mirror of
https://github.com/iperov/DeepFaceLab.git
synced 2025-08-20 13:33:24 -07:00
syntax fixes
This commit is contained in:
sinofis
parent
7233d54324
commit
65a3da435c
4 changed files with 23 additions and 22 deletions
|
|
@ -1,6 +1,8 @@
|
|||
import cv2
|
||||
import numpy as np
|
||||
from numpy import linalg as npla
|
||||
from random import random, shuffle, choice
|
||||
from scipy.stats import special_ortho_group
|
||||
import scipy as sp
|
||||
|
||||
def color_transfer_sot(src,trg, steps=10, batch_size=5, reg_sigmaXY=16.0, reg_sigmaV=5.0):
|
||||
|
|
@ -376,7 +378,7 @@ def color_augmentation(img):
|
|||
face = random_clahe(face)
|
||||
face = random_lab(face)
|
||||
img[:, :, :3] = face
|
||||
return img.astype('float32') / 255.0
|
||||
return np.clip(img.astype('float32') / 255.0, 0, 1)
|
||||
|
||||
|
||||
def random_lab(image):
|
||||
|
|
|
|||
|
|
@ -443,7 +443,7 @@ def get_image_mouth_mask (image_shape, image_landmarks):
|
|||
|
||||
image_landmarks = image_landmarks.astype(np.int)
|
||||
|
||||
cv2.fillConvexPoly( hull_mask, cv2.convexHull( image_landmarks[48, 60]), (1,) )
|
||||
cv2.fillConvexPoly( hull_mask, cv2.convexHull( image_landmarks[48:60]), (1,) )
|
||||
|
||||
dilate = h // 32
|
||||
hull_mask = cv2.dilate(hull_mask, cv2.getStructuringElement(cv2.MORPH_ELLIPSE,(dilate,dilate)), iterations = 1 )
|
||||
|
|
|
|||
|
|
@ -286,7 +286,7 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
|
|||
self.D_src_x2 = nn.PatchDiscriminator(patch_size=resolution//32, in_ch=input_ch, name="D_src_x2")
|
||||
self.model_filename_list += [ [self.D_src, 'D_src.npy'] ]
|
||||
self.model_filename_list += [ [self.D_src_x2, 'D_src_x2.npy'] ]
|
||||
elif:
|
||||
else:
|
||||
self.D_src = nn.UNetPatchDiscriminator(patch_size=resolution//16, in_ch=input_ch, name="D_src")
|
||||
self.model_filename_list += [ [self.D_src, 'D_src_v2.npy'] ]
|
||||
|
||||
|
|
@ -315,7 +315,7 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
|
|||
if gan_old:
|
||||
self.D_src_dst_opt.initialize_variables ( self.D_src.get_weights()+self.D_src_x2.get_weights(), vars_on_cpu=optimizer_vars_on_cpu, lr_dropout_on_cpu=self.options['lr_dropout']=='cpu')
|
||||
self.model_filename_list += [ (self.D_src_dst_opt, 'D_src_dst_opt.npy') ]
|
||||
elif:
|
||||
else:
|
||||
self.D_src_dst_opt.initialize_variables ( self.D_src.get_weights(), vars_on_cpu=optimizer_vars_on_cpu, lr_dropout_on_cpu=self.options['lr_dropout']=='cpu')#+self.D_src_x2.get_weights()
|
||||
self.model_filename_list += [ (self.D_src_dst_opt, 'D_src_v2_opt.npy') ]
|
||||
|
||||
|
|
@ -485,16 +485,16 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
|
|||
if gan_power != 0:
|
||||
if gan_old:
|
||||
gpu_pred_src_src_d = self.D_src(gpu_pred_src_src_masked_opt)
|
||||
|
||||
gpu_pred_src_src_d_ones = tf.ones_like (gpu_pred_src_src_d) gpu_pred_src_src_d_ones = tf.ones_like (gpu_pred_src_src_d)
