def onInitializeOptions(self, is_first_run, ask_override):
if is_first_run:
avatar_type = io.input_int(
"Avatar type ( 0:source, 1:head, 2:full_face ?:help skip:1) : ",
1, [0, 1, 2],
help_message=
"Training target for the model. Source is direct untouched images. Full_face or head are centered nose unaligned faces."
)
avatar_type = {0: 'source', 1: 'head', 2: 'full_face'}[avatar_type]
self.options['avatar_type'] = avatar_type
else:
self.options['avatar_type'] = self.options.get(
'avatar_type', 'head')
if is_first_run or ask_override:
def_stage = self.options.get('stage', 1)
self.options['stage'] = io.input_int(
"Stage (0, 1, 2 ?:help skip:%d) : " % def_stage,
def_stage, [0, 1, 2],
help_message=
"Train first stage, then second. Tune batch size to maximum possible for both stages."
)
else:
self.options['stage'] = self.options.get('stage', 1)
def ask_settings(self):
s = """Choose sharpen mode: \n"""
for key in self.sharpen_dict.keys():
s += f"""({key}) {self.sharpen_dict[key]}\n"""
s += f"""?:help Default: {list(self.sharpen_dict.keys())[0]} : """
self.sharpen_mode = io.input_int(
s,
0,
valid_list=self.sharpen_dict.keys(),
help_message="Enhance details by applying sharpen filter.")
if self.sharpen_mode != 0:
self.blursharpen_amount = np.clip(
io.input_int(
"Choose blur/sharpen amount [-100..100] (skip:0) : ", 0),
-100, 100)
s = """Choose super resolution mode: \n"""
for key in self.super_res_dict.keys():
s += f"""({key}) {self.super_res_dict[key]}\n"""
s += f"""?:help Default: {list(self.super_res_dict.keys())[0]} : """
self.super_resolution_mode = io.input_int(
s,
0,
valid_list=self.super_res_dict.keys(),
help_message="Enhance details by applying superresolution network."
)
def onInitializeOptions(self, is_first_run, ask_override):
default_face_type = 'f'
if is_first_run:
self.options['resolution'] = io.input_int(
"Resolution ( 128,224 ?:help skip:128) : ", 128, [128, 224])
else:
self.options['resolution'] = self.options.get('resolution', 128)
if is_first_run:
self.options['face_type'] = io.input_str(
"Half or Full face? (h/f, ?:help skip:f) : ",
default_face_type, ['h', 'f'],
help_message="").lower()
else:
self.options['face_type'] = self.options.get(
'face_type', default_face_type)
if (is_first_run or
ask_override) and 'tensorflow' in self.device_config.backend:
def_optimizer_mode = self.options.get('optimizer_mode', 1)
self.options['optimizer_mode'] = io.input_int(
"Optimizer mode? ( 1,2,3 ?:help skip:%d) : " %
(def_optimizer_mode),
def_optimizer_mode,
help_message=
"1 - no changes. 2 - allows you to train x2 bigger network consuming RAM. 3 - allows you to train x3 bigger network consuming huge amount of RAM and slower, depends on CPU power."
)
else:
self.options['optimizer_mode'] = self.options.get(
'optimizer_mode', 1)
def ask_settings(self):
s = """Choose sharpen mode: \n"""
for key in self.sharpen_dict.keys():
s += """({}) {}\n""".format(key, self.sharpen_dict[key])
s += """?:help Default: {} : """.format(
list(self.sharpen_dict.keys())[0])
self.sharpen_mode = io.input_int(
s,
0,
valid_list=self.sharpen_dict.keys(),
help_message="Enhance details by applying sharpen filter.")
if self.sharpen_mode != 0:
self.sharpen_amount = np.clip(
io.input_int(
"Choose sharpen amount [0..100] (skip:%d) : " % 10, 10), 0,
100)
s = """Choose super resolution mode: \n"""
for key in self.super_res_dict.keys():
s += """({}) {}\n""".format(key, self.super_res_dict[key])
s += """?:help Default: {} : """.format(
list(self.super_res_dict.keys())[0])
self.super_resolution_mode = io.input_int(
s,
0,
valid_list=self.super_res_dict.keys(),
help_message="Enhance details by applying superresolution network."
)
def onInitializeOptions(self, is_first_run, ask_override):
default_resolution = 128
default_archi = 'df'
default_face_type = 'f'
if is_first_run:
resolution = io.input_int("Resolution ( 64-256 ?:help skip:128) : ", default_resolution, help_message="More resolution requires more VRAM and time to train. Value will be adjusted to multiple of 16.")
resolution = np.clip (resolution, 64, 256)
while np.modf(resolution / 16)[0] != 0.0:
resolution -= 1
self.options['resolution'] = resolution
self.options['face_type'] = io.input_str ("Half or Full face? (h/f, ?:help skip:f) : ", default_face_type, ['h','f'], help_message="Half face has better resolution, but covers less area of cheeks.").lower()
self.options['learn_mask'] = io.input_bool ("Learn mask? (y/n, ?:help skip:y) : ", True, help_message="Learning mask can help model to recognize face directions. Learn without mask can reduce model size, in this case converter forced to use 'not predicted mask' that is not smooth as predicted. Model with style values can be learned without mask and produce same quality result.")
self.options['archi'] = io.input_str ("AE architecture (df, liae, vg ?:help skip:%s) : " % (default_archi) , default_archi, ['df','liae','vg'], help_message="'df' keeps faces more natural. 'liae' can fix overly different face shapes. 'vg' - currently testing.").lower()
else:
self.options['resolution'] = self.options.get('resolution', default_resolution)
self.options['face_type'] = self.options.get('face_type', default_face_type)
self.options['learn_mask'] = self.options.get('learn_mask', True)
self.options['archi'] = self.options.get('archi', default_archi)
default_ae_dims = 256 if self.options['archi'] == 'liae' else 512
default_ed_ch_dims = 42
if is_first_run:
self.options['ae_dims'] = np.clip ( io.input_int("AutoEncoder dims (32-1024 ?:help skip:%d) : " % (default_ae_dims) , default_ae_dims, help_message="More dims are better, but requires more VRAM. You can fine-tune model size to fit your GPU." ), 32, 1024 )
self.options['ed_ch_dims'] = np.clip ( io.input_int("Encoder/Decoder dims per channel (21-85 ?:help skip:%d) : " % (default_ed_ch_dims) , default_ed_ch_dims, help_message="More dims are better, but requires more VRAM. You can fine-tune model size to fit your GPU." ), 21, 85 )
else:
self.options['ae_dims'] = self.options.get('ae_dims', default_ae_dims)
self.options['ed_ch_dims'] = self.options.get('ed_ch_dims', default_ed_ch_dims)
if is_first_run:
self.options['lighter_encoder'] = io.input_bool ("Use lightweight encoder? (y/n, ?:help skip:n) : ", False, help_message="Lightweight encoder is 35% faster, requires less VRAM, but sacrificing overall quality.")
if self.options['archi'] != 'vg':
self.options['multiscale_decoder'] = io.input_bool ("Use multiscale decoder? (y/n, ?:help skip:n) : ", False, help_message="Multiscale decoder helps to get better details.")
else:
self.options['lighter_encoder'] = self.options.get('lighter_encoder', False)
if self.options['archi'] != 'vg':
self.options['multiscale_decoder'] = self.options.get('multiscale_decoder', False)
default_face_style_power = 0.0
default_bg_style_power = 0.0
if is_first_run or ask_override:
def_pixel_loss = self.options.get('pixel_loss', False)
self.options['pixel_loss'] = io.input_bool ("Use pixel loss? (y/n, ?:help skip: n/default ) : ", def_pixel_loss, help_message="Default DSSIM loss good for initial understanding structure of faces. Use pixel loss after 15-25k epochs to enhance fine details and decrease face jitter.")
default_face_style_power = default_face_style_power if is_first_run else self.options.get('face_style_power', default_face_style_power)
self.options['face_style_power'] = np.clip ( io.input_number("Face style power ( 0.0 .. 100.0 ?:help skip:%.2f) : " % (default_face_style_power), default_face_style_power,
help_message="Learn to transfer face style details such as light and color conditions. Warning: Enable it only after 10k epochs, when predicted face is clear enough to start learn style. Start from 0.1 value and check history changes."), 0.0, 100.0 )
default_bg_style_power = default_bg_style_power if is_first_run else self.options.get('bg_style_power', default_bg_style_power)
self.options['bg_style_power'] = np.clip ( io.input_number("Background style power ( 0.0 .. 100.0 ?:help skip:%.2f) : " % (default_bg_style_power), default_bg_style_power,
help_message="Learn to transfer image around face. This can make face more like dst."), 0.0, 100.0 )
else:
self.options['pixel_loss'] = self.options.get('pixel_loss', False)
self.options['face_style_power'] = self.options.get('face_style_power', default_face_style_power)
self.options['bg_style_power'] = self.options.get('bg_style_power', default_bg_style_power)
def cut_video(input_file,
from_time=None,
to_time=None,
audio_track_id=None,
bitrate=None):
input_file_path = Path(input_file)
if input_file_path is None:
io.log_err("input_file not found.")
return
output_file_path = input_file_path.parent / (
input_file_path.stem + "_cut" + input_file_path.suffix)
if from_time is None:
from_time = io.input_str("From time (skip: 00:00:00.000) : ",
"00:00:00.000")
if to_time is None:
to_time = io.input_str("To time (skip: 00:00:00.000) : ",
"00:00:00.000")
if audio_track_id is None:
audio_track_id = io.input_int("Specify audio track id. ( skip:0 ) : ",
0)
if bitrate is None:
bitrate = max(
1,
io.input_int("Bitrate of output file in MB/s ? (default:25) : ",
25))
kwargs = {
"c:v": "libx264",
"b:v": "%dM" % (bitrate),
"pix_fmt": "yuv420p",
}
job = ffmpeg.input(str(input_file_path), ss=from_time, to=to_time)
job_v = job['v:0']
job_a = job['a:' + str(audio_track_id) + '?']
job = ffmpeg.output(job_v, job_a, str(output_file_path),
**kwargs).overwrite_output()
try:
job = job.run()
except:
io.log_err("ffmpeg fail, job commandline:" + str(job.compile()))
def denoise_image_sequence(input_dir, ext=None, factor=None):
input_path = Path(input_dir)
if not input_path.exists():
io.log_err("input_dir not found.")
