
extractor = Extractor(detector="cv2-dnn",
aligner="cv2-dnn",
masker=self._args.mask_type,
multiprocess=True,
rotate_images=None,
min_size=20)
extractor.launch()
logger.debug("Loaded extractor")
return extractor
def load_extractor(self):
""" Set on the fly extraction """
if self.alignments.have_alignments_file:
return None
logger.debug("Loading extractor")
logger.warning("No Alignments file found. Extracting on the fly.")
logger.warning(
"NB: This will use the inferior cv2-dnn for extraction "
"and landmarks. It is recommended to perfom Extract first for "
"superior results")
extractor = Extractor(detector="cv2-dnn",
aligner="cv2-dnn",
multiprocess=False,
rotate_images=None,
min_size=20)
extractor.launch()
logger.debug("Loaded extractor")
return extractor
def load_extractor(self):
""" Set on the fly extraction """
if self.alignments.have_alignments_file:
return None
logger.debug("Loading extractor")
logger.warning("No Alignments file found. Extracting on the fly.")
logger.warning("NB: This will use the inferior cv2-dnn for extraction "
"and landmarks. It is recommended to perfom Extract first for "
"superior results")
extractor = Extractor(detector="cv2-dnn",
aligner="cv2-dnn",
loglevel=self.args.loglevel,
multiprocess=False,
rotate_images=None,
min_size=20)
extractor.launch()
logger.debug("Loaded extractor")
return extractor
def launch_aligner(self):
""" Load the aligner plugin to retrieve landmarks """
extractor = Extractor(None, "fan", None,
normalize_method="hist", exclude_gpus=self._args.exclude_gpus)
extractor.set_batchsize("align", 1)
extractor.launch()
return extractor
def init_extractor(self):
""" Initialize Aligner """
logger.debug("Initialize Extractor")
extractor = Extractor("manual",
"fan",
multiprocess=True,
normalize_method="hist")
self.queues["in"] = extractor.input_queue
# Set the batchsizes to 1
extractor.set_batchsize("detector", 1)
extractor.set_batchsize("aligner", 1)
extractor.launch()
logger.debug("Initialized Extractor")
return extractor
def _legacy_check(self):
""" Check whether the alignments file was created with the legacy extraction method.
If so, force user to re-extract all faces if any options have been specified, otherwise
raise the appropriate warnings and set the legacy options.
"""
if self._arguments.large or self._arguments.extract_every_n != 1:
logger.warning(
"This alignments file was generated with the legacy extraction method."
)
logger.warning(
"You should run this extraction job, but with 'large' deselected and "
"'extract-every-n' set to 1 to update the alignments file.")
logger.warning(
"You can then re-run this extraction job with your chosen options."
)
sys.exit(0)
maskers = ["components", "extended"]
nn_masks = [
mask for mask in list(self._alignments.mask_summary)
if mask not in maskers
]
logtype = logger.warning if nn_masks else logger.info
logtype(
"This alignments file was created with the legacy extraction method and will be "
"updated.")
logtype(
"Faces will be extracted using the new method and landmarks based masks will be "
"regenerated.")
if nn_masks:
logtype(
"However, the NN based masks '%s' will be cropped to the legacy extraction "
"method, so you may want to run the mask tool to regenerate these "
"masks.", "', '".join(nn_masks))
self._mask_pipeline = Extractor(None, None, maskers, multiprocess=True)
self._mask_pipeline.launch()
# Update alignments versioning
self._alignments._version = _VERSION # pylint:disable=protected-access
def _init_aligner(self):
""" Initialize Aligner in a background thread, and set it to :attr:`_aligner`. """
logger.debug("Initialize Aligner")
# Make sure non-GPU aligner is allocated first
for model in ("mask", "cv2-dnn", "FAN"):
logger.debug("Initializing aligner: %s", model)
plugin = None if model == "mask" else model
aligner = Extractor(None,
plugin, ["components", "extended"],
multiprocess=True,
normalize_method="hist")
if plugin:
aligner.set_batchsize("align", 1) # Set the batchsize to 1
aligner.launch()
logger.debug("Initialized %s Extractor", model)
self._aligners[model] = aligner
def __init__(self, arguments):
logger.debug("Initializing %s: (args: %s", self.__class__.__name__, arguments)
self.args = arguments
Utils.set_verbosity(self.args.loglevel)
self.output_dir = get_folder(self.args.output_dir)
logger.info("Output Directory: %s", self.args.output_dir)
self.images = Images(self.args)
self.alignments = Alignments(self.args, True, self.images.is_video)
self.post_process = PostProcess(arguments)
self.extractor = Extractor(self.args.detector,
self.args.aligner,
self.args.loglevel,
self.args.multiprocess,
self.args.rotate_images,
self.args.min_size)
self.save_queue = queue_manager.get_queue("extract_save")
self.verify_output = False
self.save_interval = None
if hasattr(self.args, "save_interval"):
self.save_interval = self.args.save_interval
logger.debug("Initialized %s", self.__class__.__name__)
class Extract(): # pylint:disable=too-few-public-methods
""" The Faceswap Face Extraction Process.
