def conversion(video_path_A):
if len(sys.argv)<=2:
output_video_path_A = "./Aout.mp4"
elif len(sys.argv)==3:
output_video_path_A = sys.argv[3]
K.set_learning_phase(0)
# Input/Output resolution
RESOLUTION = 64 # 64x64, 128x128, 256x256
assert (RESOLUTION % 64) == 0, "RESOLUTION should be 64, 128, 256"
# Architecture configuration
arch_config = {}
arch_config['IMAGE_SHAPE'] = (RESOLUTION, RESOLUTION, 3)
arch_config['use_self_attn'] = True
arch_config['norm'] = "instancenorm" # instancenorm, batchnorm, layernorm, groupnorm, none
arch_config['model_capacity'] = "standard" # standard, lite
model = FaceswapGANModel(**arch_config)
model.load_weights(path="./models")
mtcnn_weights_dir = "./mtcnn_weights/"
fd = MTCNNFaceDetector(sess=K.get_session(), model_path=mtcnn_weights_dir)
vc = VideoConverter()
vc.set_face_detector(fd)
vc.set_gan_model(model)
options = {
# ===== Fixed =====
"use_smoothed_bbox": True,
"use_kalman_filter": True,
"use_auto_downscaling": False,
"bbox_moving_avg_coef": 0.65,
"min_face_area": 35 * 35,
"IMAGE_SHAPE": model.IMAGE_SHAPE,
# ===== Tunable =====
"kf_noise_coef": 3e-3,
"use_color_correction": "hist_match",
"detec_threshold": 0.7,
"roi_coverage": 0.9,
"enhance": 0.5,
"output_type": 3,
"direction": "AtoB",
}
input_fn = video_path_A
output_fn = output_video_path_A
duration = None
vc.convert(input_fn=input_fn, output_fn=output_fn, options=options, duration=duration)
"min_face_area": 128 * 128,
"IMAGE_SHAPE": model.IMAGE_SHAPE,
# ===== Tunable =====
"kf_noise_coef": 1e-3,
"use_color_correction": "hist_match",
"detec_threshold": 0.8,
"roi_coverage": 0.92,
"enhance": 0.,
"output_type": 1,
"direction":
"BtoA", # ==================== This line determines the transform direction ====================
}
model.load_weights(path=models_dir)
fd = MTCNNFaceDetector(sess=K.get_session(), model_path="./mtcnn_weights/")
vc = VideoConverter()
vc.set_face_detector(fd)
vc.set_gan_model(model)
vc._init_kalman_filters(options["kf_noise_coef"])
# fn_source_video = "obama_new.mp4"
# fn_target_video = 'zyl.mp4'
#
# if options["direction"] == "AtoB":
# input_fn = fn_source_video
# output_fn = "OUTPUT_VIDEO_AtoB.mp4"
# elif options["direction"] == "BtoA":
# input_fn = fn_target_video
# output_fn = "OUTPUT_VIDEO_BtoA.mp4"
#
# duration = None # None or a non-negative float tuple: (start_sec, end_sec). Duration of input video to
model = FaceswapGANModel(**arch_config)
model.load_weights(path="./endeweight")
from converter.video_converter import VideoConverter
from detector.face_detector import MTCNNFaceDetector
mtcnn_weights_dir = "./weights/"
fd = MTCNNFaceDetector(sess=K.get_session(), model_path=mtcnn_weights_dir)
frames = 0
x0 = x1 = y0 = y1 = 0
vc = VideoConverter(x0, x1, y0, y1, frames)
vc.set_face_detector(fd)
vc.set_gan_model(model)
options = {
# ===== Fixed =====
"use_smoothed_bbox": True,
"use_kalman_filter": True,
"use_auto_downscaling": True,
"bbox_moving_avg_coef": 0.60,
"min_face_area": 40 * 40,
"IMAGE_SHAPE": model.IMAGE_SHAPE,
# ===== Tunable =====
"kf_noise_coef": 5e-2,
"use_color_correction": "adain_xyz", #"hist_match",#adain_xyz
def face_transform():
config = tf.ConfigProto()
config.gpu_options.allow_growth = True # 不全部占满显存, 按需分配
session = tf.Session(config=config)