return
if ext is None:
ext = io.input_str(
"Input image format (extension)? ( default:png ) : ", "png")
if factor is None:
factor = np.clip(
io.input_int("Denoise factor? (1-20 default:5) : ", 5), 1, 20)
kwargs = {}
if ext == 'jpg':
kwargs.update({'q:v': '2'})
job = (ffmpeg.input(str(input_path / ('%5d.' + ext))).filter(
"hqdn3d", factor, factor, 5,
5).output(str(input_path / ('%5d.' + ext)), **kwargs))
try:
job = job.run()
except:
io.log_err("ffmpeg fail, job commandline:" + str(job.compile()))
def onInitializeOptions(self, is_first_run, ask_override):
if is_first_run:
self.options['resolution'] = io.input_int(
"分辨率 ( 128，256 帮助:? 跳过:128) : ",
128, [128, 256],
help_message="更高的分辨率需要更多的VRAM和训练时间。 数值调整成16的倍数。")
else:
self.options['resolution'] = self.options.get('resolution', 128)
def ask_settings(self):
s = """Choose mode: \n"""
for key in self.mode_dict.keys():
s += f"""({key}) {self.mode_dict[key]}\n"""
s += f"""Default: {self.default_mode} : """
mode = io.input_int (s, self.default_mode)
self.mode = self.mode_dict.get (mode, self.mode_dict[self.default_mode] )
if 'raw' not in self.mode:
if self.mode == 'hist-match' or self.mode == 'hist-match-bw':
self.masked_hist_match = io.input_bool("Masked hist match? (y/n skip:y) : ", True)
if self.mode == 'hist-match' or self.mode == 'hist-match-bw' or self.mode == 'seamless-hist-match':
self.hist_match_threshold = np.clip ( io.input_int("Hist match threshold [0..255] (skip:255) : ", 255), 0, 255)
if self.face_type == FaceType.FULL:
s = """Choose mask mode: \n"""
for key in self.full_face_mask_mode_dict.keys():
s += f"""({key}) {self.full_face_mask_mode_dict[key]}\n"""
s += f"""?:help Default: 1 : """
self.mask_mode = io.input_int (s, 1, valid_list=self.full_face_mask_mode_dict.keys(), help_message="If you learned the mask, then option 1 should be choosed. 'dst' mask is raw shaky mask from dst aligned images. 'FAN-prd' - using super smooth mask by pretrained FAN-model from predicted face. 'FAN-dst' - using super smooth mask by pretrained FAN-model from dst face. 'FAN-prd*FAN-dst' or 'learned*FAN-prd*FAN-dst' - using multiplied masks.")
else:
s = """Choose mask mode: \n"""
for key in self.half_face_mask_mode_dict.keys():
s += f"""({key}) {self.half_face_mask_mode_dict[key]}\n"""
s += f"""?:help , Default: 1 : """
self.mask_mode = io.input_int (s, 1, valid_list=self.half_face_mask_mode_dict.keys(), help_message="If you learned the mask, then option 1 should be choosed. 'dst' mask is raw shaky mask from dst aligned images.")
if 'raw' not in self.mode:
self.erode_mask_modifier = self.base_erode_mask_modifier + np.clip ( io.input_int ("Choose erode mask modifier [-200..200] (skip:%d) : " % (self.default_erode_mask_modifier), self.default_erode_mask_modifier), -200, 200)
self.blur_mask_modifier = self.base_blur_mask_modifier + np.clip ( io.input_int ("Choose blur mask modifier [-200..200] (skip:%d) : " % (self.default_blur_mask_modifier), self.default_blur_mask_modifier), -200, 200)
self.motion_blur_power = np.clip ( io.input_int ("Choose motion blur power [0..100] (skip:%d) : " % (0), 0), 0, 100)
self.output_face_scale = np.clip (io.input_int ("Choose output face scale modifier [-50..50] (skip:0) : ", 0), -50, 50)
if 'raw' not in self.mode:
self.color_transfer_mode = io.input_str ("Apply color transfer to predicted face? Choose mode ( rct/lct skip:None ) : ", None, ['rct','lct'])
self.color_transfer_mode = self.ctm_str_dict[self.color_transfer_mode]
super().ask_settings()
if 'raw' not in self.mode:
self.color_degrade_power = np.clip ( io.input_int ("Degrade color power of final image [0..100] (skip:0) : ", 0), 0, 100)
self.export_mask_alpha = io.input_bool("Export png with alpha channel of the mask? (y/n skip:n) : ", False)
io.log_info ("")
def onInitializeOptions(self, is_first_run, ask_override):
if is_first_run:
self.options['resolution'] = io.input_int(
"Resolution ( 128,256 ?:help skip:128) : ",
128, [128, 256],
help_message=
"More resolution requires more VRAM and time to train. Value will be adjusted to multiple of 16."
)
else:
self.options['resolution'] = self.options.get('resolution', 128)
def onInitializeOptions(self, is_first_run, ask_override):
default_face_type = 'f'
if is_first_run:
self.options['resolution'] = io.input_int("Resolution ( 128,224 ?:help skip:128) : ", 128, [128,224])
else:
self.options['resolution'] = self.options.get('resolution', 128)
if is_first_run:
self.options['face_type'] = io.input_str ("Half or Full face? (h/f, ?:help skip:f) : ", default_face_type, ['h','f'], help_message="").lower()
else:
self.options['face_type'] = self.options.get('face_type', default_face_type)
def onInitializeOptions(self, is_first_run, ask_override):
if is_first_run or ask_override:
def_pixel_loss = self.options.get('pixel_loss', False)
self.options['pixel_loss'] = io.input_bool ("使用像素丢失? (y/n, 帮助:? 跳过: 默认/n ) : ", def_pixel_loss, help_message="像素丢失可能有助于增强细节和稳定面部颜色。只有在质量不随时间改善的情况下才能使用它，训练降不下去试试。")
else:
self.options['pixel_loss'] = self.options.get('pixel_loss', False)
if (is_first_run or ask_override) and 'tensorflow' in self.device_config.backend:
def_optimizer_mode = self.options.get('optimizer_mode', 1)
self.options['optimizer_mode'] = io.input_int ("优化模式? ( 1,2,3 帮助:? 跳过:%d) : " % (def_optimizer_mode), def_optimizer_mode, help_message="1 - 没有变化。2 - 允许您训练x2更大的网络消耗内存。3 - 允许你训练x3更大的网络消耗大量的内存和更慢，取决于CPU的功率。")
else:
self.options['optimizer_mode'] = self.options.get('optimizer_mode', 1)
def onInitializeOptions(self, is_first_run, ask_override):
default_resolution = 128
default_face_type = 'f'
if is_first_run:
resolution = self.options['resolution'] = io.input_int(
f"Resolution ( 64-256 ?:help skip:{default_resolution}) : ",
default_resolution,
help_message=
"More resolution requires more VRAM and time to train. Value will be adjusted to multiple of 16."
)
resolution = np.clip(resolution, 64, 256)
while np.modf(resolution / 16)[0] != 0.0:
resolution -= 1
else:
self.options['resolution'] = self.options.get(
'resolution', default_resolution)
if is_first_run:
self.options['face_type'] = io.input_str(
"Half or Full face? (h/f, ?:help skip:f) : ",
default_face_type, ['h', 'f'],
help_message="").lower()
else:
self.options['face_type'] = self.options.get(
'face_type', default_face_type)
if (is_first_run or
ask_override) and 'tensorflow' in self.device_config.backend:
def_optimizer_mode = self.options.get('optimizer_mode', 1)
self.options['optimizer_mode'] = io.input_int(
"Optimizer mode? ( 1,2,3 ?:help skip:%d) : " %
(def_optimizer_mode),
def_optimizer_mode,
help_message=
"1 - no changes. 2 - allows you to train x2 bigger network consuming RAM. 3 - allows you to train x3 bigger network consuming huge amount of RAM and slower, depends on CPU power."
)
else:
self.options['optimizer_mode'] = self.options.get(
'optimizer_mode', 1)
def extract_video(input_file, output_dir, output_ext=None, fps=None):
input_file_path = Path(input_file)
output_path = Path(output_dir)
if not output_path.exists():
output_path.mkdir(exist_ok=True)
if input_file_path.suffix == '.*':
input_file_path = Path_utils.get_first_file_by_stem(
input_file_path.parent, input_file_path.stem)
else:
if not input_file_path.exists():
input_file_path = None
if input_file_path is None:
io.log_err("input_file not found.")
return
if fps is None:
fps = io.input_int(
"Enter FPS ( ?:help skip:fullfps ) : ",
0,
help_message=
"How many frames of every second of the video will be extracted.")
if output_ext is None:
output_ext = io.input_str(
"Output image format? ( jpg png ?:help skip:png ) : ",
"png", ["png", "jpg"],
help_message=
"png is lossless, but extraction is x10 slower for HDD, requires x10 more disk space than jpg."
)
for filename in Path_utils.get_image_paths(output_path,
['.' + output_ext]):
Path(filename).unlink()
job = ffmpeg.input(str(input_file_path))
kwargs = {'pix_fmt': 'rgb24'}
if fps != 0:
kwargs.update({'r': str(fps)})
if output_ext == 'jpg':
kwargs.update({'q:v': '2'}) #highest quality for jpg
job = job.output(str(output_path / ('%5d.' + output_ext)), **kwargs)
try:
job = job.run()
except:
io.log_err("ffmpeg fail, job commandline:" + str(job.compile()))
def ask_settings(self):
s = """选择锐化模式: \n"""
for key in self.sharpen_dict.keys():
s += f"""({key}) {self.sharpen_dict[key]}\n"""
s += f"""帮助:? 默认: {list(self.sharpen_dict.keys())[0]} : """
self.sharpen_mode = io.input_int(s,
0,
valid_list=self.sharpen_dict.keys(),
help_message="通过应用锐化滤镜来增强细节。")
if self.sharpen_mode != 0:
self.blursharpen_amount = np.clip(
io.input_int("选择模糊/锐化量 [-100..100] (跳过:0) : ", 0), -100, 100)
s = """选择超级分辨率模式: \n"""
for key in self.super_res_dict.keys():
s += f"""({key}) {self.super_res_dict[key]}\n"""
s += f"""帮助:? 默认: {list(self.super_res_dict.keys())[0]} : """
self.super_resolution_mode = io.input_int(
s,
0,
valid_list=self.super_res_dict.keys(),
help_message="通过应用超分辨率网络来增强细节。")
def extract_video(input_file, output_dir, output_ext=None, fps=None):
input_file_path = Path(input_file)
output_path = Path(output_dir)
if not output_path.exists():
output_path.mkdir(exist_ok=True)
if input_file_path.suffix == '.*':
input_file_path = Path_utils.get_first_file_by_stem(
input_file_path.parent, input_file_path.stem)
else:
if not input_file_path.exists():
input_file_path = None
if input_file_path is None:
io.log_err("input_file not found.")
return
if fps is None:
fps = io.input_int("输入帧率[FPS] ( ?:帮助 跳过:默认帧率 ) : ",
0,
help_message="FPS是指每秒多少张图片，一般视频为24，推荐输入12")
if output_ext is None:
output_ext = io.input_str(
"输出格式? ( jpg还是png ?:帮助 默认为png ) : ",
"png", ["png", "jpg"],
help_message="png 为无损格式, 但是比JPG慢10倍, 空间也比JPG大十倍，建议使用JPG格式.")