The extraction process is responsible for detecting faces in a series of images/video, aligning
these faces and then generating a mask.
It leverages a series of user selected plugins, chained together using
:mod:`plugins.extract.pipeline`.
The extract process is self contained and should not be referenced by any other scripts, so it
contains no public properties.
Parameters
----------
arguments: argparse.Namespace
The arguments to be passed to the extraction process as generated from Faceswap's command
line arguments
"""
def __init__(self, arguments):
logger.debug("Initializing %s: (args: %s", self.__class__.__name__,
arguments)
self._args = arguments
self._output_dir = str(get_folder(self._args.output_dir))
logger.info("Output Directory: %s", self._args.output_dir)
self._images = ImagesLoader(self._args.input_dir,
load_with_hash=False,
fast_count=True)
self._alignments = Alignments(self._args, True, self._images.is_video)
self._existing_count = 0
self._set_skip_list()
self._post_process = PostProcess(arguments)
configfile = self._args.configfile if hasattr(self._args,
"configfile") else None
normalization = None if self._args.normalization == "none" else self._args.normalization
self._extractor = Extractor(self._args.detector,
self._args.aligner,
self._args.masker,
configfile=configfile,
multiprocess=not self._args.singleprocess,
rotate_images=self._args.rotate_images,
min_size=self._args.min_size,
normalize_method=normalization)
self._threads = list()
self._verify_output = False
logger.debug("Initialized %s", self.__class__.__name__)
@property
def _save_interval(self):
""" int: The number of frames to be processed between each saving of the alignments file if
it has been provided, otherwise ``None`` """
if hasattr(self._args, "save_interval"):
return self._args.save_interval
return None
@property
def _skip_num(self):
""" int: Number of frames to skip if extract_every_n has been provided """
return self._args.extract_every_n if hasattr(self._args,
"extract_every_n") else 1
def _set_skip_list(self):
""" Add the skip list to the image loader
Checks against `extract_every_n` and the existence of alignments data (can exist if
`skip_existing` or `skip_existing_faces` has been provided) and compiles a list of frame
indices that should not be processed, providing these to :class:`lib.image.ImagesLoader`.
"""
if self._skip_num == 1 and not self._alignments.data:
logger.debug("No frames to be skipped")
return
skip_list = []
for idx, filename in enumerate(self._images.file_list):
if idx % self._skip_num != 0:
logger.trace(
"Adding image '%s' to skip list due to extract_every_n = %s",
filename, self._skip_num)
skip_list.append(idx)
# Items may be in the alignments file if skip-existing[-faces] is selected
elif os.path.basename(filename) in self._alignments.data:
self._existing_count += 1
logger.trace("Removing image: '%s' due to previously existing",
filename)
skip_list.append(idx)
if self._existing_count != 0:
logger.info(
"Skipping %s frames due to skip_existing/skip_existing_faces.",
self._existing_count)
logger.debug("Adding skip list: %s", skip_list)
self._images.add_skip_list(skip_list)
def process(self):
""" The entry point for triggering the Extraction Process.
Should only be called from :class:`lib.cli.ScriptExecutor`
"""
logger.info('Starting, this may take a while...')
# from lib.queue_manager import queue_manager ; queue_manager.debug_monitor(3)
self._threaded_redirector("load")
self._run_extraction()
for thread in self._threads:
thread.join()
self._alignments.save()
finalize(self._images.process_count + self._existing_count,
self._alignments.faces_count, self._verify_output)
def _threaded_redirector(self, task, io_args=None):
""" Redirect image input/output tasks to relevant queues in background thread
Parameters
----------
task: str
The name of the task to be put into a background thread
io_args: tuple, optional
Any arguments that need to be provided to the background function
"""
logger.debug("Threading task: (Task: '%s')", task)
io_args = tuple() if io_args is None else (io_args, )
func = getattr(self, "_{}".format(task))
io_thread = MultiThread(func, *io_args, thread_count=1)
io_thread.start()
self._threads.append(io_thread)
def _load(self):
""" Load the images
Loads images from :class:`lib.image.ImagesLoader`, formats them into a dict compatible
with :class:`plugins.extract.Pipeline.Extractor` and passes them into the extraction queue.
