def extract_vggface2_dataset(input_dir, device_args={} ):
multi_gpu = device_args.get('multi_gpu', False)
cpu_only = device_args.get('cpu_only', False)
input_path = Path(input_dir)
if not input_path.exists():
raise ValueError('Input directory not found. Please ensure it exists.')
bb_csv = input_path / 'loose_bb_train.csv'
if not bb_csv.exists():
raise ValueError('loose_bb_train.csv found. Please ensure it exists.')
bb_lines = bb_csv.read_text().split('\n')
bb_lines.pop(0)
bb_dict = {}
for line in bb_lines:
name, l, t, w, h = line.split(',')
name = name[1:-1]
l, t, w, h = [ int(x) for x in (l, t, w, h) ]
bb_dict[name] = (l,t,w, h)
output_path = input_path.parent / (input_path.name + '_out')
dir_names = Path_utils.get_all_dir_names(input_path)
if not output_path.exists():
output_path.mkdir(parents=True, exist_ok=True)
data = []
for dir_name in io.progress_bar_generator(dir_names, "Collecting"):
cur_input_path = input_path / dir_name
cur_output_path = output_path / dir_name
if not cur_output_path.exists():
cur_output_path.mkdir(parents=True, exist_ok=True)
input_path_image_paths = Path_utils.get_image_paths(cur_input_path)
for filename in input_path_image_paths:
filename_path = Path(filename)
name = filename_path.parent.name + '/' + filename_path.stem
if name not in bb_dict:
continue
l,t,w,h = bb_dict[name]
if min(w,h) < 128:
continue
data += [ ExtractSubprocessor.Data(filename=filename,rects=[ (l,t,l+w,t+h) ], landmarks_accurate=False, force_output_path=cur_output_path ) ]
face_type = FaceType.fromString('full_face')
io.log_info ('Performing 2nd pass...')
data = ExtractSubprocessor (data, 'landmarks', 256, face_type, debug_dir=None, multi_gpu=multi_gpu, cpu_only=cpu_only, manual=False).run()
io.log_info ('Performing 3rd pass...')
ExtractSubprocessor (data, 'final', 256, face_type, debug_dir=None, multi_gpu=multi_gpu, cpu_only=cpu_only, manual=False, final_output_path=None).run()
def dev_test(input_dir):
input_path = Path(input_dir)
dir_names = Path_utils.get_all_dir_names(input_path)
for dir_name in io.progress_bar_generator(dir_names, desc="Processing"):
img_paths = Path_utils.get_image_paths (input_path / dir_name)
for filename in img_paths:
filepath = Path(filename)
dflimg = DFLIMG.load (filepath)
if dflimg is None:
raise ValueError
dflimg.embed_and_set(filename, person_name=dir_name)
def dev_test(input_dir):
input_path = Path(input_dir)
dir_names = Path_utils.get_all_dir_names(input_path)
for dir_name in dir_names:
img_paths = Path_utils.get_image_paths (input_path / dir_name)
for filename in img_paths:
filepath = Path(filename)
dflimg = DFLIMG.load (filepath)
if dflimg is None:
raise ValueError
import code
code.interact(local=dict(globals(), **locals()))
def extract_vggface2_dataset(input_dir, device_args={}):
multi_gpu = device_args.get('multi_gpu', False)
cpu_only = device_args.get('cpu_only', False)
input_path = Path(input_dir)
if not input_path.exists():
raise ValueError('Input directory not found. Please ensure it exists.')
