Spaces:
Configuration error
Configuration error
File size: 6,880 Bytes
efdd9ee |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 |
from typing import Any, Tuple, List
from cv2.typing import Size
from functools import lru_cache
import cv2
import numpy
from facefusion.typing import BoundingBox, FaceLandmark5, FaceLandmark68, VisionFrame, Mask, Matrix, Translation, WarpTemplate, WarpTemplateSet, FaceAnalyserAge, FaceAnalyserGender
WARP_TEMPLATES : WarpTemplateSet =\
{
'arcface_112_v1': numpy.array(
[
[ 0.35473214, 0.45658929 ],
[ 0.64526786, 0.45658929 ],
[ 0.50000000, 0.61154464 ],
[ 0.37913393, 0.77687500 ],
[ 0.62086607, 0.77687500 ]
]),
'arcface_112_v2': numpy.array(
[
[ 0.34191607, 0.46157411 ],
[ 0.65653393, 0.45983393 ],
[ 0.50022500, 0.64050536 ],
[ 0.37097589, 0.82469196 ],
[ 0.63151696, 0.82325089 ]
]),
'arcface_128_v2': numpy.array(
[
[ 0.36167656, 0.40387734 ],
[ 0.63696719, 0.40235469 ],
[ 0.50019687, 0.56044219 ],
[ 0.38710391, 0.72160547 ],
[ 0.61507734, 0.72034453 ]
]),
'ffhq_512': numpy.array(
[
[ 0.37691676, 0.46864664 ],
[ 0.62285697, 0.46912813 ],
[ 0.50123859, 0.61331904 ],
[ 0.39308822, 0.72541100 ],
[ 0.61150205, 0.72490465 ]
])
}
def estimate_matrix_by_face_landmark_5(face_landmark_5 : FaceLandmark5, warp_template : WarpTemplate, crop_size : Size) -> Matrix:
normed_warp_template = WARP_TEMPLATES.get(warp_template) * crop_size
affine_matrix = cv2.estimateAffinePartial2D(face_landmark_5, normed_warp_template, method = cv2.RANSAC, ransacReprojThreshold = 100)[0]
return affine_matrix
def warp_face_by_face_landmark_5(temp_vision_frame : VisionFrame, face_landmark_5 : FaceLandmark5, warp_template : WarpTemplate, crop_size : Size) -> Tuple[VisionFrame, Matrix]:
affine_matrix = estimate_matrix_by_face_landmark_5(face_landmark_5, warp_template, crop_size)
crop_vision_frame = cv2.warpAffine(temp_vision_frame, affine_matrix, crop_size, borderMode = cv2.BORDER_REPLICATE, flags = cv2.INTER_AREA)
return crop_vision_frame, affine_matrix
def warp_face_by_bounding_box(temp_vision_frame : VisionFrame, bounding_box : BoundingBox, crop_size : Size) -> Tuple[VisionFrame, Matrix]:
source_points = numpy.array([ [ bounding_box[0], bounding_box[1] ], [bounding_box[2], bounding_box[1] ], [ bounding_box[0], bounding_box[3] ] ]).astype(numpy.float32)
target_points = numpy.array([ [ 0, 0 ], [ crop_size[0], 0 ], [ 0, crop_size[1] ] ]).astype(numpy.float32)
affine_matrix = cv2.getAffineTransform(source_points, target_points)
if bounding_box[2] - bounding_box[0] > crop_size[0] or bounding_box[3] - bounding_box[1] > crop_size[1]:
interpolation_method = cv2.INTER_AREA
else:
interpolation_method = cv2.INTER_LINEAR
crop_vision_frame = cv2.warpAffine(temp_vision_frame, affine_matrix, crop_size, flags = interpolation_method)
return crop_vision_frame, affine_matrix
def warp_face_by_translation(temp_vision_frame : VisionFrame, translation : Translation, scale : float, crop_size : Size) -> Tuple[VisionFrame, Matrix]:
affine_matrix = numpy.array([ [ scale, 0, translation[0] ], [ 0, scale, translation[1] ] ])
crop_vision_frame = cv2.warpAffine(temp_vision_frame, affine_matrix, crop_size)
return crop_vision_frame, affine_matrix
def paste_back(temp_vision_frame : VisionFrame, crop_vision_frame : VisionFrame, crop_mask : Mask, affine_matrix : Matrix) -> VisionFrame:
inverse_matrix = cv2.invertAffineTransform(affine_matrix)
temp_size = temp_vision_frame.shape[:2][::-1]