"""
logger.debug("Load Images: Start")
load_queue = self._extractor.input_queue
for filename, image in self._images.load():
if load_queue.shutdown.is_set():
logger.debug("Load Queue: Stop signal received. Terminating")
break
item = ExtractMedia(filename, image[..., :3])
load_queue.put(item)
load_queue.put("EOF")
logger.debug("Load Images: Complete")
def _reload(self, detected_faces):
""" Reload the images and pair to detected face
When the extraction pipeline is running in serial mode, images are reloaded from disk,
paired with their extraction data and passed back into the extraction queue
Parameters
----------
detected_faces: dict
Dictionary of :class:`plugins.extract.pipeline.ExtractMedia` with the filename as the
key for repopulating the image attribute.
"""
logger.debug("Reload Images: Start. Detected Faces Count: %s",
len(detected_faces))
load_queue = self._extractor.input_queue
for filename, image in self._images.load():
if load_queue.shutdown.is_set():
logger.debug("Reload Queue: Stop signal received. Terminating")
break
logger.trace("Reloading image: '%s'", filename)
extract_media = detected_faces.pop(filename, None)
if not extract_media:
logger.warning("Couldn't find faces for: %s", filename)
continue
extract_media.set_image(image)
load_queue.put(extract_media)
load_queue.put("EOF")
logger.debug("Reload Images: Complete")
def _run_extraction(self):
""" The main Faceswap Extraction process
Receives items from :class:`plugins.extract.Pipeline.Extractor` and either saves out the
faces and data (if on the final pass) or reprocesses data through the pipeline for serial
processing.
"""
size = self._args.size if hasattr(self._args, "size") else 256
saver = ImagesSaver(self._output_dir, as_bytes=True)
exception = False
phase_desc = "Extraction"
for phase in range(self._extractor.passes):
if exception:
break
is_final = self._extractor.final_pass
detected_faces = dict()
self._extractor.launch()
self._check_thread_error()
if self._args.singleprocess:
phase_desc = self._extractor.phase.title()
desc = "Running pass {} of {}: {}".format(phase + 1,
self._extractor.passes,
phase_desc)
status_bar = tqdm(self._extractor.detected_faces(),
total=self._images.process_count,
file=sys.stdout,
desc=desc)
for idx, extract_media in enumerate(status_bar):
self._check_thread_error()
if is_final:
self._output_processing(extract_media, size)
self._output_faces(saver, extract_media)
if self._save_interval and (idx +
1) % self._save_interval == 0:
self._alignments.save()
else:
extract_media.remove_image()
# cache extract_media for next run
detected_faces[extract_media.filename] = extract_media
status_bar.update(1)
if not is_final:
logger.debug("Reloading images")
self._threaded_redirector("reload", detected_faces)
saver.close()
def _check_thread_error(self):
""" Check if any errors have occurred in the running threads and their errors """
for thread in self._threads:
thread.check_and_raise_error()
def _output_processing(self, extract_media, size):
""" Prepare faces for output
Loads the aligned face, perform any processing actions and verify the output.
Parameters
----------
extract_media: :class:`plugins.extract.pipeline.ExtractMedia`
Output from :class:`plugins.extract.pipeline.Extractor`
size: int
The size that the aligned face should be created at
"""
for face in extract_media.detected_faces:
face.load_aligned(extract_media.image, size=size)
self._post_process.do_actions(extract_media)
extract_media.remove_image()
faces_count = len(extract_media.detected_faces)
if faces_count == 0:
logger.verbose("No faces were detected in image: %s",
os.path.basename(extract_media.filename))
if not self._verify_output and faces_count > 1:
self._verify_output = True
def _output_faces(self, saver, extract_media):
""" Output faces to save thread
Set the face filename based on the frame name and put the face to the
:class:`~lib.image.ImagesSaver` save queue and add the face information to the alignments
data.
Parameters
----------
saver: lib.images.ImagesSaver
The background saver for saving the image
extract_media: :class:`~plugins.extract.pipeline.ExtractMedia`
The output from :class:`~plugins.extract.Pipeline.Extractor`
"""
logger.trace("Outputting faces for %s", extract_media.filename)
final_faces = list()
filename, extension = os.path.splitext(
os.path.basename(extract_media.filename))
for idx, face in enumerate(extract_media.detected_faces):
output_filename = "{}_{}{}".format(filename, str(idx), extension)
face.hash, image = encode_image_with_hash(face.aligned_face,
extension)
saver.save(output_filename, image)
final_faces.append(face.to_alignment())
self._alignments.data[os.path.basename(
extract_media.filename)] = dict(faces=final_faces)
del extract_media
class Extract():
""" The extract process. """
def __init__(self, arguments):
logger.debug("Initializing %s: (args: %s", self.__class__.__name__, arguments)
self.args = arguments
Utils.set_verbosity(self.args.loglevel)
self.output_dir = get_folder(self.args.output_dir)
logger.info("Output Directory: %s", self.args.output_dir)
self.images = Images(self.args)
self.alignments = Alignments(self.args, True, self.images.is_video)
self.post_process = PostProcess(arguments)
self.extractor = Extractor(self.args.detector,
self.args.aligner,
self.args.loglevel,
self.args.multiprocess,
self.args.rotate_images,
self.args.min_size)
self.save_queue = queue_manager.get_queue("extract_save")
self.verify_output = False
self.save_interval = None
if hasattr(self.args, "save_interval"):
self.save_interval = self.args.save_interval
logger.debug("Initialized %s", self.__class__.__name__)
@property
def skip_num(self):
""" Number of frames to skip if extract_every_n is passed """
return self.args.extract_every_n if hasattr(self.args, "extract_every_n") else 1
def process(self):
""" Perform the extraction process """
logger.info('Starting, this may take a while...')
