github/DeepFaceLab
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLab.git synced 2025-07-05 04:26:42 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

added new extractor: S3FD,

Browse source 
all extractors now produce less false-positive faces
This commit is contained in:
iperov 2019-03-10 23:18:10 +04:00
parent 9440224556
commit fbf39d2727
10 changed files with 83 additions and 112 deletions
Download patch file Download diff file Expand all files Collapse all files

9
.gitignore vendored
View file

@ -4,14 +4,5 @@
!*.txt
!*.jpg
!requirements*
!doc
!facelib
!gpufmkmgr
!localization
!mainscripts
!mathlib
!models
!nnlib
!utils
!Dockerfile*
!*.sh

BIN
doc/manual_ru.pdf
View file

Binary file not shown.

4
doc/manual_ru_source.xml
View file

File diff suppressed because one or more lines are too long

BIN
facelib/2DFAN-4.h5
View file

Binary file not shown.

140
facelib/LandmarksExtractor.py
View file

@ -3,101 +3,18 @@ import os
import cv2
from pathlib import Path
def transform(point, center, scale, resolution):
pt = np.array ( [point[0], point[1], 1.0] )
h = 200.0 * scale
m = np.eye(3)
m[0,0] = resolution / h
m[1,1] = resolution / h
m[0,2] = resolution * ( -center[0] / h + 0.5 )
m[1,2] = resolution * ( -center[1] / h + 0.5 )
m = np.linalg.inv(m)
return np.matmul (m, pt)[0:2]
def crop(image, center, scale, resolution=256.0):
ul = transform([1, 1], center, scale, resolution).astype( np.int )
br = transform([resolution, resolution], center, scale, resolution).astype( np.int )
if image.ndim > 2:
newDim = np.array([br[1] - ul[1], br[0] - ul[0], image.shape[2]], dtype=np.int32)
newImg = np.zeros(newDim, dtype=np.uint8)
else:
newDim = np.array([br[1] - ul[1], br[0] - ul[0]], dtype=np.int)
newImg = np.zeros(newDim, dtype=np.uint8)
ht = image.shape[0]
wd = image.shape[1]
newX = np.array([max(1, -ul[0] + 1), min(br[0], wd) - ul[0]], dtype=np.int32)
newY = np.array([max(1, -ul[1] + 1), min(br[1], ht) - ul[1]], dtype=np.int32)
oldX = np.array([max(1, ul[0] + 1), min(br[0], wd)], dtype=np.int32)
oldY = np.array([max(1, ul[1] + 1), min(br[1], ht)], dtype=np.int32)
newImg[newY[0] - 1:newY[1], newX[0] - 1:newX[1] ] = image[oldY[0] - 1:oldY[1], oldX[0] - 1:oldX[1], :]
newImg = cv2.resize(newImg, dsize=(int(resolution), int(resolution)), interpolation=cv2.INTER_LINEAR)
return newImg
def get_pts_from_predict(a, center, scale):
b = a.reshape ( (a.shape[0], a.shape[1]*a.shape[2]) )
c = b.argmax(1).reshape ( (a.shape[0], 1) ).repeat(2, axis=1).astype(np.float)
c[:,0] %= a.shape[2]
c[:,1] = np.apply_along_axis ( lambda x: np.floor(x / a.shape[2]), 0, c[:,1] )
for i in range(a.shape[0]):
pX, pY = int(c[i,0]), int(c[i,1])
if pX > 0 and pX < 63 and pY > 0 and pY < 63:
diff = np.array ( [a[i,pY,pX+1]-a[i,pY,pX-1], a[i,pY+1,pX]-a[i,pY-1,pX]] )
c[i] += np.sign(diff)*0.25
c += 0.5
return [ transform (c[i], center, scale, a.shape[2]) for i in range(a.shape[0]) ]
class LandmarksExtractor(object):
def __init__ (self, keras):
self.keras = keras
K = self.keras.backend
class TorchBatchNorm2D(self.keras.layers.Layer):
def __init__(self, axis=-1, momentum=0.99, epsilon=1e-3, **kwargs):
super(TorchBatchNorm2D, self).__init__(**kwargs)
self.supports_masking = True
self.axis = axis
self.momentum = momentum
self.epsilon = epsilon
def build(self, input_shape):
dim = input_shape[self.axis]
if dim is None:
raise ValueError('Axis ' + str(self.axis) + ' of ' 'input tensor should have a defined dimension ' 'but the layer received an input with shape ' + str(input_shape) + '.')
shape = (dim,)
self.gamma = self.add_weight(shape=shape, name='gamma', initializer='ones', regularizer=None, constraint=None)
self.beta = self.add_weight(shape=shape, name='beta', initializer='zeros', regularizer=None, constraint=None)
self.moving_mean = self.add_weight(shape=shape, name='moving_mean', initializer='zeros', trainable=False)
self.moving_variance = self.add_weight(shape=shape, name='moving_variance', initializer='ones', trainable=False)