for filename in Path_utils.get_image_paths(output_path,
['.' + output_ext]):
Path(filename).unlink()
job = ffmpeg.input(str(input_file_path))
kwargs = {'pix_fmt': 'rgb24'}
if fps != 0:
kwargs.update({'r': str(fps)})
if output_ext == 'jpg':
kwargs.update({'q:v': '2'}) #highest quality for jpg
job = job.output(str(output_path / ('%5d.' + output_ext)), **kwargs)
try:
job = job.run()
except:
io.log_err("ffmpeg 调用失败, 错误提示:" + str(job.compile()))
def onInitializeOptions(self, is_first_run, ask_override):
default_face_type = 'f'
if is_first_run:
self.options['resolution'] = io.input_int(
"分辨率 ( 128，256 帮助:? 跳过:128) : ",
128, [128, 256],
help_message="更高的分辨率需要更多的VRAM和训练时间。 数值调整成16的倍数。")
self.options['face_type'] = io.input_str(
"半脸（h）全脸（f）? (帮助:? 跳过:f) : ",
default_face_type, ['h', 'f'],
help_message="半脸有更好的分辨率，但覆盖的脸颊面积较小。").lower()
else:
self.options['resolution'] = self.options.get('resolution', 128)
self.options['face_type'] = self.options.get(
'face_type', default_face_type)
def onInitializeOptions(self, is_first_run, ask_override):
default_resolution = 128
default_face_type = 'f'
if is_first_run:
resolution = self.options['resolution'] = io.input_int(f"Resolution ( 64-256 ?:help skip:{default_resolution}) : ", default_resolution, help_message="More resolution requires more VRAM and time to train. Value will be adjusted to multiple of 16.")
resolution = np.clip (resolution, 64, 256)
while np.modf(resolution / 16)[0] != 0.0:
resolution -= 1
else:
self.options['resolution'] = self.options.get('resolution', default_resolution)
if is_first_run:
self.options['face_type'] = io.input_str ("Half or Full face? (h/f, ?:help skip:f) : ", default_face_type, ['h','f'], help_message="").lower()
else:
self.options['face_type'] = self.options.get('face_type', default_face_type)
def extract_video(input_file, output_dir, output_ext=None, fps=None):
input_file_path = Path(input_file)
output_path = Path(output_dir)
if not output_path.exists():
output_path.mkdir(exist_ok=True)
if input_file_path.suffix == '.*':
input_file_path = Path_utils.get_first_file_by_stem(
input_file_path.parent, input_file_path.stem)
else:
if not input_file_path.exists():
input_file_path = None
if input_file_path is None:
io.log_err("input_file not found.")
return
if output_ext is None:
output_ext = io.input_str(
"Output image format (extension)? ( default:png ) : ", "png")
if fps is None:
fps = io.input_int(
"Enter FPS ( ?:help skip:fullfps ) : ",
0,
help_message=
"How many frames of every second of the video will be extracted.")
for filename in Path_utils.get_image_paths(output_path,
['.' + output_ext]):
Path(filename).unlink()
job = ffmpeg.input(str(input_file_path))
kwargs = {}
if fps != 0:
kwargs.update({'r': str(fps)})
job = job.output(str(output_path / ('%5d.' + output_ext)), **kwargs)
try:
job = job.run()
except:
io.log_err("ffmpeg fail, job commandline:" + str(job.compile()))
def onInitializeOptions(self, is_first_run, ask_override):
default_face_type = 'f'
if is_first_run:
self.options['resolution'] = io.input_int(
"Resolution ( 128,256 ?:help skip:128) : ",
128, [128, 256],
help_message=
"More resolution requires more VRAM and time to train. Value will be adjusted to multiple of 16."
)
self.options['face_type'] = io.input_str(
"Half or Full face? (h/f, ?:help skip:f) : ",
default_face_type, ['h', 'f'],
help_message=
"Half face has better resolution, but covers less area of cheeks."
).lower()
else:
self.options['resolution'] = self.options.get('resolution', 128)
self.options['face_type'] = self.options.get(
'face_type', default_face_type)
def onInitializeOptions(self, is_first_run, ask_override):
if is_first_run:
self.options['lighter_ae'] = io.input_bool(
"使用轻量级自动编码器? (y/n, 帮助:？ 跳过:n) : ",
False,
help_message=
"轻量级自动编码器速度更快，需要的显存更少，牺牲了整体质量。如果您的显存小于或等于4G，建议选择此选项。")
else:
default_lighter_ae = self.options.get(
'created_vram_gb',
99) <= 4 #temporally support old models, deprecate in future
if 'created_vram_gb' in self.options.keys():
self.options.pop('created_vram_gb')
self.options['lighter_ae'] = self.options.get(
'lighter_ae', default_lighter_ae)
if is_first_run or ask_override:
def_pixel_loss = self.options.get('pixel_loss', False)
self.options['pixel_loss'] = io.input_bool(
"使用像素丢失? (y/n, 帮助:? 跳过: 默认/n ) : ",
def_pixel_loss,
help_message=
"像素丢失可能有助于增强细节和稳定面部颜色。只有在质量不随时间改善的情况下才能使用它，训练降不下去试试。")
else:
self.options['pixel_loss'] = self.options.get('pixel_loss', False)
if (is_first_run or
ask_override) and 'tensorflow' in self.device_config.backend:
def_optimizer_mode = self.options.get('optimizer_mode', 1)
self.options['optimizer_mode'] = io.input_int(
"优化模式? ( 1,2,3 帮助:? 跳过:%d) : " % (def_optimizer_mode),
def_optimizer_mode,
help_message=
"1 - 没有变化。2 - 允许您训练x2更大的网络消耗内存。3 - 允许你训练x3更大的网络消耗大量的内存和更慢，取决于CPU的功率。"
)
else:
self.options['optimizer_mode'] = self.options.get(
'optimizer_mode', 1)
def ask_settings(self):
s = """Choose mode: \n"""
for key in mode_dict.keys():
s += f"""({key}) {mode_dict[key]}\n"""
s += f"""Default: {self.default_mode} : """
mode = io.input_int(s, self.default_mode)
self.mode = mode_dict.get(mode, mode_dict[self.default_mode])
if 'raw' not in self.mode:
if self.mode == 'hist-match' or self.mode == 'hist-match-bw':
self.masked_hist_match = io.input_bool(
"Masked hist match? (y/n skip:y) : ", True)
if self.mode == 'hist-match' or self.mode == 'hist-match-bw' or self.mode == 'seamless-hist-match':
self.hist_match_threshold = np.clip(
io.input_int(
"Hist match threshold [0..255] (skip:255) : ", 255),
0, 255)
if self.face_type == FaceType.FULL:
s = """Choose mask mode: \n"""
for key in full_face_mask_mode_dict.keys():
s += f"""({key}) {full_face_mask_mode_dict[key]}\n"""
s += f"""?:help Default: 1 : """
self.mask_mode = io.input_int(
s,
1,
valid_list=full_face_mask_mode_dict.keys(),
help_message=
"If you learned the mask, then option 1 should be choosed. 'dst' mask is raw shaky mask from dst aligned images. 'FAN-prd' - using super smooth mask by pretrained FAN-model from predicted face. 'FAN-dst' - using super smooth mask by pretrained FAN-model from dst face. 'FAN-prd*FAN-dst' or 'learned*FAN-prd*FAN-dst' - using multiplied masks."
)
else:
s = """Choose mask mode: \n"""
for key in half_face_mask_mode_dict.keys():
s += f"""({key}) {half_face_mask_mode_dict[key]}\n"""
s += f"""?:help , Default: 1 : """
self.mask_mode = io.input_int(
s,
1,
valid_list=half_face_mask_mode_dict.keys(),
help_message=
"If you learned the mask, then option 1 should be choosed. 'dst' mask is raw shaky mask from dst aligned images."
)
if 'raw' not in self.mode:
self.erode_mask_modifier = np.clip(
io.input_int(
"Choose erode mask modifier [-400..400] (skip:%d) : " % 0,
0), -400, 400)
self.blur_mask_modifier = np.clip(
io.input_int(
"Choose blur mask modifier [-400..400] (skip:%d) : " % 0,
0), -400, 400)
self.motion_blur_power = np.clip(
io.input_int(
"Choose motion blur power [0..100] (skip:%d) : " % (0), 0),
0, 100)
self.output_face_scale = np.clip(
io.input_int(
"Choose output face scale modifier [-50..50] (skip:0) : ", 0),
-50, 50)
if 'raw' not in self.mode:
self.color_transfer_mode = np.clip(
io.input_int(
"Apply random color transfer to src faceset? (0) None, (1) LCT, (2) RCT, "
"(3) RCT-c, (4) RCT-p, (5) RCT-pc, (6) mRTC, (7) mRTC-c, (8) mRTC-p, (9) mRTC-pc "
"?:help skip:%s) : " % ColorTransferMode.NONE,
ColorTransferMode.NONE), ColorTransferMode.NONE,
ColorTransferMode.EBS)
super().ask_settings()
if 'raw' not in self.mode:
self.color_degrade_power = np.clip(
io.input_int(
"Degrade color power of final image [0..100] (skip:0) : ",
0), 0, 100)
self.export_mask_alpha = io.input_bool(
"Export png with alpha channel of the mask? (y/n skip:n) : ",
False)
io.log_info("")
def onInitializeOptions(self, is_first_run, ask_override):
yn_str = {True: 'y', False: 'n'}
default_resolution = 128
default_archi = 'df'
default_face_type = 'f'
if is_first_run:
resolution = io.input_int(
"Resolution ( 64-256 ?:help skip:128) : ",
default_resolution,
help_message=
"More resolution requires more VRAM and time to train. Value will be adjusted to multiple of 16."
)
resolution = np.clip(resolution, 64, 256)
while np.modf(resolution / 16)[0] != 0.0:
resolution -= 1
self.options['resolution'] = resolution
self.options['face_type'] = io.input_str(
"Half, mid full, or full face? (h/mf/f, ?:help skip:f) : ",
default_face_type, ['h', 'mf', 'f'],
help_message=
"Half face has better resolution, but covers less area of cheeks. Mid face is 30% wider than half face."
).lower()
else:
self.options['resolution'] = self.options.get(
'resolution', default_resolution)
self.options['face_type'] = self.options.get(
'face_type', default_face_type)
default_learn_mask = self.options.get('learn_mask', True)
if is_first_run or ask_override:
self.options['learn_mask'] = io.input_bool(
f"Learn mask? (y/n, ?:help skip:{yn_str[default_learn_mask]} ) : ",
default_learn_mask,
help_message=
"Learning mask can help model to recognize face directions. Learn without mask can reduce model size, in this case converter forced to use 'not predicted mask' that is not smooth as predicted."
)
else:
self.options['learn_mask'] = self.options.get(
'learn_mask', default_learn_mask)
if (is_first_run or
ask_override) and 'tensorflow' in self.device_config.backend:
def_optimizer_mode = self.options.get('optimizer_mode', 1)
self.options['optimizer_mode'] = io.input_int(
"Optimizer mode? ( 1,2,3 ?:help skip:%d) : " %
(def_optimizer_mode),
def_optimizer_mode,
help_message=
"1 - no changes. 2 - allows you to train x2 bigger network consuming RAM. 3 - allows you to train x3 bigger network consuming huge amount of RAM and slower, depends on CPU power."
)
else:
self.options['optimizer_mode'] = self.options.get(
'optimizer_mode', 1)
if is_first_run:
self.options['archi'] = io.input_str(
"AE architecture (df, liae ?:help skip:%s) : " %
(default_archi),
default_archi, ['df', 'liae'],
help_message=
"'df' keeps faces more natural. 'liae' can fix overly different face shapes."