# queue_manager.debug_monitor(3)
self.threaded_io("load")
save_thread = self.threaded_io("save")
self.run_extraction()
save_thread.join()
self.alignments.save()
Utils.finalize(self.images.images_found // self.skip_num,
self.alignments.faces_count,
self.verify_output)
def threaded_io(self, task, io_args=None):
""" Perform I/O task in a background thread """
logger.debug("Threading task: (Task: '%s')", task)
io_args = tuple() if io_args is None else (io_args, )
if task == "load":
func = self.load_images
elif task == "save":
func = self.save_faces
elif task == "reload":
func = self.reload_images
io_thread = MultiThread(func, *io_args, thread_count=1)
io_thread.start()
return io_thread
def load_images(self):
""" Load the images """
logger.debug("Load Images: Start")
load_queue = self.extractor.input_queue
idx = 0
for filename, image in self.images.load():
idx += 1
if load_queue.shutdown.is_set():
logger.debug("Load Queue: Stop signal received. Terminating")
break
if idx % self.skip_num != 0:
logger.trace("Skipping image '%s' due to extract_every_n = %s",
filename, self.skip_num)
continue
if image is None or not image.any():
logger.warning("Unable to open image. Skipping: '%s'", filename)
continue
imagename = os.path.basename(filename)
if imagename in self.alignments.data.keys():
logger.trace("Skipping image: '%s'", filename)
continue
item = {"filename": filename,
"image": image}
load_queue.put(item)
load_queue.put("EOF")
logger.debug("Load Images: Complete")
def reload_images(self, detected_faces):
""" Reload the images and pair to detected face """
logger.debug("Reload Images: Start. Detected Faces Count: %s", len(detected_faces))
load_queue = self.extractor.input_queue
for filename, image in self.images.load():
if load_queue.shutdown.is_set():
logger.debug("Reload Queue: Stop signal received. Terminating")
break
logger.trace("Reloading image: '%s'", filename)
detect_item = detected_faces.pop(filename, None)
if not detect_item:
logger.warning("Couldn't find faces for: %s", filename)
continue
detect_item["image"] = image
load_queue.put(detect_item)
load_queue.put("EOF")
logger.debug("Reload Images: Complete")
def save_faces(self):
""" Save the generated faces """
logger.debug("Save Faces: Start")
while True:
if self.save_queue.shutdown.is_set():
logger.debug("Save Queue: Stop signal received. Terminating")
break
item = self.save_queue.get()
logger.trace(item)
if item == "EOF":
break
filename, face = item
logger.trace("Saving face: '%s'", filename)
try:
with open(filename, "wb") as out_file:
out_file.write(face)
except Exception as err: # pylint: disable=broad-except
logger.error("Failed to save image '%s'. Original Error: %s", filename, err)
continue
logger.debug("Save Faces: Complete")
def process_item_count(self):
""" Return the number of items to be processedd """
processed = sum(os.path.basename(frame) in self.alignments.data.keys()
for frame in self.images.input_images)
logger.debug("Items already processed: %s", processed)
if processed != 0 and self.args.skip_existing:
logger.info("Skipping previously extracted frames: %s", processed)
if processed != 0 and self.args.skip_faces:
logger.info("Skipping frames with detected faces: %s", processed)
to_process = (self.images.images_found - processed) // self.skip_num
logger.debug("Items to be Processed: %s", to_process)
if to_process == 0:
logger.error("No frames to process. Exiting")
queue_manager.terminate_queues()
exit(0)
return to_process
def run_extraction(self):
""" Run Face Detection """
to_process = self.process_item_count()
size = self.args.size if hasattr(self.args, "size") else 256
align_eyes = self.args.align_eyes if hasattr(self.args, "align_eyes") else False
