github/DeepFaceLab
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLab.git synced 2025-08-20 05:23:22 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #145 from faceshiftlabs/feat/image-degradation-random-blur

Browse source 
Feat/image degradation random blur
This commit is contained in:
Jeremy Hummel 2021-05-23 20:04:51 -07:00 • committed by GitHub
commit b725ac164d
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 56 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

21
models/Model_SAEHD/Model.py
View file

@ -57,6 +57,9 @@ class SAEHDModel(ModelBase):
default_random_warp = self.options['random_warp'] = self.load_or_def_option('random_warp', True) default_random_warp = self.options['random_warp'] = self.load_or_def_option('random_warp', True)
default_random_downsample = self.options['random_downsample'] = self.load_or_def_option('random_downsample', False) default_random_downsample = self.options['random_downsample'] = self.load_or_def_option('random_downsample', False)
default_random_noise = self.options['random_noise'] = self.load_or_def_option('random_noise', False)
default_random_blur = self.options['random_blur'] = self.load_or_def_option('random_blur', False)
default_background_power = self.options['background_power'] = self.load_or_def_option('background_power', 0.0) default_background_power = self.options['background_power'] = self.load_or_def_option('background_power', 0.0)
default_true_face_power = self.options['true_face_power'] = self.load_or_def_option('true_face_power', 0.0) default_true_face_power = self.options['true_face_power'] = self.load_or_def_option('true_face_power', 0.0)
default_face_style_power = self.options['face_style_power'] = self.load_or_def_option('face_style_power', 0.0) default_face_style_power = self.options['face_style_power'] = self.load_or_def_option('face_style_power', 0.0)
@ -161,8 +164,8 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
self.options['random_warp'] = io.input_bool ("Enable random warp of samples", 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 and reduce subpixel shake for less amount of iterations.") self.options['random_warp'] = io.input_bool ("Enable random warp of samples", 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 and reduce subpixel shake for less amount of iterations.")
self.options['random_downsample'] = io.input_bool("Enable random downsample of samples", default_random_downsample, help_message="") self.options['random_downsample'] = io.input_bool("Enable random downsample of samples", default_random_downsample, help_message="")
# self.options['random_noise'] = io.input_bool("Enable random noise added to samples", False, help_message="") self.options['random_noise'] = io.input_bool("Enable random noise added to samples", default_random_noise, help_message="")
# self.options['random_blur'] = io.input_bool("Enable random blur of samples", False, help_message="") self.options['random_blur'] = io.input_bool("Enable random blur of samples", False, help_message="")
# self.options['random_jpeg'] = io.input_bool("Enable random jpeg compression of samples", False, help_message="") # self.options['random_jpeg'] = io.input_bool("Enable random jpeg compression of samples", False, help_message="")
self.options['gan_version'] = np.clip (io.input_int("GAN version", default_gan_version, add_info="2 or 3", help_message="Choose GAN version (v2: 7/16/2020, v3: 1/3/2021):"), 2, 3) self.options['gan_version'] = np.clip (io.input_int("GAN version", default_gan_version, add_info="2 or 3", help_message="Choose GAN version (v2: 7/16/2020, v3: 1/3/2021):"), 2, 3)
@ -751,7 +754,12 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
self.set_training_data_generators ([ self.set_training_data_generators ([
SampleGeneratorFace(training_data_src_path, random_ct_samples_path=random_ct_samples_path, debug=self.is_debug(), batch_size=self.get_batch_size(), SampleGeneratorFace(training_data_src_path, random_ct_samples_path=random_ct_samples_path, debug=self.is_debug(), batch_size=self.get_batch_size(),
sample_process_options=SampleProcessor.Options(random_flip=self.random_flip), sample_process_options=SampleProcessor.Options(random_flip=self.random_flip),
output_sample_types = [ {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':random_warp, 'random_downsample': self.options['random_downsample'], 'transform':True, 'channel_type' : channel_type, 'ct_mode': ct_mode, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution}, output_sample_types = [ {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':random_warp,
'random_downsample': self.options['random_downsample'],
'random_noise': self.options['random_noise'],
'random_blur': self.options['random_blur'],
'transform':True, 'channel_type' : channel_type, 'ct_mode': ct_mode,
'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution},
{'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':False , 'transform':True, 'channel_type' : channel_type, 'ct_mode': ct_mode, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution}, {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':False , 'transform':True, 'channel_type' : channel_type, 'ct_mode': ct_mode, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution},
{'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.FULL_FACE, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution}, {'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.FULL_FACE, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution},
{'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.FULL_FACE_EYES, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution}, {'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.FULL_FACE_EYES, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution},
@ -761,7 +769,12 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
SampleGeneratorFace(training_data_dst_path, debug=self.is_debug(), batch_size=self.get_batch_size(), SampleGeneratorFace(training_data_dst_path, debug=self.is_debug(), batch_size=self.get_batch_size(),
sample_process_options=SampleProcessor.Options(random_flip=self.random_flip), sample_process_options=SampleProcessor.Options(random_flip=self.random_flip),
output_sample_types = [ {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':random_warp, 'random_downsample': self.options['random_downsample'], 'transform':True, 'channel_type' : channel_type, 'ct_mode': fs_aug, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution}, output_sample_types = [ {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':random_warp,
'random_downsample': self.options['random_downsample'],
'random_noise': self.options['random_noise'],
'random_blur': self.options['random_blur'],
'transform':True, 'channel_type' : channel_type, 'ct_mode': fs_aug,
'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution},
{'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':False , 'transform':True, 'channel_type' : channel_type, 'ct_mode': fs_aug, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution}, {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':False , 'transform':True, 'channel_type' : channel_type, 'ct_mode': fs_aug, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution},
{'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.FULL_FACE, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution}, {'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.FULL_FACE, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution},
{'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.FULL_FACE_EYES, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution}, {'sample_type': SampleProcessor.SampleType.FACE_MASK, 'warp':False , 'transform':True, 'channel_type' : SampleProcessor.ChannelType.G, 'face_mask_type' : SampleProcessor.FaceMaskType.FULL_FACE_EYES, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution},