self.built = True
def call(self, inputs, training=None):
input_shape = K.int_shape(inputs)
broadcast_shape = [1] * len(input_shape)
broadcast_shape[self.axis] = input_shape[self.axis]
broadcast_moving_mean = K.reshape(self.moving_mean, broadcast_shape)
broadcast_moving_variance = K.reshape(self.moving_variance, broadcast_shape)
broadcast_gamma = K.reshape(self.gamma, broadcast_shape)
broadcast_beta = K.reshape(self.beta, broadcast_shape)
invstd = K.ones (shape=broadcast_shape, dtype='float32') / K.sqrt(broadcast_moving_variance + K.constant(self.epsilon, dtype='float32'))
return (inputs - broadcast_moving_mean) * invstd * broadcast_gamma + broadcast_beta
def get_config(self):
config = { 'axis': self.axis, 'momentum': self.momentum, 'epsilon': self.epsilon }
base_config = super(TorchBatchNorm2D, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
self.TorchBatchNorm2D = TorchBatchNorm2D
def __enter__(self):
keras_model_path = Path(__file__).parent / "2DFAN-4.h5"
if not keras_model_path.exists():
return None
self.keras_model = self.keras.models.load_model ( str(keras_model_path), custom_objects={'TorchBatchNorm2D': self.TorchBatchNorm2D} )
self.keras_model = self.keras.models.load_model (str(keras_model_path))
return self
@ -116,13 +33,58 @@ class LandmarksExtractor(object):
center[1] -= (bottom - top) * 0.12
scale = (right - left + bottom - top) / 195.0
image = crop(input_image, center, scale).transpose ( (2,0,1) ).astype(np.float32) / 255.0
image = self.crop(input_image, center, scale).astype(np.float32)
image = np.expand_dims(image, 0)
predicted = self.keras_model.predict (image)
pts_img = get_pts_from_predict ( predicted[-1], center, scale)
predicted = self.keras_model.predict (image).transpose (0,3,1,2)
pts_img = self.get_pts_from_predict ( predicted[-1], center, scale)
pts_img = [ ( int(pt[0]), int(pt[1]) ) for pt in pts_img ]
landmarks.append ( ( (left, top, right, bottom),pts_img ) )
return landmarks
def transform(self, point, center, scale, resolution):
pt = np.array ( [point[0], point[1], 1.0] )
h = 200.0 * scale
m = np.eye(3)
m[0,0] = resolution / h
m[1,1] = resolution / h
m[0,2] = resolution * ( -center[0] / h + 0.5 )
m[1,2] = resolution * ( -center[1] / h + 0.5 )
m = np.linalg.inv(m)
return np.matmul (m, pt)[0:2]
def crop(self, image, center, scale, resolution=256.0):
ul = self.transform([1, 1], center, scale, resolution).astype( np.int )
br = self.transform([resolution, resolution], center, scale, resolution).astype( np.int )
if image.ndim > 2:
newDim = np.array([br[1] - ul[1], br[0] - ul[0], image.shape[2]], dtype=np.int32)
newImg = np.zeros(newDim, dtype=np.uint8)
else:
newDim = np.array([br[1] - ul[1], br[0] - ul[0]], dtype=np.int)
newImg = np.zeros(newDim, dtype=np.uint8)
ht = image.shape[0]
wd = image.shape[1]
newX = np.array([max(1, -ul[0] + 1), min(br[0], wd) - ul[0]], dtype=np.int32)
newY = np.array([max(1, -ul[1] + 1), min(br[1], ht) - ul[1]], dtype=np.int32)
oldX = np.array([max(1, ul[0] + 1), min(br[0], wd)], dtype=np.int32)
oldY = np.array([max(1, ul[1] + 1), min(br[1], ht)], dtype=np.int32)
newImg[newY[0] - 1:newY[1], newX[0] - 1:newX[1] ] = image[oldY[0] - 1:oldY[1], oldX[0] - 1:oldX[1], :]
newImg = cv2.resize(newImg, dsize=(int(resolution), int(resolution)), interpolation=cv2.INTER_LINEAR)
return newImg
def get_pts_from_predict(self, a, center, scale):
b = a.reshape ( (a.shape[0], a.shape[1]*a.shape[2]) )
c = b.argmax(1).reshape ( (a.shape[0], 1) ).repeat(2, axis=1).astype(np.float)
c[:,0] %= a.shape[2]
c[:,1] = np.apply_along_axis ( lambda x: np.floor(x / a.shape[2]), 0, c[:,1] )
for i in range(a.shape[0]):
pX, pY = int(c[i,0]), int(c[i,1])
if pX > 0 and pX < 63 and pY > 0 and pY < 63:
diff = np.array ( [a[i,pY,pX+1]-a[i,pY,pX-1], a[i,pY+1,pX]-a[i,pY-1,pX]] )
c[i] += np.sign(diff)*0.25
c += 0.5
return [ self.transform (c[i], center, scale, a.shape[2]) for i in range(a.shape[0]) ]