exception = False
for phase in range(self.extractor.passes):
if exception:
break
is_final = self.extractor.final_pass
detected_faces = dict()
self.extractor.launch()
for idx, faces in enumerate(tqdm(self.extractor.detected_faces(),
total=to_process,
file=sys.stdout,
desc="Running pass {} of {}: {}".format(
phase + 1,
self.extractor.passes,
self.extractor.phase.title()))):
exception = faces.get("exception", False)
if exception:
break
filename = faces["filename"]
if self.extractor.final_pass:
self.output_processing(faces, align_eyes, size, filename)
self.output_faces(filename, faces)
if self.save_interval and idx + 1 % self.save_interval == 0:
self.alignments.save()
else:
del faces["image"]
detected_faces[filename] = faces
if is_final:
logger.debug("Putting EOF to save")
self.save_queue.put("EOF")
else:
logger.debug("Reloading images")
self.threaded_io("reload", detected_faces)
def output_processing(self, faces, align_eyes, size, filename):
""" Prepare faces for output """
self.align_face(faces, align_eyes, size, filename)
self.post_process.do_actions(faces)
faces_count = len(faces["detected_faces"])
if faces_count == 0:
logger.verbose("No faces were detected in image: %s",
os.path.basename(filename))
if not self.verify_output and faces_count > 1:
self.verify_output = True
def align_face(self, faces, align_eyes, size, filename):
""" Align the detected face and add the destination file path """
final_faces = list()
image = faces["image"]
landmarks = faces["landmarks"]
detected_faces = faces["detected_faces"]
for idx, face in enumerate(detected_faces):
detected_face = DetectedFace()
detected_face.from_bounding_box(face, image)
detected_face.landmarksXY = landmarks[idx]
detected_face.load_aligned(image, size=size, align_eyes=align_eyes)
final_faces.append({"file_location": self.output_dir / Path(filename).stem,
"face": detected_face})
faces["detected_faces"] = final_faces
def output_faces(self, filename, faces):
""" Output faces to save thread """
final_faces = list()
for idx, detected_face in enumerate(faces["detected_faces"]):
output_file = detected_face["file_location"]
extension = Path(filename).suffix
out_filename = "{}_{}{}".format(str(output_file), str(idx), extension)
face = detected_face["face"]
resized_face = face.aligned_face
face.hash, img = hash_encode_image(resized_face, extension)
self.save_queue.put((out_filename, img))
final_faces.append(face.to_alignment())
self.alignments.data[os.path.basename(filename)] = final_faces
class Extract():
""" The extract process. """
def __init__(self, arguments):
logger.debug("Initializing %s: (args: %s", self.__class__.__name__,
arguments)
self.args = arguments
Utils.set_verbosity(self.args.loglevel)
self.output_dir = get_folder(self.args.output_dir)
logger.info("Output Directory: %s", self.args.output_dir)
self.images = Images(self.args)
self.alignments = Alignments(self.args, True, self.images.is_video)
self.post_process = PostProcess(arguments)
self.extractor = Extractor(self.args.detector, self.args.aligner,
self.args.loglevel, self.args.multiprocess,
self.args.rotate_images, self.args.min_size)
self.save_queue = queue_manager.get_queue("extract_save")
self.verify_output = False
self.save_interval = None
if hasattr(self.args, "save_interval"):
self.save_interval = self.args.save_interval
logger.debug("Initialized %s", self.__class__.__name__)
@property
def skip_num(self):
""" Number of frames to skip if extract_every_n is passed """
return self.args.extract_every_n if hasattr(self.args,
"extract_every_n") else 1
def process(self):
""" Perform the extraction process """
logger.info('Starting, this may take a while...')