).lower(
) #-s version is slower, but has decreased change to collapse.
else:
self.options['archi'] = self.options.get('archi', default_archi)
default_ae_dims = 256
default_ed_ch_dims = 21
if is_first_run:
self.options['ae_dims'] = np.clip(
io.input_int(
"AutoEncoder dims (32-1024 ?:help skip:%d) : " %
(default_ae_dims),
default_ae_dims,
help_message=
"All face information will packed to AE dims. If amount of AE dims are not enough, then for example closed eyes will not be recognized. More dims are better, but require more VRAM. You can fine-tune model size to fit your GPU."
), 32, 1024)
self.options['ed_ch_dims'] = np.clip(
io.input_int(
"Encoder/Decoder dims per channel (10-85 ?:help skip:%d) : "
% (default_ed_ch_dims),
default_ed_ch_dims,
help_message=
"More dims help to recognize more facial features and achieve sharper result, but require more VRAM. You can fine-tune model size to fit your GPU."
), 10, 85)
else:
self.options['ae_dims'] = self.options.get('ae_dims',
default_ae_dims)
self.options['ed_ch_dims'] = self.options.get(
'ed_ch_dims', default_ed_ch_dims)
default_true_face_training = self.options.get('true_face_training',
False)
default_face_style_power = self.options.get('face_style_power', 0.0)
default_bg_style_power = self.options.get('bg_style_power', 0.0)
if is_first_run or ask_override:
default_lr_dropout = self.options.get('lr_dropout', False)
self.options['lr_dropout'] = io.input_bool(
f"Use learning rate dropout? (y/n, ?:help skip:{yn_str[default_lr_dropout]} ) : ",
default_lr_dropout,
help_message=
"When the face is trained enough, you can enable this option to get extra sharpness for less amount of iterations."
)
default_random_warp = self.options.get('random_warp', True)
self.options['random_warp'] = io.input_bool(
f"Enable random warp of samples? ( y/n, ?:help skip:{yn_str[default_random_warp]}) : ",
default_random_warp,
help_message=
"Random warp is required to generalize facial expressions of both faces. When the face is trained enough, you can disable it to get extra sharpness for less amount of iterations."
)
self.options['true_face_training'] = io.input_bool(
f"Enable 'true face' training? (y/n, ?:help skip:{yn_str[default_true_face_training]}) : ",
default_true_face_training,
help_message=
"The result face will be more like src and will get extra sharpness. Enable it for last 10-20k iterations before conversion."
)
self.options['face_style_power'] = np.clip(
io.input_number(
"Face style power ( 0.0 .. 100.0 ?:help skip:%.2f) : " %
(default_face_style_power),
default_face_style_power,
help_message=
"Learn to transfer face style details such as light and color conditions. Warning: Enable it only after 10k iters, when predicted face is clear enough to start learn style. Start from 0.1 value and check history changes. Enabling this option increases the chance of model collapse."
), 0.0, 100.0)
self.options['bg_style_power'] = np.clip(
io.input_number(
"Background style power ( 0.0 .. 100.0 ?:help skip:%.2f) : "
% (default_bg_style_power),
default_bg_style_power,
help_message=
"Learn to transfer image around face. This can make face more like dst. Enabling this option increases the chance of model collapse."
), 0.0, 100.0)
default_ct_mode = self.options.get('ct_mode', 'none')
self.options['ct_mode'] = io.input_str(
f"Color transfer mode apply to src faceset. ( none/rct/lct/mkl/idt/sot, ?:help skip:{default_ct_mode}) : ",
default_ct_mode, ['none', 'rct', 'lct', 'mkl', 'idt', 'sot'],
help_message=
"Change color distribution of src samples close to dst samples. Try all modes to find the best."
)
if nnlib.device.backend != 'plaidML': # todo https://github.com/plaidml/plaidml/issues/301
default_clipgrad = False if is_first_run else self.options.get(
'clipgrad', False)
self.options['clipgrad'] = io.input_bool(
f"Enable gradient clipping? (y/n, ?:help skip:{yn_str[default_clipgrad]}) : ",
default_clipgrad,
help_message=
"Gradient clipping reduces chance of model collapse, sacrificing speed of training."
)
else:
self.options['clipgrad'] = False
else:
self.options['lr_dropout'] = self.options.get('lr_dropout', False)
self.options['random_warp'] = self.options.get('random_warp', True)
self.options['true_face_training'] = self.options.get(
'true_face_training', default_true_face_training)
self.options['face_style_power'] = self.options.get(
'face_style_power', default_face_style_power)
self.options['bg_style_power'] = self.options.get(
'bg_style_power', default_bg_style_power)
self.options['ct_mode'] = self.options.get('ct_mode', 'none')
self.options['clipgrad'] = self.options.get('clipgrad', False)
if is_first_run:
self.options['pretrain'] = io.input_bool(
"Pretrain the model? (y/n, ?:help skip:n) : ",
False,
help_message=
"Pretrain the model with large amount of various faces. This technique may help to train the fake with overly different face shapes and light conditions of src/dst data. Face will be look more like a morphed. To reduce the morph effect, some model files will be initialized but not be updated after pretrain: LIAE: inter_AB.h5 DF: encoder.h5. The longer you pretrain the model the more morphed face will look. After that, save and run the training again."
)
else:
self.options['pretrain'] = False
def __init__(self,
model_path,
training_data_src_path=None,
training_data_dst_path=None,
debug=False,
device_args=None,
ask_write_preview_history=True,
ask_target_iter=True,
ask_batch_size=True,
ask_sort_by_yaw=True,
ask_random_flip=True,
ask_src_scale_mod=True):
device_args['force_gpu_idx'] = device_args.get('force_gpu_idx', -1)
device_args['cpu_only'] = device_args.get('cpu_only', False)
if device_args['force_gpu_idx'] == -1 and not device_args['cpu_only']:
idxs_names_list = nnlib.device.getValidDevicesIdxsWithNamesList()
if len(idxs_names_list) > 1:
io.log_info("You have multi GPUs in a system: ")
for idx, name in idxs_names_list:
io.log_info("[%d] : %s" % (idx, name))
device_args['force_gpu_idx'] = io.input_int(
"Which GPU idx to choose? ( skip: best GPU ) : ", -1,
[x[0] for x in idxs_names_list])
self.device_args = device_args
self.device_config = nnlib.DeviceConfig(allow_growth=False,
**self.device_args)
io.log_info("Loading model...")
self.model_path = model_path
self.model_data_path = Path(
self.get_strpath_storage_for_file('data.dat'))
self.training_data_src_path = training_data_src_path
self.training_data_dst_path = training_data_dst_path
self.src_images_paths = None
self.dst_images_paths = None
self.src_yaw_images_paths = None
self.dst_yaw_images_paths = None
self.src_data_generator = None
self.dst_data_generator = None
self.debug = debug
self.is_training_mode = (training_data_src_path is not None
and training_data_dst_path is not None)
self.iter = 0
self.options = {}
self.loss_history = []
self.sample_for_preview = None
model_data = {}
if self.model_data_path.exists():
model_data = pickle.loads(self.model_data_path.read_bytes())
self.iter = max(model_data.get('iter', 0),
model_data.get('epoch', 0))
if 'epoch' in self.options:
self.options.pop('epoch')
if self.iter != 0:
self.options = model_data['options']
self.loss_history = model_data[
'loss_history'] if 'loss_history' in model_data.keys(
) else []
self.sample_for_preview = model_data[
'sample_for_preview'] if 'sample_for_preview' in model_data.keys(
) else None
ask_override = self.is_training_mode and self.iter != 0 and io.input_in_time(
"Press enter in 2 seconds to override model settings.", 2)
yn_str = {True: 'y', False: 'n'}
if self.iter == 0:
io.log_info(
"\nModel first run. Enter model options as default for each run."
)
if ask_write_preview_history and (self.iter == 0 or ask_override):
default_write_preview_history = False if self.iter == 0 else self.options.get(
'write_preview_history', False)
self.options['write_preview_history'] = io.input_bool(
"Write preview history? (y/n ?:help skip:%s) : " %
(yn_str[default_write_preview_history]),
default_write_preview_history,
help_message=
"Preview history will be writed to <ModelName>_history folder."
)
else:
self.options['write_preview_history'] = self.options.get(
'write_preview_history', False)
if ask_target_iter:
if (self.iter == 0 or ask_override):
self.options['target_iter'] = max(
0,
io.input_int(
"Target iteration (skip:unlimited/default) : ", 0))
else:
self.options['target_iter'] = max(
model_data.get('target_iter', 0),
self.options.get('target_epoch', 0))
if 'target_epoch' in self.options:
self.options.pop('target_epoch')
if ask_batch_size and (self.iter == 0 or ask_override):
default_batch_size = 0 if self.iter == 0 else self.options.get(
'batch_size', 0)
self.options['batch_size'] = max(
0,
io.input_int(
"Batch_size (?:help skip:%d) : " % (default_batch_size),
default_batch_size,
help_message=
"Larger batch size is better for NN's generalization, but it can cause Out of Memory error. Tune this value for your videocard manually."
))
else:
self.options['batch_size'] = self.options.get('batch_size', 0)
if ask_sort_by_yaw:
if (self.iter == 0):
self.options['sort_by_yaw'] = io.input_bool(
"Feed faces to network sorted by yaw? (y/n ?:help skip:n) : ",
False,
help_message=
"NN will not learn src face directions that don't match dst face directions. Do not use if the dst face has hair that covers the jaw."
)
else:
self.options['sort_by_yaw'] = self.options.get(
'sort_by_yaw', False)
if ask_random_flip:
if (self.iter == 0):
self.options['random_flip'] = io.input_bool(
"Flip faces randomly? (y/n ?:help skip:y) : ",
True,
help_message=
"Predicted face will look more naturally without this option, but src faceset should cover all face directions as dst faceset."
)
else:
self.options['random_flip'] = self.options.get(
'random_flip', True)
if ask_src_scale_mod:
if (self.iter == 0):
self.options['src_scale_mod'] = np.clip(
io.input_int(
"Src face scale modifier % ( -30...30, ?:help skip:0) : ",
0,
help_message=
"If src face shape is wider than dst, try to decrease this value to get a better result."