BIN
facelib/S3FD.h5 Normal file
View file

Binary file not shown.

1
facelib/__init__.py
View file

@ -1,4 +1,5 @@
from .FaceType import FaceType
from .DLIBExtractor import DLIBExtractor
from .MTCExtractor import MTCExtractor
from .S3FDExtractor import S3FDExtractor
from .LandmarksExtractor import LandmarksExtractor

2
main.py
View file

@ -39,7 +39,7 @@ if __name__ == "__main__":
extract_parser.add_argument('--output-dir', required=True, action=fixPathAction, dest="output_dir", help="Output directory. This is where the extracted files will be stored.")
extract_parser.add_argument('--debug', action="store_true", dest="debug", default=False, help="Writes debug images to [output_dir]_debug\ directory.")
extract_parser.add_argument('--face-type', dest="face_type", choices=['half_face', 'full_face', 'head', 'avatar', 'mark_only'], default='full_face', help="Default 'full_face'. Don't change this option, currently all models uses 'full_face'")
extract_parser.add_argument('--detector', dest="detector", choices=['dlib','mt','manual'], default='dlib', help="Type of detector. Default 'dlib'. 'mt' (MTCNNv1) - faster, better, almost no jitter, perfect for gathering thousands faces for src-set. It is also good for dst-set, but can generate false faces in frames where main face not recognized! In this case for dst-set use either 'dlib' with '--manual-fix' or '--detector manual'. Manual detector suitable only for dst-set.")
extract_parser.add_argument('--detector', dest="detector", choices=['dlib','mt','s3fd','manual'], default='dlib', help="Type of detector. Default 'dlib'. 'mt' (MTCNNv1) - faster, better, almost no jitter, perfect for gathering thousands faces for src-set. It is also good for dst-set, but can generate false faces in frames where main face not recognized! In this case for dst-set use either 'dlib' with '--manual-fix' or '--detector manual'. Manual detector suitable only for dst-set.")
extract_parser.add_argument('--multi-gpu', action="store_true", dest="multi_gpu", default=False, help="Enables multi GPU.")
extract_parser.add_argument('--manual-fix', action="store_true", dest="manual_fix", default=False, help="Enables manual extract only frames where faces were not recognized.")
extract_parser.add_argument('--manual-output-debug-fix', action="store_true", dest="manual_output_debug_fix", default=False, help="Performs manual reextract input-dir frames which were deleted from [output_dir]_debug\ dir.")