# queue_manager.debug_monitor(3)
self.threaded_io("load")
save_thread = self.threaded_io("save")
self.run_extraction()
save_thread.join()
self.alignments.save()
Utils.finalize(self.images.images_found // self.skip_num,
self.alignments.faces_count, self.verify_output)
def threaded_io(self, task, io_args=None):
""" Perform I/O task in a background thread """
logger.debug("Threading task: (Task: '%s')", task)
io_args = tuple() if io_args is None else (io_args, )
if task == "load":
func = self.load_images
elif task == "save":
func = self.save_faces
elif task == "reload":
func = self.reload_images
io_thread = MultiThread(func, *io_args, thread_count=1)
io_thread.start()
return io_thread
def load_images(self):
""" Load the images """
logger.debug("Load Images: Start")
load_queue = self.extractor.input_queue
idx = 0
for filename, image in self.images.load():
idx += 1
if load_queue.shutdown.is_set():
logger.debug("Load Queue: Stop signal received. Terminating")
break
if idx % self.skip_num != 0:
logger.trace("Skipping image '%s' due to extract_every_n = %s",
filename, self.skip_num)
continue
if image is None or not image.any():
logger.warning("Unable to open image. Skipping: '%s'",
filename)
continue
imagename = os.path.basename(filename)
if imagename in self.alignments.data.keys():
logger.trace("Skipping image: '%s'", filename)
continue
item = {"filename": filename, "image": image}
load_queue.put(item)
load_queue.put("EOF")
logger.debug("Load Images: Complete")
def reload_images(self, detected_faces):
""" Reload the images and pair to detected face """
logger.debug("Reload Images: Start. Detected Faces Count: %s",
len(detected_faces))
load_queue = self.extractor.input_queue
for filename, image in self.images.load():
if load_queue.shutdown.is_set():
logger.debug("Reload Queue: Stop signal received. Terminating")
break
logger.trace("Reloading image: '%s'", filename)
detect_item = detected_faces.pop(filename, None)
if not detect_item:
logger.warning("Couldn't find faces for: %s", filename)
continue
detect_item["image"] = image
load_queue.put(detect_item)
load_queue.put("EOF")
logger.debug("Reload Images: Complete")
def save_faces(self):
""" Save the generated faces """
logger.debug("Save Faces: Start")
while True:
if self.save_queue.shutdown.is_set():
logger.debug("Save Queue: Stop signal received. Terminating")
break
item = self.save_queue.get()
logger.trace(item)
if item == "EOF":
break
filename, face = item
logger.trace("Saving face: '%s'", filename)
try:
with open(filename, "wb") as out_file:
out_file.write(face)
except Exception as err: # pylint: disable=broad-except
logger.error("Failed to save image '%s'. Original Error: %s",
filename, err)
continue
logger.debug("Save Faces: Complete")
def process_item_count(self):
""" Return the number of items to be processedd """
processed = sum(
os.path.basename(frame) in self.alignments.data.keys()
for frame in self.images.input_images)
logger.debug("Items already processed: %s", processed)
if processed != 0 and self.args.skip_existing:
logger.info("Skipping previously extracted frames: %s", processed)
if processed != 0 and self.args.skip_faces:
logger.info("Skipping frames with detected faces: %s", processed)
to_process = (self.images.images_found - processed) // self.skip_num
logger.debug("Items to be Processed: %s", to_process)
if to_process == 0:
logger.error("No frames to process. Exiting")
queue_manager.terminate_queues()
exit(0)
return to_process
def run_extraction(self):
""" Run Face Detection """
to_process = self.process_item_count()
size = self.args.size if hasattr(self.args, "size") else 256
align_eyes = self.args.align_eyes if hasattr(self.args,
"align_eyes") else False
exception = False
for phase in range(self.extractor.passes):
if exception:
break
is_final = self.extractor.final_pass
detected_faces = dict()
self.extractor.launch()
for idx, faces in enumerate(
tqdm(self.extractor.detected_faces(),
total=to_process,
file=sys.stdout,
desc="Running pass {} of {}: {}".format(
phase + 1, self.extractor.passes,
self.extractor.phase.title()))):
exception = faces.get("exception", False)
if exception:
break
filename = faces["filename"]
if self.extractor.final_pass:
self.output_processing(faces, align_eyes, size, filename)
self.output_faces(filename, faces)
if self.save_interval and (idx +
1) % self.save_interval == 0:
self.alignments.save()
else:
del faces["image"]
detected_faces[filename] = faces
if is_final:
logger.debug("Putting EOF to save")
self.save_queue.put("EOF")
else:
logger.debug("Reloading images")
self.threaded_io("reload", detected_faces)
def output_processing(self, faces, align_eyes, size, filename):
""" Prepare faces for output """
self.align_face(faces, align_eyes, size, filename)
self.post_process.do_actions(faces)
faces_count = len(faces["detected_faces"])
if faces_count == 0:
logger.verbose("No faces were detected in image: %s",
os.path.basename(filename))
if not self.verify_output and faces_count > 1:
self.verify_output = True
def align_face(self, faces, align_eyes, size, filename):
""" Align the detected face and add the destination file path """