inverse_mask = cv2.warpAffine(crop_mask, inverse_matrix, temp_size).clip(0, 1)
inverse_vision_frame = cv2.warpAffine(crop_vision_frame, inverse_matrix, temp_size, borderMode = cv2.BORDER_REPLICATE)
paste_vision_frame = temp_vision_frame.copy()
paste_vision_frame[:, :, 0] = inverse_mask * inverse_vision_frame[:, :, 0] + (1 - inverse_mask) * temp_vision_frame[:, :, 0]
paste_vision_frame[:, :, 1] = inverse_mask * inverse_vision_frame[:, :, 1] + (1 - inverse_mask) * temp_vision_frame[:, :, 1]
paste_vision_frame[:, :, 2] = inverse_mask * inverse_vision_frame[:, :, 2] + (1 - inverse_mask) * temp_vision_frame[:, :, 2]
return paste_vision_frame
@lru_cache(maxsize = None)
def create_static_anchors(feature_stride : int, anchor_total : int, stride_height : int, stride_width : int) -> numpy.ndarray[Any, Any]:
y, x = numpy.mgrid[:stride_height, :stride_width][::-1]
anchors = numpy.stack((y, x), axis = -1)
anchors = (anchors * feature_stride).reshape((-1, 2))
anchors = numpy.stack([ anchors ] * anchor_total, axis = 1).reshape((-1, 2))
return anchors
def create_bounding_box_from_face_landmark_68(face_landmark_68 : FaceLandmark68) -> BoundingBox:
min_x, min_y = numpy.min(face_landmark_68, axis = 0)
max_x, max_y = numpy.max(face_landmark_68, axis = 0)
bounding_box = numpy.array([ min_x, min_y, max_x, max_y ]).astype(numpy.int16)
return bounding_box
def distance_to_bounding_box(points : numpy.ndarray[Any, Any], distance : numpy.ndarray[Any, Any]) -> BoundingBox:
x1 = points[:, 0] - distance[:, 0]
y1 = points[:, 1] - distance[:, 1]
x2 = points[:, 0] + distance[:, 2]
y2 = points[:, 1] + distance[:, 3]
bounding_box = numpy.column_stack([ x1, y1, x2, y2 ])
return bounding_box
def distance_to_face_landmark_5(points : numpy.ndarray[Any, Any], distance : numpy.ndarray[Any, Any]) -> FaceLandmark5:
x = points[:, 0::2] + distance[:, 0::2]
y = points[:, 1::2] + distance[:, 1::2]
face_landmark_5 = numpy.stack((x, y), axis = -1)
return face_landmark_5
def convert_face_landmark_68_to_5(face_landmark_68 : FaceLandmark68) -> FaceLandmark5:
face_landmark_5 = numpy.array(
[
numpy.mean(face_landmark_68[36:42], axis = 0),
numpy.mean(face_landmark_68[42:48], axis = 0),
face_landmark_68[30],
face_landmark_68[48],
face_landmark_68[54]
])
return face_landmark_5
def apply_nms(bounding_box_list : List[BoundingBox], iou_threshold : float) -> List[int]:
keep_indices = []
dimension_list = numpy.reshape(bounding_box_list, (-1, 4))
x1 = dimension_list[:, 0]
y1 = dimension_list[:, 1]
x2 = dimension_list[:, 2]
y2 = dimension_list[:, 3]
areas = (x2 - x1 + 1) * (y2 - y1 + 1)
indices = numpy.arange(len(bounding_box_list))
while indices.size > 0:
index = indices[0]
remain_indices = indices[1:]
keep_indices.append(index)
xx1 = numpy.maximum(x1[index], x1[remain_indices])
yy1 = numpy.maximum(y1[index], y1[remain_indices])
xx2 = numpy.minimum(x2[index], x2[remain_indices])
yy2 = numpy.minimum(y2[index], y2[remain_indices])
width = numpy.maximum(0, xx2 - xx1 + 1)
height = numpy.maximum(0, yy2 - yy1 + 1)
iou = width * height / (areas[index] + areas[remain_indices] - width * height)
indices = indices[numpy.where(iou <= iou_threshold)[0] + 1]
return keep_indices
def categorize_age(age : int) -> FaceAnalyserAge:
if age < 13:
return 'child'
elif age < 19:
return 'teen'
elif age < 60:
return 'adult'
return 'senior'
def categorize_gender(gender : int) -> FaceAnalyserGender:
if gender == 0:
return 'female'
return 'male'
|