), -30, 30)
else:
self.options['src_scale_mod'] = self.options.get(
'src_scale_mod', 0)
self.write_preview_history = self.options.get('write_preview_history',
False)
if not self.write_preview_history and 'write_preview_history' in self.options:
self.options.pop('write_preview_history')
self.target_iter = self.options.get('target_iter', 0)
if self.target_iter == 0 and 'target_iter' in self.options:
self.options.pop('target_iter')
self.batch_size = self.options.get('batch_size', 0)
self.sort_by_yaw = self.options.get('sort_by_yaw', False)
self.random_flip = self.options.get('random_flip', True)
self.src_scale_mod = self.options.get('src_scale_mod', 0)
if self.src_scale_mod == 0 and 'src_scale_mod' in self.options:
self.options.pop('src_scale_mod')
self.onInitializeOptions(self.iter == 0, ask_override)
nnlib.import_all(self.device_config)
self.keras = nnlib.keras
self.K = nnlib.keras.backend
self.onInitialize()
self.options['batch_size'] = self.batch_size
if self.debug or self.batch_size == 0:
self.batch_size = 1
if self.is_training_mode:
if self.device_args['force_gpu_idx'] == -1:
self.preview_history_path = self.model_path / (
'%s_history' % (self.get_model_name()))
else:
self.preview_history_path = self.model_path / (
'%d_%s_history' %
(self.device_args['force_gpu_idx'], self.get_model_name()))
if self.write_preview_history or io.is_colab():
if not self.preview_history_path.exists():
self.preview_history_path.mkdir(exist_ok=True)
else:
if self.iter == 0:
for filename in Path_utils.get_image_paths(
self.preview_history_path):
Path(filename).unlink()
if self.generator_list is None:
raise ValueError('You didnt set_training_data_generators()')
else:
for i, generator in enumerate(self.generator_list):
if not isinstance(generator, SampleGeneratorBase):
raise ValueError(
'training data generator is not subclass of SampleGeneratorBase'
)
if (self.sample_for_preview is None) or (self.iter == 0):
self.sample_for_preview = self.generate_next_sample()
model_summary_text = []
model_summary_text += ["===== Model summary ====="]
model_summary_text += ["== Model name: " + self.get_model_name()]
model_summary_text += ["=="]
model_summary_text += ["== Current iteration: " + str(self.iter)]
model_summary_text += ["=="]
model_summary_text += ["== Model options:"]
for key in self.options.keys():
model_summary_text += ["== |== %s : %s" % (key, self.options[key])]
if self.device_config.multi_gpu:
model_summary_text += ["== |== multi_gpu : True "]
model_summary_text += ["== Running on:"]
if self.device_config.cpu_only:
model_summary_text += ["== |== [CPU]"]
else:
for idx in self.device_config.gpu_idxs:
model_summary_text += [
"== |== [%d : %s]" % (idx, nnlib.device.getDeviceName(idx))
]
if not self.device_config.cpu_only and self.device_config.gpu_vram_gb[
0] == 2:
model_summary_text += ["=="]
model_summary_text += [
"== WARNING: You are using 2GB GPU. Result quality may be significantly decreased."
]
model_summary_text += [
"== If training does not start, close all programs and try again."
]
model_summary_text += [
"== Also you can disable Windows Aero Desktop to get extra free VRAM."
]
model_summary_text += ["=="]
model_summary_text += ["========================="]
model_summary_text = "\r\n".join(model_summary_text)
self.model_summary_text = model_summary_text
io.log_info(model_summary_text)
def __init__(self,
model_path,
training_data_src_path=None,
training_data_dst_path=None,
pretraining_data_path=None,
debug=False,
device_args=None,
ask_enable_autobackup=True,
ask_write_preview_history=True,
ask_target_iter=True,
ask_batch_size=True,
ask_sort_by_yaw=True,
ask_random_flip=True,
ask_src_scale_mod=True):
device_args['force_gpu_idx'] = device_args.get('force_gpu_idx', -1)
device_args['cpu_only'] = device_args.get('cpu_only', False)
if device_args['force_gpu_idx'] == -1 and not device_args['cpu_only']:
idxs_names_list = nnlib.device.getValidDevicesIdxsWithNamesList()
if len(idxs_names_list) > 1:
io.log_info("You have multi GPUs in a system: ")
for idx, name in idxs_names_list:
io.log_info("[%d] : %s" % (idx, name))
device_args['force_gpu_idx'] = io.input_int(
"Which GPU idx to choose? ( skip: best GPU ) : ", -1,
[x[0] for x in idxs_names_list])
self.device_args = device_args
self.device_config = nnlib.DeviceConfig(allow_growth=True,
**self.device_args)
io.log_info("Loading model...")
self.model_path = model_path
self.model_data_path = Path(
self.get_strpath_storage_for_file('data.dat'))
self.training_data_src_path = training_data_src_path
self.training_data_dst_path = training_data_dst_path
self.pretraining_data_path = pretraining_data_path
self.src_images_paths = None
self.dst_images_paths = None
self.src_yaw_images_paths = None
self.dst_yaw_images_paths = None
self.src_data_generator = None
self.dst_data_generator = None
self.debug = debug
self.is_training_mode = (training_data_src_path is not None
and training_data_dst_path is not None)
self.iter = 0
self.options = {}
self.loss_history = []
self.sample_for_preview = None
model_data = {}
if self.model_data_path.exists():
model_data = pickle.loads(self.model_data_path.read_bytes())
self.iter = max(model_data.get('iter', 0),
model_data.get('epoch', 0))
if 'epoch' in self.options:
self.options.pop('epoch')
if self.iter != 0:
self.options = model_data['options']
self.loss_history = model_data.get('loss_history', [])
self.sample_for_preview = model_data.get(
'sample_for_preview', None)
ask_override = self.is_training_mode and self.iter != 0 and io.input_in_time(
"Press enter in 2 seconds to override model settings.",
5 if io.is_colab() else 2)
yn_str = {True: 'y', False: 'n'}
if self.iter == 0:
io.log_info(
"\nModel first run. Enter model options as default for each run."
)
if ask_enable_autobackup and (self.iter == 0 or ask_override):
default_autobackup = False if self.iter == 0 else self.options.get(
'autobackup', False)
self.options['autobackup'] = io.input_bool(
"Enable autobackup? (y/n ?:help skip:%s) : " %
(yn_str[default_autobackup]),
default_autobackup,
help_message=
"Autobackup model files with preview every hour for last 15 hours. Latest backup located in model/<>_autobackups/01"
)
else:
self.options['autobackup'] = self.options.get('autobackup', False)
if ask_write_preview_history and (self.iter == 0 or ask_override):
default_write_preview_history = False if self.iter == 0 else self.options.get(
'write_preview_history', False)
self.options['write_preview_history'] = io.input_bool(
"Write preview history? (y/n ?:help skip:%s) : " %
(yn_str[default_write_preview_history]),
default_write_preview_history,
help_message=
"Preview history will be writed to <ModelName>_history folder."
)
else:
self.options['write_preview_history'] = self.options.get(
'write_preview_history', False)
if (self.iter == 0 or ask_override) and self.options[
'write_preview_history'] and io.is_support_windows():
choose_preview_history = io.input_bool(
"Choose image for the preview history? (y/n skip:%s) : " %
(yn_str[False]), False)
elif (self.iter == 0 or ask_override
) and self.options['write_preview_history'] and io.is_colab():
choose_preview_history = io.input_bool(
"Randomly choose new image for preview history? (y/n ?:help skip:%s) : "
% (yn_str[False]),
False,
help_message=
"Preview image history will stay stuck with old faces if you reuse the same model on different celebs. Choose no unless you are changing src/dst to a new person"
)
else:
choose_preview_history = False
if ask_target_iter:
if (self.iter == 0 or ask_override):
self.options['target_iter'] = max(
0,
io.input_int(
"Target iteration (skip:unlimited/default) : ", 0))
else:
self.options['target_iter'] = max(
model_data.get('target_iter', 0),
self.options.get('target_epoch', 0))
if 'target_epoch' in self.options:
self.options.pop('target_epoch')
if ask_batch_size and (self.iter == 0 or ask_override):
default_batch_size = 0 if self.iter == 0 else self.options.get(
'batch_size', 0)
self.options['batch_size'] = max(
0,
io.input_int(
"Batch_size (?:help skip:%d) : " % (default_batch_size),
default_batch_size,
help_message=
"Larger batch size is better for NN's generalization, but it can cause Out of Memory error. Tune this value for your videocard manually."
))
else:
self.options['batch_size'] = self.options.get('batch_size', 0)
if ask_sort_by_yaw:
if (self.iter == 0 or ask_override):
default_sort_by_yaw = self.options.get('sort_by_yaw', False)
self.options['sort_by_yaw'] = io.input_bool(
"Feed faces to network sorted by yaw? (y/n ?:help skip:%s) : "
% (yn_str[default_sort_by_yaw]),
default_sort_by_yaw,
help_message=
"NN will not learn src face directions that don't match dst face directions. Do not use if the dst face has hair that covers the jaw."
)
else:
self.options['sort_by_yaw'] = self.options.get(
'sort_by_yaw', False)
if ask_random_flip:
if (self.iter == 0):
self.options['random_flip'] = io.input_bool(
"Flip faces randomly? (y/n ?:help skip:y) : ",
True,
help_message=
"Predicted face will look more naturally without this option, but src faceset should cover all face directions as dst faceset."
)
else:
self.options['random_flip'] = self.options.get(
'random_flip', True)
if ask_src_scale_mod:
if (self.iter == 0):
self.options['src_scale_mod'] = np.clip(
io.input_int(
"Src face scale modifier % ( -30...30, ?:help skip:0) : ",
0,
help_message=
"If src face shape is wider than dst, try to decrease this value to get a better result."
), -30, 30)
else:
self.options['src_scale_mod'] = self.options.get(
'src_scale_mod', 0)
self.autobackup = self.options.get('autobackup', False)
if not self.autobackup and 'autobackup' in self.options:
self.options.pop('autobackup')
self.write_preview_history = self.options.get('write_preview_history',
False)
if not self.write_preview_history and 'write_preview_history' in self.options:
self.options.pop('write_preview_history')
self.target_iter = self.options.get('target_iter', 0)
if self.target_iter == 0 and 'target_iter' in self.options:
self.options.pop('target_iter')
self.batch_size = self.options.get('batch_size', 0)
self.sort_by_yaw = self.options.get('sort_by_yaw', False)
self.random_flip = self.options.get('random_flip', True)
self.src_scale_mod = self.options.get('src_scale_mod', 0)
if self.src_scale_mod == 0 and 'src_scale_mod' in self.options:
self.options.pop('src_scale_mod')
self.onInitializeOptions(self.iter == 0, ask_override)
nnlib.import_all(self.device_config)
self.keras = nnlib.keras
self.K = nnlib.keras.backend
self.onInitialize()
self.options['batch_size'] = self.batch_size
if self.debug or self.batch_size == 0:
self.batch_size = 1
if self.is_training_mode:
if self.device_args['force_gpu_idx'] == -1:
self.preview_history_path = self.model_path / (
'%s_history' % (self.get_model_name()))
self.autobackups_path = self.model_path / (
'%s_autobackups' % (self.get_model_name()))
else:
self.preview_history_path = self.model_path / (
'%d_%s_history' %
(self.device_args['force_gpu_idx'], self.get_model_name()))
self.autobackups_path = self.model_path / (
'%d_%s_autobackups' %
(self.device_args['force_gpu_idx'], self.get_model_name()))
if self.autobackup:
self.autobackup_current_hour = time.localtime().tm_hour
if not self.autobackups_path.exists():
self.autobackups_path.mkdir(exist_ok=True)
if self.write_preview_history or io.is_colab():
if not self.preview_history_path.exists():
self.preview_history_path.mkdir(exist_ok=True)
else:
if self.iter == 0:
for filename in Path_utils.get_image_paths(
self.preview_history_path):
Path(filename).unlink()
if self.generator_list is None:
raise ValueError('You didnt set_training_data_generators()')
else:
for i, generator in enumerate(self.generator_list):
if not isinstance(generator, SampleGeneratorBase):
raise ValueError(
'training data generator is not subclass of SampleGeneratorBase'
)
if self.sample_for_preview is None or choose_preview_history:
if choose_preview_history and io.is_support_windows():
wnd_name = "[p] - next. [enter] - confirm."