final_faces = list()
image = faces["image"]
landmarks = faces["landmarks"]
detected_faces = faces["detected_faces"]
for idx, face in enumerate(detected_faces):
detected_face = DetectedFace()
detected_face.from_bounding_box(face, image)
detected_face.landmarksXY = landmarks[idx]
detected_face.load_aligned(image, size=size, align_eyes=align_eyes)
final_faces.append({
"file_location":
self.output_dir / Path(filename).stem,
"face":
detected_face
})
faces["detected_faces"] = final_faces
def output_faces(self, filename, faces):
""" Output faces to save thread """
final_faces = list()
for idx, detected_face in enumerate(faces["detected_faces"]):
output_file = detected_face["file_location"]
extension = Path(filename).suffix
out_filename = "{}_{}{}".format(str(output_file), str(idx),
extension)
face = detected_face["face"]
resized_face = face.aligned_face
face.hash, img = hash_encode_image(resized_face, extension)
self.save_queue.put((out_filename, img))
final_faces.append(face.to_alignment())
self.alignments.data[os.path.basename(filename)] = final_faces
class Extract(): # pylint:disable=too-few-public-methods
""" Re-extract faces from source frames based on Alignment data
Parameters
----------
alignments: :class:`tools.lib_alignments.media.AlignmentData`
The alignments data loaded from an alignments file for this rename job
arguments: :class:`argparse.Namespace`
The :mod:`argparse` arguments as passed in from :mod:`tools.py`
"""
def __init__(self, alignments, arguments):
logger.debug("Initializing %s: (arguments: %s)",
self.__class__.__name__, arguments)
self._arguments = arguments
self._alignments = alignments
self._is_legacy = self._alignments.version == 1.0 # pylint:disable=protected-access
self._mask_pipeline = None
self._faces_dir = arguments.faces_dir
self._frames = Frames(arguments.frames_dir)
self._extracted_faces = ExtractedFaces(self._frames,
self._alignments,
size=arguments.size)
self._saver = None
logger.debug("Initialized %s", self.__class__.__name__)
def process(self):
""" Run the re-extraction from Alignments file process"""
logger.info("[EXTRACT FACES]") # Tidy up cli output
self._check_folder()
if self._is_legacy:
self._legacy_check()
self._saver = ImagesSaver(self._faces_dir, as_bytes=True)
self._export_faces()
def _check_folder(self):
""" Check that the faces folder doesn't pre-exist and create. """
err = None
if not self._faces_dir:
err = "ERROR: Output faces folder not provided."
elif not os.path.isdir(self._faces_dir):
logger.debug("Creating folder: '%s'", self._faces_dir)
os.makedirs(self._faces_dir)
elif os.listdir(self._faces_dir):
err = "ERROR: Output faces folder should be empty: '{}'".format(
self._faces_dir)
if err:
logger.error(err)
sys.exit(0)
logger.verbose("Creating output folder at '%s'", self._faces_dir)
def _legacy_check(self):
""" Check whether the alignments file was created with the legacy extraction method.
If so, force user to re-extract all faces if any options have been specified, otherwise
raise the appropriate warnings and set the legacy options.
"""
if self._arguments.large or self._arguments.extract_every_n != 1:
logger.warning(
"This alignments file was generated with the legacy extraction method."
)
logger.warning(
"You should run this extraction job, but with 'large' deselected and "
"'extract-every-n' set to 1 to update the alignments file.")
logger.warning(
"You can then re-run this extraction job with your chosen options."
)
sys.exit(0)
maskers = ["components", "extended"]
nn_masks = [
mask for mask in list(self._alignments.mask_summary)
if mask not in maskers
]
logtype = logger.warning if nn_masks else logger.info
logtype(
"This alignments file was created with the legacy extraction method and will be "
"updated.")
logtype(
"Faces will be extracted using the new method and landmarks based masks will be "
"regenerated.")
if nn_masks:
logtype(
"However, the NN based masks '%s' will be cropped to the legacy extraction "
"method, so you may want to run the mask tool to regenerate these "
"masks.", "', '".join(nn_masks))
self._mask_pipeline = Extractor(None, None, maskers, multiprocess=True)
self._mask_pipeline.launch()
# Update alignments versioning
self._alignments._version = _VERSION # pylint:disable=protected-access
def _export_faces(self):
""" Export the faces to the output folder. """
extracted_faces = 0
skip_list = self._set_skip_list()
count = self._frames.count if skip_list is None else self._frames.count - len(
skip_list)
for filename, image in tqdm(self._frames.stream(skip_list=skip_list),
total=count,
desc="Saving extracted faces"):
frame_name = os.path.basename(filename)
if not self._alignments.frame_exists(frame_name):
logger.verbose("Skipping '%s' - Alignments not found",
frame_name)
continue
extracted_faces += self._output_faces(frame_name, image)
if self._is_legacy and extracted_faces != 0 and not self._arguments.large:
self._alignments.save()
logger.info("%s face(s) extracted", extracted_faces)
def _set_skip_list(self):
""" Set the indices for frames that should be skipped based on the `extract_every_n`
command line option.