output_path = input_path.parent / (input_path.name + '_out')
dir_names = Path_utils.get_all_dir_names(input_path)
if not output_path.exists():
output_path.mkdir(parents=True, exist_ok=True)
for dir_name in dir_names:
cur_input_path = input_path / dir_name
cur_output_path = output_path / dir_name
l = len(Path_utils.get_image_paths(cur_input_path))
if l < 250 or l > 350:
continue
io.log_info(f"Processing: {str(cur_input_path)} ")
if not cur_output_path.exists():
cur_output_path.mkdir(parents=True, exist_ok=True)
Extractor.main(str(cur_input_path),
str(cur_output_path),
detector='s3fd',
image_size=256,
face_type='full_face',
max_faces_from_image=1,
device_args=device_args)
io.log_info(f"Sorting: {str(cur_input_path)} ")
Sorter.main(input_path=str(cur_output_path), sort_by_method='hist')
try:
io.log_info(f"Removing: {str(cur_input_path)} ")
shutil.rmtree(cur_input_path)
except:
io.log_info(f"unable to remove: {str(cur_input_path)} ")
def load(sample_type,
samples_path,
target_samples_path=None,
person_id_mode=False):
cache = SampleLoader.cache
if str(samples_path) not in cache.keys():
cache[str(samples_path)] = [None] * SampleType.QTY
datas = cache[str(samples_path)]
if sample_type == SampleType.IMAGE:
if datas[sample_type] is None:
datas[sample_type] = [
Sample(filename=filename)
for filename in io.progress_bar_generator(
Path_utils.get_image_paths(samples_path), "Loading")
]
elif sample_type == SampleType.FACE:
if datas[sample_type] is None:
if person_id_mode:
dir_names = Path_utils.get_all_dir_names(samples_path)
all_samples = []
for i, dir_name in io.progress_bar_generator(
[*enumerate(dir_names)], "Loading"):
all_samples += SampleLoader.upgradeToFaceSamples(
[
Sample(filename=filename, person_id=i)
for filename in Path_utils.get_image_paths(
samples_path / dir_name)
],
silent=True)
datas[sample_type] = all_samples
else:
datas[sample_type] = SampleLoader.upgradeToFaceSamples([
Sample(filename=filename) for filename in
Path_utils.get_image_paths(samples_path)
])
elif sample_type == SampleType.FACE_TEMPORAL_SORTED:
if datas[sample_type] is None:
datas[
sample_type] = SampleLoader.upgradeToFaceTemporalSortedSamples(
SampleLoader.load(SampleType.FACE, samples_path))
elif sample_type == SampleType.FACE_YAW_SORTED:
if datas[sample_type] is None:
datas[
sample_type] = SampleLoader.upgradeToFaceYawSortedSamples(
SampleLoader.load(SampleType.FACE, samples_path))
elif sample_type == SampleType.FACE_YAW_SORTED_AS_TARGET:
if datas[sample_type] is None:
if target_samples_path is None:
raise Exception(
'target_samples_path is None for FACE_YAW_SORTED_AS_TARGET'
)
datas[
sample_type] = SampleLoader.upgradeToFaceYawSortedAsTargetSamples(
SampleLoader.load(SampleType.FACE_YAW_SORTED,
samples_path),
SampleLoader.load(SampleType.FACE_YAW_SORTED,
target_samples_path))
return datas[sample_type]
def get_person_id_max_count(samples_path):
return len(Path_utils.get_all_dir_names(samples_path))
def load(sample_type, samples_path, target_samples_path=None, person_id_mode=False, use_caching=False):
cache = SampleLoader.cache
if str(samples_path) not in cache.keys():
cache[str(samples_path)] = [None]*SampleType.QTY
datas = cache[str(samples_path)]
if sample_type == SampleType.IMAGE:
if datas[sample_type] is None:
datas[sample_type] = [ Sample(filename=filename) for filename in io.progress_bar_generator( Path_utils.get_image_paths(samples_path), "Loading") ]
elif sample_type == SampleType.FACE:
if datas[sample_type] is None:
if not use_caching:
datas[sample_type] = SampleLoader.upgradeToFaceSamples( [ Sample(filename=filename) for filename in Path_utils.get_image_paths(samples_path) ] )
else:
samples_dat = samples_path / 'samples.dat'
if samples_dat.exists():
io.log_info (f"Using saved samples info from '{samples_dat}' ")
all_samples = pickle.loads(samples_dat.read_bytes())
if person_id_mode:
for samples in all_samples:
for sample in samples:
sample.filename = str( samples_path / Path(sample.filename) )
else:
for sample in all_samples:
sample.filename = str( samples_path / Path(sample.filename) )
datas[sample_type] = all_samples
else:
if person_id_mode:
dir_names = Path_utils.get_all_dir_names(samples_path)