40
samplelib/SampleProcessor.py
View file

@ -7,7 +7,7 @@ import numpy as np
from core import imagelib from core import imagelib
from core.cv2ex import * from core.cv2ex import *
from core.imagelib import sd from core.imagelib import sd, LinearMotionBlur
from core.imagelib.color_transfer import random_lab_rotation from core.imagelib.color_transfer import random_lab_rotation
from facelib import FaceType, LandmarksProcessor from facelib import FaceType, LandmarksProcessor
@ -113,6 +113,8 @@ class SampleProcessor(object):
warp = opts.get('warp', False) warp = opts.get('warp', False)
transform = opts.get('transform', False) transform = opts.get('transform', False)
random_downsample = opts.get('random_downsample', False) random_downsample = opts.get('random_downsample', False)
random_noise = opts.get('random_noise', False)
random_blur = opts.get('random_blur', False)
motion_blur = opts.get('motion_blur', None) motion_blur = opts.get('motion_blur', None)
gaussian_blur = opts.get('gaussian_blur', None) gaussian_blur = opts.get('gaussian_blur', None)
random_bilinear_resize = opts.get('random_bilinear_resize', None) random_bilinear_resize = opts.get('random_bilinear_resize', None)
@ -220,6 +222,42 @@ class SampleProcessor(object):
img = cv2.resize(img, (down_res, down_res), interpolation=cv2.INTER_CUBIC) img = cv2.resize(img, (down_res, down_res), interpolation=cv2.INTER_CUBIC)
img = cv2.resize(img, (resolution, resolution), interpolation=cv2.INTER_CUBIC) img = cv2.resize(img, (resolution, resolution), interpolation=cv2.INTER_CUBIC)
# Apply random noise
if random_noise:
noise_type = np.random.choice(['gaussian', 'laplace', 'poisson'])
noise_scale = (20 * np.random.random() + 20)
if noise_type == 'gaussian':
noise = np.random.normal(scale=noise_scale, size=img.shape)
img += noise / 255.0
elif noise_type == 'laplace':
noise = np.random.laplace(scale=noise_scale, size=img.shape)
img += noise / 255.0
elif noise_type == 'poisson':
noise_lam = (15 * np.random.random() + 15)
noise = np.random.poisson(lam=noise_lam, size=img.shape)
img += noise / 255.0
# Apply random blur
if random_blur:
blur_type = np.random.choice(['motion', 'gaussian'])
if blur_type == 'motion':
blur_k = np.random.randint(10, 20)
blur_angle = 360 * np.random.random()
img = LinearMotionBlur(img, blur_k, blur_angle)
elif blur_type == 'gaussian':
blur_sigma = 5 * np.random.random() + 3
if blur_sigma < 5.0:
kernel_size = 2.9 * blur_sigma # 97% of weight
else:
kernel_size = 2.6 * blur_sigma # 95% of weight
kernel_size = int(kernel_size)
kernel_size = kernel_size + 1 if kernel_size % 2 == 0 else kernel_size
img = cv2.GaussianBlur(img, (kernel_size, kernel_size), blur_sigma)
img = imagelib.warp_by_params (params_per_resolution[resolution], img, warp, transform, can_flip=True, border_replicate=border_replicate) img = imagelib.warp_by_params (params_per_resolution[resolution], img, warp, transform, can_flip=True, border_replicate=border_replicate)
img = np.clip(img.astype(np.float32), 0, 1) img = np.clip(img.astype(np.float32), 0, 1)