io.named_window(wnd_name)
io.capture_keys(wnd_name)
choosed = False
while not choosed:
self.sample_for_preview = self.generate_next_sample()
preview = self.get_static_preview()
io.show_image(wnd_name,
(preview * 255).astype(np.uint8))
while True:
key_events = io.get_key_events(wnd_name)
key, chr_key, ctrl_pressed, alt_pressed, shift_pressed = key_events[
-1] if len(key_events) > 0 else (0, 0, False,
False, False)
if key == ord('\n') or key == ord('\r'):
choosed = True
break
elif key == ord('p'):
break
try:
io.process_messages(0.1)
except KeyboardInterrupt:
choosed = True
io.destroy_window(wnd_name)
else:
self.sample_for_preview = self.generate_next_sample()
self.last_sample = self.sample_for_preview
###Generate text summary of model hyperparameters
#Find the longest key name and value string. Used as column widths.
width_name = max(
[len(k) for k in self.options.keys()] + [17]
) + 1 # Single space buffer to left edge. Minimum of 17, the length of the longest static string used "Current iteration"
width_value = max([len(str(x)) for x in self.options.values()] +
[len(str(self.iter)),
len(self.get_model_name())]
) + 1 # Single space buffer to right edge
if not self.device_config.cpu_only: #Check length of GPU names
width_value = max([
len(nnlib.device.getDeviceName(idx)) + 1
for idx in self.device_config.gpu_idxs
] + [width_value])
width_total = width_name + width_value + 2 #Plus 2 for ": "
model_summary_text = []
model_summary_text += [f'=={" Model Summary ":=^{width_total}}=='
] # Model/status summary
model_summary_text += [f'=={" "*width_total}==']
model_summary_text += [
f'=={"Model name": >{width_name}}: {self.get_model_name(): <{width_value}}=='
] # Name
model_summary_text += [f'=={" "*width_total}==']
model_summary_text += [
f'=={"Current iteration": >{width_name}}: {str(self.iter): <{width_value}}=='
] # Iter
model_summary_text += [f'=={" "*width_total}==']
model_summary_text += [f'=={" Model Options ":-^{width_total}}=='
] # Model options
model_summary_text += [f'=={" "*width_total}==']
for key in self.options.keys():
model_summary_text += [
f'=={key: >{width_name}}: {str(self.options[key]): <{width_value}}=='
] # self.options key/value pairs
model_summary_text += [f'=={" "*width_total}==']
model_summary_text += [f'=={" Running On ":-^{width_total}}=='
] # Training hardware info
model_summary_text += [f'=={" "*width_total}==']
if self.device_config.multi_gpu:
model_summary_text += [
f'=={"Using multi_gpu": >{width_name}}: {"True": <{width_value}}=='
] # multi_gpu
model_summary_text += [f'=={" "*width_total}==']
if self.device_config.cpu_only:
model_summary_text += [
f'=={"Using device": >{width_name}}: {"CPU": <{width_value}}=='
] # cpu_only
else:
for idx in self.device_config.gpu_idxs:
model_summary_text += [
f'=={"Device index": >{width_name}}: {idx: <{width_value}}=='
] # GPU hardware device index
model_summary_text += [
f'=={"Name": >{width_name}}: {nnlib.device.getDeviceName(idx): <{width_value}}=='
] # GPU name
vram_str = f'{nnlib.device.getDeviceVRAMTotalGb(idx):.2f}GB' # GPU VRAM - Formated as #.## (or ##.##)
model_summary_text += [
f'=={"VRAM": >{width_name}}: {vram_str: <{width_value}}=='
]
model_summary_text += [f'=={" "*width_total}==']
model_summary_text += [f'=={"="*width_total}==']
if not self.device_config.cpu_only and self.device_config.gpu_vram_gb[
0] <= 2: # Low VRAM warning
model_summary_text += ["/!\\"]
model_summary_text += ["/!\\ WARNING:"]
model_summary_text += [
"/!\\ You are using a GPU with 2GB or less VRAM. This may significantly reduce the quality of your result!"
]
model_summary_text += [
"/!\\ If training does not start, close all programs and try again."
]
model_summary_text += [
"/!\\ Also you can disable Windows Aero Desktop to increase available VRAM."
]
model_summary_text += ["/!\\"]
model_summary_text = "\n".join(model_summary_text)
self.model_summary_text = model_summary_text
io.log_info(model_summary_text)
def mask_editor_main(input_dir,
confirmed_dir=None,
skipped_dir=None,
no_default_mask=False):
input_path = Path(input_dir)
confirmed_path = Path(confirmed_dir)
skipped_path = Path(skipped_dir)
if not input_path.exists():
raise ValueError('Input directory not found. Please ensure it exists.')
if not confirmed_path.exists():
confirmed_path.mkdir(parents=True)
if not skipped_path.exists():
skipped_path.mkdir(parents=True)
if not no_default_mask:
eyebrows_expand_mod = np.clip(
io.input_int(
"Default eyebrows expand modifier? (0..400, skip:100) : ",
100), 0, 400) / 100.0
else:
eyebrows_expand_mod = None
wnd_name = "MaskEditor tool"
io.named_window(wnd_name)
io.capture_mouse(wnd_name)
io.capture_keys(wnd_name)
cached_images = {}
image_paths = [Path(x) for x in Path_utils.get_image_paths(input_path)]
done_paths = []
done_images_types = {}
image_paths_total = len(image_paths)
saved_ie_polys = IEPolys()
zoom_factor = 1.0
preview_images_count = 9
target_wh = 256
do_prev_count = 0
do_save_move_count = 0
do_save_count = 0
do_skip_move_count = 0
do_skip_count = 0
def jobs_count():
return do_prev_count + do_save_move_count + do_save_count + do_skip_move_count + do_skip_count
is_exit = False
while not is_exit:
if len(image_paths) > 0:
filepath = image_paths.pop(0)
else:
filepath = None
next_image_paths = image_paths[0:preview_images_count]
next_image_paths_names = [path.name for path in next_image_paths]
prev_image_paths = done_paths[-preview_images_count:]
prev_image_paths_names = [path.name for path in prev_image_paths]
for key in list(cached_images.keys()):
if key not in prev_image_paths_names and \
key not in next_image_paths_names:
cached_images.pop(key)
for paths in [prev_image_paths, next_image_paths]:
for path in paths:
if path.name not in cached_images:
cached_images[path.name] = cv2_imread(str(path)) / 255.0
if filepath is not None:
if filepath.suffix == '.png':
dflimg = DFLPNG.load(str(filepath))
elif filepath.suffix == '.jpg':
dflimg = DFLJPG.load(str(filepath))
else:
dflimg = None
if dflimg is None:
io.log_err("%s is not a dfl image file" % (filepath.name))
continue
else:
lmrks = dflimg.get_landmarks()
ie_polys = dflimg.get_ie_polys()
fanseg_mask = dflimg.get_fanseg_mask()
if filepath.name in cached_images:
img = cached_images[filepath.name]
else:
img = cached_images[filepath.name] = cv2_imread(
str(filepath)) / 255.0
if fanseg_mask is not None:
mask = fanseg_mask
else:
if no_default_mask:
mask = np.zeros((target_wh, target_wh, 3))
else:
mask = LandmarksProcessor.get_image_hull_mask(
img.shape,
lmrks,
eyebrows_expand_mod=eyebrows_expand_mod)
else:
img = np.zeros((target_wh, target_wh, 3))
mask = np.ones((target_wh, target_wh, 3))
ie_polys = None
def get_status_lines_func():
return [
'Progress: %d / %d . Current file: %s' %
(len(done_paths), image_paths_total,
str(filepath.name) if filepath is not None else "end"),
'[Left mouse button] - mark include mask.',
'[Right mouse button] - mark exclude mask.',
'[Middle mouse button] - finish current poly.',
'[Mouse wheel] - undo/redo poly or point. [+ctrl] - undo to begin/redo to end',
'[r] - applies edits made to last saved image.',
'[q] - prev image. [w] - skip and move to %s. [e] - save and move to %s. '
% (skipped_path.name, confirmed_path.name),
'[z] - prev image. [x] - skip. [c] - save. ',
'hold [shift] - speed up the frame counter by 10.',
'[-/+] - window zoom [esc] - quit',
]
try:
ed = MaskEditor(img,
[(done_images_types[name], cached_images[name])
for name in prev_image_paths_names],
[(0, cached_images[name])
for name in next_image_paths_names], mask,
ie_polys, get_status_lines_func)
except Exception as e:
print(e)
continue
next = False
while not next:
io.process_messages(0.005)
if jobs_count() == 0:
for (x, y, ev, flags) in io.get_mouse_events(wnd_name):
x, y = int(x / zoom_factor), int(y / zoom_factor)
ed.set_mouse_pos(x, y)
if filepath is not None:
if ev == io.EVENT_LBUTTONDOWN:
ed.mask_point(1)
elif ev == io.EVENT_RBUTTONDOWN:
ed.mask_point(0)
elif ev == io.EVENT_MBUTTONDOWN:
ed.mask_finish()
elif ev == io.EVENT_MOUSEWHEEL:
if flags & 0x80000000 != 0:
if flags & 0x8 != 0:
ed.undo_to_begin_point()
else:
ed.undo_point()
else:
if flags & 0x8 != 0:
ed.redo_to_end_point()
else:
ed.redo_point()
for key, chr_key, ctrl_pressed, alt_pressed, shift_pressed in io.get_key_events(
wnd_name):
if chr_key == 'q' or chr_key == 'z':
do_prev_count = 1 if not shift_pressed else 10
elif chr_key == '-':
zoom_factor = np.clip(zoom_factor - 0.1, 0.1, 4.0)
ed.set_screen_changed()
elif chr_key == '+':
zoom_factor = np.clip(zoom_factor + 0.1, 0.1, 4.0)
ed.set_screen_changed()
elif key == 27: #esc
is_exit = True
next = True
break
elif filepath is not None:
if chr_key == 'e':
saved_ie_polys = ed.ie_polys
do_save_move_count = 1 if not shift_pressed else 10
elif chr_key == 'c':
saved_ie_polys = ed.ie_polys
do_save_count = 1 if not shift_pressed else 10
elif chr_key == 'w':
do_skip_move_count = 1 if not shift_pressed else 10
elif chr_key == 'x':
do_skip_count = 1 if not shift_pressed else 10
elif chr_key == 'r' and saved_ie_polys != None:
ed.set_ie_polys(saved_ie_polys)
if do_prev_count > 0:
do_prev_count -= 1
if len(done_paths) > 0:
if filepath is not None:
image_paths.insert(0, filepath)
filepath = done_paths.pop(-1)
done_images_types[filepath.name] = 0
if filepath.parent != input_path:
new_filename_path = input_path / filepath.name
filepath.rename(new_filename_path)
image_paths.insert(0, new_filename_path)
else:
image_paths.insert(0, filepath)
next = True
elif filepath is not None:
if do_save_move_count > 0:
do_save_move_count -= 1
ed.mask_finish()
dflimg.embed_and_set(
str(filepath),
ie_polys=ed.get_ie_polys(),
eyebrows_expand_mod=eyebrows_expand_mod)
done_paths += [confirmed_path / filepath.name]
done_images_types[filepath.name] = 2
filepath.rename(done_paths[-1])
next = True
elif do_save_count > 0:
do_save_count -= 1
ed.mask_finish()
dflimg.embed_and_set(
str(filepath),
ie_polys=ed.get_ie_polys(),
eyebrows_expand_mod=eyebrows_expand_mod)
done_paths += [filepath]
done_images_types[filepath.name] = 2
next = True
elif do_skip_move_count > 0:
do_skip_move_count -= 1
done_paths += [skipped_path / filepath.name]
done_images_types[filepath.name] = 1
filepath.rename(done_paths[-1])
next = True
elif do_skip_count > 0:
do_skip_count -= 1
done_paths += [filepath]
done_images_types[filepath.name] = 1
next = True
else:
do_save_move_count = do_save_count = do_skip_move_count = do_skip_count = 0
if jobs_count() == 0:
if ed.switch_screen_changed():
screen = ed.make_screen()
if zoom_factor != 1.0:
h, w, c = screen.shape
screen = cv2.resize(
screen,
(int(w * zoom_factor), int(h * zoom_factor)))
io.show_image(wnd_name, screen)
io.process_messages(0.005)
io.destroy_all_windows()
def onInitializeOptions(self, is_first_run, ask_override):
yn_str = {True: 'y', False: 'n'}
default_resolution = 128
default_archi = 'df'
default_face_type = 'f'
if is_first_run:
resolution = io.input_int(
"Resolution ( 64-256 ?:help skip:128) : ",
default_resolution,
help_message=
"More resolution requires more VRAM and time to train. Value will be adjusted to multiple of 16."