all_samples = []
for i, dir_name in io.progress_bar_generator( [*enumerate(dir_names)] , "Loading"):
all_samples += [ SampleLoader.upgradeToFaceSamples( [ Sample(filename=filename, person_id=i) for filename in Path_utils.get_image_paths( samples_path / dir_name ) ], silent=True ) ]
datas[sample_type] = all_samples
else:
datas[sample_type] = all_samples = SampleLoader.upgradeToFaceSamples( [ Sample(filename=filename) for filename in Path_utils.get_image_paths(samples_path) ] )
if person_id_mode:
for samples in all_samples:
for sample in samples:
sample.filename = str(Path(sample.filename).relative_to(samples_path))
else:
for sample in all_samples:
sample.filename = str(Path(sample.filename).relative_to(samples_path))
samples_dat.write_bytes (pickle.dumps(all_samples))
if person_id_mode:
for samples in all_samples:
for sample in samples:
sample.filename = str( samples_path / Path(sample.filename) )
else:
for sample in all_samples:
sample.filename = str( samples_path / Path(sample.filename) )
elif sample_type == SampleType.FACE_TEMPORAL_SORTED:
if datas[sample_type] is None:
datas[sample_type] = SampleLoader.upgradeToFaceTemporalSortedSamples( SampleLoader.load(SampleType.FACE, samples_path) )
elif sample_type == SampleType.FACE_YAW_SORTED:
if datas[sample_type] is None:
datas[sample_type] = SampleLoader.upgradeToFaceYawSortedSamples( SampleLoader.load(SampleType.FACE, samples_path) )
elif sample_type == SampleType.FACE_YAW_SORTED_AS_TARGET:
if datas[sample_type] is None:
if target_samples_path is None:
raise Exception('target_samples_path is None for FACE_YAW_SORTED_AS_TARGET')
datas[sample_type] = SampleLoader.upgradeToFaceYawSortedAsTargetSamples( SampleLoader.load(SampleType.FACE_YAW_SORTED, samples_path), SampleLoader.load(SampleType.FACE_YAW_SORTED, target_samples_path) )
return datas[sample_type]
def pack(samples_path):
samples_dat_path = samples_path / packed_faceset_filename
if samples_dat_path.exists():
io.log_info(f"{samples_dat_path} : file already exists !")
io.input_bool("Press enter to continue and overwrite.", False)
as_person_faceset = False
dir_names = Path_utils.get_all_dir_names(samples_path)
if len(dir_names) != 0:
as_person_faceset = io.input_bool(
f"{len(dir_names)} subdirectories found, process as person faceset? (y/n) skip:y : ",
True)
if as_person_faceset:
image_paths = []
for dir_name in dir_names:
image_paths += Path_utils.get_image_paths(samples_path /
dir_name)
else:
image_paths = Path_utils.get_image_paths(samples_path)
samples = samplelib.SampleHost.load_face_samples(image_paths)
samples_len = len(samples)
samples_configs = []
for sample in io.progress_bar_generator(samples, "Processing"):
sample_filepath = Path(sample.filename)
sample.filename = sample_filepath.name
if as_person_faceset:
sample.person_name = sample_filepath.parent.name
samples_configs.append(sample.get_config())
samples_bytes = pickle.dumps(samples_configs, 4)
of = open(samples_dat_path, "wb")
of.write(struct.pack("Q", PackedFaceset.VERSION))
of.write(struct.pack("Q", len(samples_bytes)))
of.write(samples_bytes)
del samples_bytes #just free mem
del samples_configs
sample_data_table_offset = of.tell()
of.write(bytes(8 * (samples_len + 1))) #sample data offset table
data_start_offset = of.tell()
offsets = []
for sample in io.progress_bar_generator(samples, "Packing"):
try:
if sample.person_name is not None:
sample_path = samples_path / sample.person_name / sample.filename
else:
sample_path = samples_path / sample.filename
with open(sample_path, "rb") as f:
b = f.read()
offsets.append(of.tell() - data_start_offset)
of.write(b)
except:
raise Exception(f"error while processing sample {sample_path}")
offsets.append(of.tell())
of.seek(sample_data_table_offset, 0)
for offset in offsets:
of.write(struct.pack("Q", offset))
of.seek(0, 2)
of.close()
for filename in io.progress_bar_generator(image_paths,
"Deleting files"):
Path(filename).unlink()
if as_person_faceset:
for dir_name in io.progress_bar_generator(dir_names,
"Deleting dirs"):
dir_path = samples_path / dir_name
try:
shutil.rmtree(dir_path)
except:
io.log_info(f"unable to remove: {dir_path} ")