Returns
-------
list or ``None``
A list of indices to be skipped if extract_every_n is not `1` otherwise
returns ``None``
"""
skip_num = self._arguments.extract_every_n
if skip_num == 1:
logger.debug("Not skipping any frames")
return None
skip_list = []
for idx, item in enumerate(self._frames.file_list_sorted):
if idx % skip_num != 0:
logger.trace(
"Adding image '%s' to skip list due to extract_every_n = %s",
item["frame_fullname"], skip_num)
skip_list.append(idx)
logger.debug("Adding skip list: %s", skip_list)
return skip_list
def _output_faces(self, filename, image):
""" For each frame save out the faces
Parameters
----------
filename: str
The filename (without the full path) of the current frame
image: :class:`numpy.ndarray`
The full frame that faces are to be extracted from
Returns
-------
int
The total number of faces that have been extracted
"""
logger.trace("Outputting frame: %s", filename)
face_count = 0
frame_name = os.path.splitext(filename)[0]
faces = self._select_valid_faces(filename, image)
if not faces:
return face_count
if self._is_legacy:
faces = self._process_legacy(filename, image, faces)
for idx, face in enumerate(faces):
output = "{}_{}.png".format(frame_name, str(idx))
meta = dict(alignments=face.to_png_meta(),
source=dict(
alignments_version=self._alignments.version,
original_filename=output,
face_index=idx,
source_filename=filename,
source_is_video=self._frames.is_video))
self._saver.save(
output, encode_image(face.aligned.face, ".png", metadata=meta))
if not self._arguments.large and self._is_legacy:
face.thumbnail = generate_thumbnail(face.aligned.face,
size=96,
quality=60)
self._alignments.data[filename]["faces"][
idx] = face.to_alignment()
face_count += 1
self._saver.close()
return face_count
def _select_valid_faces(self, frame, image):
""" Return the aligned faces from a frame that meet the selection criteria,
Parameters
----------
frame: str
The filename (without the full path) of the current frame
image: :class:`numpy.ndarray`
The full frame that faces are to be extracted from
Returns
-------
list:
List of valid :class:`lib,align.DetectedFace` objects
"""
faces = self._extracted_faces.get_faces_in_frame(frame, image=image)
if not self._arguments.large:
valid_faces = faces
else:
sizes = self._extracted_faces.get_roi_size_for_frame(frame)
valid_faces = [
faces[idx] for idx, size in enumerate(sizes)
if size >= self._extracted_faces.size
]
logger.trace("frame: '%s', total_faces: %s, valid_faces: %s", frame,
len(faces), len(valid_faces))
return valid_faces
def _process_legacy(self, filename, image, detected_faces):
""" Process legacy face extractions to new extraction method.
Updates stored masks to new extract size
Parameters
----------
filename: str
The current frame filename
image: :class:`numpy.ndarray`
The current image the contains the faces
detected_faces: list
list of :class:`lib.align.DetectedFace` objects for the current frame
"""
# Update landmarks based masks for face centering
mask_item = ExtractMedia(filename,
image,
detected_faces=detected_faces)
self._mask_pipeline.input_queue.put(mask_item)
faces = next(self._mask_pipeline.detected_faces()).detected_faces
# Pad and shift Neural Network based masks to face centering
for face in faces:
self._pad_legacy_masks(face)
return faces
@classmethod
def _pad_legacy_masks(cls, detected_face):
""" Recenter legacy Neural Network based masks from legacy centering to face centering
and pad accordingly.
Update the masks back into the detected face objects.
Parameters
----------
detected_face: :class:`lib.align.DetectedFace`
The detected face to update the masks for
"""
offset = detected_face.aligned.pose.offset["face"]
for name, mask in detected_face.mask.items(
): # Re-center mask and pad to face size
if name in ("components", "extended"):
continue
old_mask = mask.mask.astype("float32") / 255.0
size = old_mask.shape[0]
new_size = int(size + (size * _EXTRACT_RATIOS["face"]) / 2)
shift = np.rint(offset *
(size -
(size * _EXTRACT_RATIOS["face"]))).astype("int32")
pos = np.array([(new_size // 2 - size // 2) - shift[1],
(new_size // 2) + (size // 2) - shift[1],
(new_size // 2 - size // 2) - shift[0],
(new_size // 2) + (size // 2) - shift[0]])
bounds = np.array([
max(0, pos[0]),
min(new_size, pos[1]),
max(0, pos[2]),
min(new_size, pos[3])
])
slice_in = [
slice(0 - (pos[0] - bounds[0]), size - (pos[1] - bounds[1])),
slice(0 - (pos[2] - bounds[2]), size - (pos[3] - bounds[3]))
]
slice_out = [
slice(bounds[0], bounds[1]),
slice(bounds[2], bounds[3])
]
new_mask = np.zeros((new_size, new_size, 1), dtype="float32")
new_mask[slice_out[0], slice_out[1], :] = old_mask[slice_in[0],
slice_in[1], :]
mask.replace_mask(new_mask)
# Get the affine matrix from recently generated components mask
# pylint:disable=protected-access
mask._affine_matrix = detected_face.mask[
"components"].affine_matrix
def launch_aligner():
""" Load the aligner plugin to retrieve landmarks """
extractor = Extractor(None, "fan", None, normalize_method="hist")
extractor.set_batchsize("align", 1)
extractor.launch()
return extractor