)
resolution = np.clip(resolution, 64, 256)
while np.modf(resolution / 16)[0] != 0.0:
resolution -= 1
self.options['resolution'] = resolution
self.options['face_type'] = io.input_str(
"Half or Full face? (h/f, ?:help skip:f) : ",
default_face_type, ['h', 'f'],
help_message=
"Half face has better resolution, but covers less area of cheeks."
).lower()
self.options['learn_mask'] = io.input_bool(
"Learn mask? (y/n, ?:help skip:y) : ",
True,
help_message=
"Learning mask can help model to recognize face directions. Learn without mask can reduce model size, in this case converter forced to use 'not predicted mask' that is not smooth as predicted. Model with style values can be learned without mask and produce same quality result."
)
else:
self.options['resolution'] = self.options.get(
'resolution', default_resolution)
self.options['face_type'] = self.options.get(
'face_type', default_face_type)
self.options['learn_mask'] = self.options.get('learn_mask', True)
if (is_first_run or
ask_override) and 'tensorflow' in self.device_config.backend:
def_optimizer_mode = self.options.get('optimizer_mode', 1)
self.options['optimizer_mode'] = io.input_int(
"Optimizer mode? ( 1,2,3 ?:help skip:%d) : " %
(def_optimizer_mode),
def_optimizer_mode,
help_message=
"1 - no changes. 2 - allows you to train x2 bigger network consuming RAM. 3 - allows you to train x3 bigger network consuming huge amount of RAM and slower, depends on CPU power."
)
else:
self.options['optimizer_mode'] = self.options.get(
'optimizer_mode', 1)
if is_first_run:
self.options['archi'] = io.input_str(
"AE architecture (df, liae ?:help skip:%s) : " %
(default_archi),
default_archi, ['df', 'liae'],
help_message=
"'df' keeps faces more natural. 'liae' can fix overly different face shapes."
).lower(
) #-s version is slower, but has decreased change to collapse.
else:
self.options['archi'] = self.options.get('archi', default_archi)
default_ae_dims = 256 if 'liae' in self.options['archi'] else 512
default_e_ch_dims = 42
default_d_ch_dims = default_e_ch_dims // 2
def_ca_weights = False
if is_first_run:
self.options['ae_dims'] = np.clip(
io.input_int(
"AutoEncoder dims (32-1024 ?:help skip:%d) : " %
(default_ae_dims),
default_ae_dims,
help_message=
"All face information will packed to AE dims. If amount of AE dims are not enough, then for example closed eyes will not be recognized. More dims are better, but require more VRAM. You can fine-tune model size to fit your GPU."
), 32, 1024)
self.options['e_ch_dims'] = np.clip(
io.input_int(
"Encoder dims per channel (21-85 ?:help skip:%d) : " %
(default_e_ch_dims),
default_e_ch_dims,
help_message=
"More encoder dims help to recognize more facial features, but require more VRAM. You can fine-tune model size to fit your GPU."
), 21, 85)
default_d_ch_dims = self.options['e_ch_dims'] // 2
self.options['d_ch_dims'] = np.clip(
io.input_int(
"Decoder dims per channel (10-85 ?:help skip:%d) : " %
(default_d_ch_dims),
default_d_ch_dims,
help_message=
"More decoder dims help to get better details, but require more VRAM. You can fine-tune model size to fit your GPU."
), 10, 85)
self.options['multiscale_decoder'] = io.input_bool(
"Use multiscale decoder? (y/n, ?:help skip:n) : ",
False,
help_message="Multiscale decoder helps to get better details.")
self.options['ca_weights'] = io.input_bool(
"Use CA weights? (y/n, ?:help skip: %s ) : " %
(yn_str[def_ca_weights]),
def_ca_weights,
help_message=
"Initialize network with 'Convolution Aware' weights. This may help to achieve a higher accuracy model, but consumes a time at first run."
)
else:
self.options['ae_dims'] = self.options.get('ae_dims',
default_ae_dims)
self.options['e_ch_dims'] = self.options.get(
'e_ch_dims', default_e_ch_dims)
self.options['d_ch_dims'] = self.options.get(
'd_ch_dims', default_d_ch_dims)
self.options['multiscale_decoder'] = self.options.get(
'multiscale_decoder', False)
self.options['ca_weights'] = self.options.get(
'ca_weights', def_ca_weights)
default_face_style_power = 0.0
default_bg_style_power = 0.0
if is_first_run or ask_override:
def_pixel_loss = self.options.get('pixel_loss', False)
self.options['pixel_loss'] = io.input_bool(
"Use pixel loss? (y/n, ?:help skip: %s ) : " %
(yn_str[def_pixel_loss]),
def_pixel_loss,
help_message=
"Pixel loss may help to enhance fine details and stabilize face color. Use it only if quality does not improve over time. Enabling this option too early increases the chance of model collapse."
)
default_face_style_power = default_face_style_power if is_first_run else self.options.get(
'face_style_power', default_face_style_power)
self.options['face_style_power'] = np.clip(
io.input_number(
"Face style power ( 0.0 .. 100.0 ?:help skip:%.2f) : " %
(default_face_style_power),
default_face_style_power,
help_message=
"Learn to transfer face style details such as light and color conditions. Warning: Enable it only after 10k iters, when predicted face is clear enough to start learn style. Start from 0.1 value and check history changes. Enabling this option increases the chance of model collapse."
), 0.0, 100.0)
default_bg_style_power = default_bg_style_power if is_first_run else self.options.get(
'bg_style_power', default_bg_style_power)
self.options['bg_style_power'] = np.clip(
io.input_number(
"Background style power ( 0.0 .. 100.0 ?:help skip:%.2f) : "
% (default_bg_style_power),
default_bg_style_power,
help_message=
"Learn to transfer image around face. This can make face more like dst. Enabling this option increases the chance of model collapse."
), 0.0, 100.0)
default_apply_random_ct = False if is_first_run else self.options.get(
'apply_random_ct', False)
self.options['apply_random_ct'] = io.input_bool(
"Apply random color transfer to src faceset? (y/n, ?:help skip:%s) : "
% (yn_str[default_apply_random_ct]),
default_apply_random_ct,
help_message=
"Increase variativity of src samples by apply LCT color transfer from random dst samples. It is like 'face_style' learning, but more precise color transfer and without risk of model collapse, also it does not require additional GPU resources, but the training time may be longer, due to the src faceset is becoming more diverse."
)
if nnlib.device.backend != 'plaidML': # todo https://github.com/plaidml/plaidml/issues/301
default_clipgrad = False if is_first_run else self.options.get(
'clipgrad', False)
self.options['clipgrad'] = io.input_bool(
"Enable gradient clipping? (y/n, ?:help skip:%s) : " %
(yn_str[default_clipgrad]),
default_clipgrad,
help_message=
"Gradient clipping reduces chance of model collapse, sacrificing speed of training."
)
else:
self.options['clipgrad'] = False
else:
self.options['pixel_loss'] = self.options.get('pixel_loss', False)
self.options['face_style_power'] = self.options.get(
'face_style_power', default_face_style_power)
self.options['bg_style_power'] = self.options.get(
'bg_style_power', default_bg_style_power)
self.options['apply_random_ct'] = self.options.get(
'apply_random_ct', False)
self.options['clipgrad'] = self.options.get('clipgrad', False)
if is_first_run:
self.options['pretrain'] = io.input_bool(
"Pretrain the model? (y/n, ?:help skip:n) : ",
False,
help_message=
"Pretrain the model with large amount of various faces. This technique may help to train the fake with overly different face shapes and light conditions of src/dst data. Face will be look more like a morphed. To reduce the morph effect, some model files will be initialized but not be updated after pretrain: LIAE: inter_AB.h5 DF: encoder.h5. The longer you pretrain the model the more morphed face will look. After that, save and run the training again."