34
mainscripts/Extractor.py
View file

@ -6,6 +6,7 @@ import multiprocessing
import shutil
from pathlib import Path
import numpy as np
import mathlib
import cv2
from utils import Path_utils
from utils.DFLJPG import DFLJPG
@ -47,6 +48,9 @@ class ExtractSubprocessor(Subprocessor):
elif self.detector == 'dlib':
nnlib.import_dlib (device_config)
self.e = facelib.DLIBExtractor(nnlib.dlib)
elif self.detector == 's3fd':
nnlib.import_all (device_config)
self.e = facelib.S3FDExtractor()
else:
raise ValueError ("Wrond detector type.")
@ -104,15 +108,11 @@ class ExtractSubprocessor(Subprocessor):
debug_output_file = '{}{}'.format( str(Path(str(self.output_path) + '_debug') / filename_path.stem), '.jpg')
debug_image = image.copy()
for (face_idx, face) in enumerate(faces):
output_file = '{}_{}{}'.format(str(self.output_path / filename_path.stem), str(face_idx), '.jpg')
rect = face[0]
face_idx = 0
for face in faces:
rect = np.array(face[0])
image_landmarks = np.array(face[1])
if self.debug:
LandmarksProcessor.draw_rect_landmarks (debug_image, rect, image_landmarks, self.image_size, self.face_type)
if self.face_type == FaceType.MARK_ONLY:
face_image = image
face_image_landmarks = image_landmarks
@ -120,6 +120,20 @@ class ExtractSubprocessor(Subprocessor):
image_to_face_mat = LandmarksProcessor.get_transform_mat (image_landmarks, self.image_size, self.face_type)
face_image = cv2.warpAffine(image, image_to_face_mat, (self.image_size, self.image_size), cv2.INTER_LANCZOS4)
face_image_landmarks = LandmarksProcessor.transform_points (image_landmarks, image_to_face_mat)
landmarks_bbox = LandmarksProcessor.transform_points ( [ (0,0), (0,self.image_size-1), (self.image_size-1, self.image_size-1), (self.image_size-1,0) ], image_to_face_mat, True)
rect_area = mathlib.polygon_area(np.array(rect[[0,2,2,0]]), np.array(rect[[1,1,3,3]]))
landmarks_area = mathlib.polygon_area(landmarks_bbox[:,0], landmarks_bbox[:,1] )
if landmarks_area > 4*rect_area: #get rid of faces which umeyama-landmark-area > 4*detector-rect-area
continue
if self.debug:
LandmarksProcessor.draw_rect_landmarks (debug_image, rect, image_landmarks, self.image_size, self.face_type)
output_file = '{}_{}{}'.format(str(self.output_path / filename_path.stem), str(face_idx), '.jpg')
face_idx += 1
if src_dflimg is not None:
#if extracting from dflimg just copy it in order not to lose quality
@ -199,13 +213,13 @@ class ExtractSubprocessor(Subprocessor):
cpu_only = True
if not cpu_only and (type == 'rects' or type == 'landmarks'):
if type == 'rects' and self.detector == 'mt' and nnlib.device.backend == "plaidML":
if type == 'rects' and (self.detector == 'mt' or self.detector == 's3fd') and nnlib.device.backend == "plaidML":
cpu_only = True
else:
if multi_gpu:
devices = nnlib.device.getValidDevicesWithAtLeastTotalMemoryGB(2)
if not multi_gpu or len(devices) == 0:
devices = [nnlib.device.getBestValidDeviceIdx()]
devices = [nnlib.device.getBestValidDeviceIdx()]
if len(devices) == 0:
devices = [0]
@ -213,7 +227,7 @@ class ExtractSubprocessor(Subprocessor):
dev_name = nnlib.device.getDeviceName(idx)
dev_vram = nnlib.device.getDeviceVRAMTotalGb(idx)
if not self.manual and ( (self.type == 'rects') ):
if not self.manual and ( self.type == 'rects' and self.detector != 's3fd' ):
for i in range ( int (max (1, dev_vram / 2) ) ):
yield (idx, 'GPU', '%s #%d' % (dev_name,i) , dev_vram)
else:

5
mathlib/__init__.py
View file

@ -19,4 +19,7 @@ def rotationMatrixToEulerAngles(R) :
x = math.atan2(-R[1,2], R[1,1])
y = math.atan2(-R[2,0], sy)
z = 0
return np.array([x, y, z])
return np.array([x, y, z])
def polygon_area(x,y):
return 0.5*np.abs(np.dot(x,np.roll(y,1))-np.dot(y,np.roll(x,1)))