# 设置session
K.set_session(session)
models_dir = "../models"
RESOLUTION = 256 # 64x64, 128x128, 256x256
# Architecture configuration
arch_config = {}
arch_config['IMAGE_SHAPE'] = (RESOLUTION, RESOLUTION, 3)
arch_config['use_self_attn'] = True
arch_config[
'norm'] = "instancenorm" # instancenorm, batchnorm, layernorm, groupnorm, none
arch_config['model_capacity'] = "standard" # standard, lite
model = FaceswapGANModel(**arch_config)
options = {
# ===== Fixed =====
"use_smoothed_bbox": True,
"use_kalman_filter": True,
"use_auto_downscaling": False,
"bbox_moving_avg_coef": 0.70, # 0.65
"min_face_area": 128 * 128,
"IMAGE_SHAPE": model.IMAGE_SHAPE,
# ===== Tunable =====
"kf_noise_coef": 1e-3,
"use_color_correction": "hist_match",
"detec_threshold": 0.8,
"roi_coverage": 0.92,
"enhance": 0.,
"output_type": 1,
"direction":
"BtoA", # ==================== This line determines the transform direction ====================
}
model.load_weights(path=models_dir)
fd = MTCNNFaceDetector(sess=K.get_session(),
model_path="../mtcnn_weights/")
vc = VideoConverter()
vc.set_face_detector(fd)
vc.set_gan_model(model)
vc._init_kalman_filters(options["kf_noise_coef"])
def transform(imageB64):
"""
:param imageB64: 图片base64编码
:return: 转换后的图片base64编码
"""
rgb_img = base64_to_image(imageB64)
result = vc.process_video(rgb_img, options)
result = normalization(result)
r, g, b = cv2.split(result)
img_bgr = cv2.merge([b, g, r])
return np.array(result).tolist()
# bgr base64
# res_base64 = image_to_base64(img_bgr)
# return res_base64
return transform
def transform_img(inStack, outStack):
print('Process to transform: %s ' % os.getpid(), time.time())
config = tf.ConfigProto()
config.gpu_options.allow_growth = True # 不全部占满显存, 按需分配
session = tf.Session(config=config)
# 设置session
K.set_session(session)
models_dir = "../models_transform"
RESOLUTION = 256 # 64x64, 128x128, 256x256
# Architecture configuration
arch_config = {}
arch_config['IMAGE_SHAPE'] = (RESOLUTION, RESOLUTION, 3)
arch_config['use_self_attn'] = True
# TODO 归一化设置
arch_config[
'norm'] = "instancenorm" # instancenorm, batchnorm, layernorm, groupnorm, none
arch_config['model_capacity'] = "standard" # standard, lite
model = FaceswapGANModel(**arch_config)
options = {
# ===== Fixed =====
"use_smoothed_bbox": True,
"use_kalman_filter": True,
"use_auto_downscaling": False,
"bbox_moving_avg_coef": 0.65, # 0.65
"min_face_area": 35 * 35,
"IMAGE_SHAPE": model.IMAGE_SHAPE,
# ===== Tunable =====
"kf_noise_coef": 1e-3,
"use_color_correction": "hist_match",
"detec_threshold": 0.8,
"roi_coverage": 0.90,
"enhance": 0.,
"output_type": 1,
"direction":
"BtoA", # ==================== This line determines the transform direction ====================
}
model.load_weights(path=models_dir)
fd = MTCNNFaceDetector(sess=K.get_session(),
model_path="../mtcnn_weights/")
vc = VideoConverter()
vc.set_face_detector(fd)
vc.set_gan_model(model)
vc._init_kalman_filters(options["kf_noise_coef"])
while True:
if len(inStack) != 0:
start_time = time.time()
rgb_img = inStack.pop()
# print("transform_img inputQ size ;",inputQ.qsize())
# 获取转换后的人脸
result = vc.process_video(rgb_img, options)
result = normalization(result) * 255
result = np.uint8(result)
print(time.time() - start_time)
outStack.append(result)