)
else:
self.options['pretrain'] = False
def sort_final(input_path, include_by_blur=True):
io.log_info("Performing final sort.")
target_count = io.input_int("Target number of images? (default:2000) : ",
2000)
img_list, trash_img_list = FinalLoaderSubprocessor(
Path_utils.get_image_paths(input_path), include_by_blur).run()
final_img_list = []
grads = 128
imgs_per_grad = round(target_count / grads)
grads_space = np.linspace(-1.0, 1.0, grads)
yaws_sample_list = [None] * grads
for g in io.progress_bar_generator(range(grads), "Sort by yaw"):
yaw = grads_space[g]
next_yaw = grads_space[g + 1] if g < grads - 1 else yaw
yaw_samples = []
for img in img_list:
s_yaw = -img[3]
if (g == 0 and s_yaw < next_yaw) or \
(g < grads-1 and s_yaw >= yaw and s_yaw < next_yaw) or \
(g == grads-1 and s_yaw >= yaw):
yaw_samples += [img]
if len(yaw_samples) > 0:
yaws_sample_list[g] = yaw_samples
total_lack = 0
for g in io.progress_bar_generator(range(grads), ""):
img_list = yaws_sample_list[g]
img_list_len = len(img_list) if img_list is not None else 0
lack = imgs_per_grad - img_list_len
total_lack += max(lack, 0)
imgs_per_grad += total_lack // grads
if include_by_blur:
sharpned_imgs_per_grad = imgs_per_grad * 10
for g in io.progress_bar_generator(range(grads), "Sort by blur"):
img_list = yaws_sample_list[g]
if img_list is None:
continue
img_list = sorted(img_list,
key=operator.itemgetter(1),
reverse=True)
if len(img_list) > sharpned_imgs_per_grad:
trash_img_list += img_list[sharpned_imgs_per_grad:]
img_list = img_list[0:sharpned_imgs_per_grad]
yaws_sample_list[g] = img_list
yaw_pitch_sample_list = [None] * grads
pitch_grads = imgs_per_grad
for g in io.progress_bar_generator(range(grads), "Sort by pitch"):
img_list = yaws_sample_list[g]
if img_list is None:
continue
pitch_sample_list = [None] * pitch_grads
grads_space = np.linspace(-1.0, 1.0, pitch_grads)
for pg in range(pitch_grads):
pitch = grads_space[pg]
next_pitch = grads_space[pg + 1] if pg < pitch_grads - 1 else pitch
pitch_samples = []
for img in img_list:
s_pitch = img[4]
if (pg == 0 and s_pitch < next_pitch) or \
(pg < pitch_grads-1 and s_pitch >= pitch and s_pitch < next_pitch) or \
(pg == pitch_grads-1 and s_pitch >= pitch):
pitch_samples += [img]
if len(pitch_samples) > 0:
pitch_sample_list[pg] = pitch_samples
yaw_pitch_sample_list[g] = pitch_sample_list
yaw_pitch_sample_list = FinalHistDissimSubprocessor(
yaw_pitch_sample_list).run()
for g in io.progress_bar_generator(range(grads), "Fetching the best"):
pitch_sample_list = yaw_pitch_sample_list[g]
if pitch_sample_list is None:
continue
n = imgs_per_grad
while n > 0:
n_prev = n
for pg in range(pitch_grads):
img_list = pitch_sample_list[pg]
if img_list is None:
continue
final_img_list += [img_list.pop(0)]
if len(img_list) == 0:
pitch_sample_list[pg] = None
n -= 1
if n == 0:
break
if n_prev == n:
break
for pg in range(pitch_grads):
img_list = pitch_sample_list[pg]
if img_list is None:
continue
trash_img_list += img_list
return final_img_list, trash_img_list
def onInitializeOptions(self, is_first_run, ask_override):
yn_str = {True:'y',False:'n'}
default_resolution = 128
default_archi = 'df'
default_face_type = 'f'
if is_first_run:
resolution = io.input_int("Resolution ( 64-256 ?:help skip:128) : ", default_resolution, help_message="More resolution requires more VRAM and time to train. Value will be adjusted to multiple of 16.")
resolution = np.clip (resolution, 64, 256)
while np.modf(resolution / 16)[0] != 0.0:
resolution -= 1
self.options['resolution'] = resolution
self.options['face_type'] = io.input_str ("Half or Full face? (h/f, ?:help skip:f) : ", default_face_type, ['h','f'], help_message="Half face has better resolution, but covers less area of cheeks.").lower()
self.options['learn_mask'] = io.input_bool ("Learn mask? (y/n, ?:help skip:y) : ", True, help_message="Learning mask can help model to recognize face directions. Learn without mask can reduce model size, in this case converter forced to use 'not predicted mask' that is not smooth as predicted. Model with style values can be learned without mask and produce same quality result.")
else:
self.options['resolution'] = self.options.get('resolution', default_resolution)
self.options['face_type'] = self.options.get('face_type', default_face_type)
self.options['learn_mask'] = self.options.get('learn_mask', True)
if (is_first_run or ask_override) and 'tensorflow' in self.device_config.backend:
def_optimizer_mode = self.options.get('optimizer_mode', 1)
self.options['optimizer_mode'] = io.input_int ("Optimizer mode? ( 1,2,3 ?:help skip:%d) : " % (def_optimizer_mode), def_optimizer_mode, help_message="1 - no changes. 2 - allows you to train x2 bigger network consuming RAM. 3 - allows you to train x3 bigger network consuming huge amount of RAM and slower, depends on CPU power.")
else:
self.options['optimizer_mode'] = self.options.get('optimizer_mode', 1)
if is_first_run:
self.options['archi'] = io.input_str ("AE architecture (df, liae ?:help skip:%s) : " % (default_archi) , default_archi, ['df','liae'], help_message="'df' keeps faces more natural. 'liae' can fix overly different face shapes.").lower()
else:
self.options['archi'] = self.options.get('archi', default_archi)
default_ae_dims = 256 if self.options['archi'] == 'liae' else 512
default_e_ch_dims = 42
default_d_ch_dims = default_e_ch_dims // 2
if is_first_run:
self.options['ae_dims'] = np.clip ( io.input_int("AutoEncoder dims (32-1024 ?:help skip:%d) : " % (default_ae_dims) , default_ae_dims, help_message="All face information will packed to AE dims. If amount of AE dims are not enough, then for example closed eyes will not be recognized. More dims are better, but require more VRAM. You can fine-tune model size to fit your GPU." ), 32, 1024 )
self.options['e_ch_dims'] = np.clip ( io.input_int("Encoder dims per channel (21-85 ?:help skip:%d) : " % (default_e_ch_dims) , default_e_ch_dims, help_message="More encoder dims help to recognize more facial features, but require more VRAM. You can fine-tune model size to fit your GPU." ), 21, 85 )
default_d_ch_dims = self.options['e_ch_dims'] // 2
self.options['d_ch_dims'] = np.clip ( io.input_int("Decoder dims per channel (10-85 ?:help skip:%d) : " % (default_d_ch_dims) , default_d_ch_dims, help_message="More decoder dims help to get better details, but require more VRAM. You can fine-tune model size to fit your GPU." ), 10, 85 )
self.options['d_residual_blocks'] = io.input_bool ("Add residual blocks to decoder? (y/n, ?:help skip:n) : ", False, help_message="These blocks help to get better details, but require more computing time.")
self.options['remove_gray_border'] = io.input_bool ("Remove gray border? (y/n, ?:help skip:n) : ", False, help_message="Removes gray border of predicted face, but requires more computing resources.")
else:
self.options['ae_dims'] = self.options.get('ae_dims', default_ae_dims)
self.options['e_ch_dims'] = self.options.get('e_ch_dims', default_e_ch_dims)
self.options['d_ch_dims'] = self.options.get('d_ch_dims', default_d_ch_dims)
self.options['d_residual_blocks'] = self.options.get('d_residual_blocks', False)
self.options['remove_gray_border'] = self.options.get('remove_gray_border', False)
if is_first_run:
self.options['lighter_encoder'] = io.input_bool ("Use lightweight encoder? (y/n, ?:help skip:n) : ", False, help_message="Lightweight encoder is 35% faster, requires less VRAM, but sacrificing overall quality.")
self.options['multiscale_decoder'] = io.input_bool ("Use multiscale decoder? (y/n, ?:help skip:n) : ", False, help_message="Multiscale decoder helps to get better details.")
else:
self.options['lighter_encoder'] = self.options.get('lighter_encoder', False)
self.options['multiscale_decoder'] = self.options.get('multiscale_decoder', False)
default_face_style_power = 0.0
default_bg_style_power = 0.0
if is_first_run or ask_override:
def_pixel_loss = self.options.get('pixel_loss', False)
self.options['pixel_loss'] = io.input_bool ("Use pixel loss? (y/n, ?:help skip: %s ) : " % (yn_str[def_pixel_loss]), def_pixel_loss, help_message="Default DSSIM loss good for initial understanding structure of faces. Use pixel loss after 15-25k iters to enhance fine details and decrease face jitter.")
default_face_style_power = default_face_style_power if is_first_run else self.options.get('face_style_power', default_face_style_power)
self.options['face_style_power'] = np.clip ( io.input_number("Face style power ( 0.0 .. 100.0 ?:help skip:%.2f) : " % (default_face_style_power), default_face_style_power,
help_message="Learn to transfer face style details such as light and color conditions. Warning: Enable it only after 10k iters, when predicted face is clear enough to start learn style. Start from 0.1 value and check history changes."), 0.0, 100.0 )
default_bg_style_power = default_bg_style_power if is_first_run else self.options.get('bg_style_power', default_bg_style_power)
self.options['bg_style_power'] = np.clip ( io.input_number("Background style power ( 0.0 .. 100.0 ?:help skip:%.2f) : " % (default_bg_style_power), default_bg_style_power,
help_message="Learn to transfer image around face. This can make face more like dst."), 0.0, 100.0 )
else:
self.options['pixel_loss'] = self.options.get('pixel_loss', False)
self.options['face_style_power'] = self.options.get('face_style_power', default_face_style_power)
self.options['bg_style_power'] = self.options.get('bg_style_power', default_bg_style_power)
def extract():
import os
import shutil
from mainscripts import VideoEd
from mainscripts import Extractor
from interact import interact as io
root_dir = get_root_path()
extract_workspace = os.path.join(root_dir, "extract_workspace")
target_dir = os.path.join(extract_workspace, "aligned_")
valid_exts = [".mp4", ".avi", ".wmv", ".mkv"]
fps = io.input_int(
"Enter FPS ( ?:help skip:fullfps ) : ",
0,
help_message=
"How many frames of every second of the video will be extracted.")
min_pixel = io.input_int("Enter Min Pixel ( ?:help skip: 512) : ",
512,
help_message="Min Pixel")
def file_filter(file):
if os.path.isdir(os.path.join(extract_workspace, file)):
return False
ext = os.path.splitext(file)[-1]
if ext not in valid_exts:
return False
return True
files = list(filter(file_filter, os.listdir(extract_workspace)))
files.sort()
pos = 0
for file in files:
pos += 1
io.log_info("@@@@@ Start Process %s, %d / %d" %
(file, pos, len(files)))
# 提取图片
input_file = os.path.join(extract_workspace, file)
output_dir = os.path.join(extract_workspace, "extract_images")
if not os.path.exists(output_dir):
os.mkdir(output_dir)
for f in os.listdir(output_dir):
os.remove(os.path.join(output_dir, f))
VideoEd.extract_video(input_file,
output_dir,
output_ext="png",
fps=fps)
io.log_info("@@@@@ Start Extract %s, %d / %d" %
(file, pos, len(files)))
# 提取人脸
input_dir = output_dir
output_dir = os.path.join(extract_workspace, "_current")
debug_dir = os.path.join(extract_workspace, "debug")
Extractor.main(input_dir,
output_dir,
debug_dir,
"s3fd",
min_pixel=min_pixel)
# fanseg
io.log_info("@@@@@ Start FanSeg %s, %d / %d" %
(file, pos, len(files)))
Extractor.extract_fanseg(output_dir)
# 复制到结果集
io.log_info("@@@@@ Start Move %s, %d / %d" % (file, pos, len(files)))
if not os.path.exists(target_dir):
os.mkdir(target_dir)
ts = get_time_str()
for f in os.listdir(output_dir):
src = os.path.join(output_dir, f)
dst = os.path.join(target_dir, "%s_%s" % (ts, f))
shutil.move(src, dst)
# 全部做完，删除该文件
io.log_info("@@@@@ Finish %s, %d / %d" % (file, pos, len(files)))
os.remove(os.path.join(extract_workspace, file))
os.rmdir(output_dir)