|
||||
gpu_pred_src_src_d_zeros = tf.zeros_like(gpu_pred_src_src_d) gpu_pred_src_src_d_zeros = tf.zeros_like(gpu_pred_src_src_d)
|
||||
|
||||
gpu_pred_src_src_d_ones = tf.ones_like (gpu_pred_src_src_d)
|
||||
gpu_pred_src_src_d_zeros = tf.zeros_like(gpu_pred_src_src_d)
|
||||
gpu_target_src_d = self.D_src(gpu_target_src_masked_opt)
|
||||
gpu_target_src_d_ones = tf.ones_like(gpu_target_src_d)
|
||||
|
||||
gpu_pred_src_src_x2_d = self.D_src_x2(gpu_pred_src_src_masked_opt) gpu_pred_src_src_d2_ones = tf.ones_like (gpu_pred_src_src_d2)
|
||||
gpu_pred_src_src_x2_d_ones = tf.ones_like (gpu_pred_src_src_x2_d) gpu_pred_src_src_d2_zeros = tf.zeros_like(gpu_pred_src_src_d2)
|
||||
gpu_pred_src_src_x2_d = self.D_src_x2(gpu_pred_src_src_masked_opt)
|
||||
gpu_pred_src_src_x2_d_ones = tf.ones_like (gpu_pred_src_src_x2_d)
|
||||
gpu_pred_src_src_x2_d_zeros = tf.zeros_like(gpu_pred_src_src_x2_d)
|
||||
gpu_target_src_x2_d = self.D_src_x2(gpu_target_src_masked_opt) gpu_target_src_d, \
|
||||
gpu_target_src_x2_d = self.D_src_x2(gpu_target_src_masked_opt)
|
||||
gpu_target_src_x2_d_ones = tf.ones_like(gpu_target_src_x2_d)
|
||||
|
||||
gpu_D_src_dst_loss = (DLoss(gpu_target_src_d_ones , gpu_target_src_d) + \
|
||||
|
|
@ -507,7 +507,7 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
|
|||
gpu_G_loss += 0.5*gan_power*( DLoss(gpu_pred_src_src_d_ones,
|
||||
gpu_pred_src_src_d) + DLoss(gpu_pred_src_src_x2_d_ones, gpu_pred_src_src_x2_d))
|
||||
|
||||
elif:
|
||||
else:
|
||||
gpu_pred_src_src_d, \
|
||||
gpu_pred_src_src_d2 = self.D_src(gpu_pred_src_src_masked_opt)
|
||||
|
||||
|
|
@ -648,6 +648,10 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
|
|||
if ct_mode is not None:
|
||||
src_generators_count = int(src_generators_count * 1.5)
|
||||
|
||||
fs_aug = None
|
||||
if ct_mode == 'fs-aug':
|
||||
fs_aug = 'fs-aug'
|
||||
|
||||
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(),
|
||||
sample_process_options=SampleProcessor.Options(random_flip=self.random_flip),
|
||||
|
|
@ -658,9 +662,6 @@ Examples: df, liae, df-d, df-ud, liae-ud, ...
|
|||
uniform_yaw_distribution=self.options['uniform_yaw'] or self.pretrain,
|
||||
generators_count=src_generators_count ),
|
||||
|
||||
fs_aug = None
|
||||
if ct_mode == 'fs-aug':
|
||||
fs_aug = 'fs-aug'
|
||||
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),
|
||||
output_sample_types = [ {'sample_type': SampleProcessor.SampleType.FACE_IMAGE,'warp':random_warp, 'transform':True, 'channel_type' : SampleProcessor.ChannelType.BGR, 'ct_mode': fs_aug, 'face_type':self.face_type, 'data_format':nn.data_format, 'resolution': resolution},
|
||||
|
|
|
|||
|
|
@ -72,13 +72,15 @@ class SampleProcessor(object):
|
|||
eyes_mask = LandmarksProcessor.get_image_eye_mask (sample_bgr.shape, sample_landmarks)
|
||||
# set eye masks to 1-2
|
||||
clip = np.clip(eyes_mask, 0, 1)
|
||||
return a[a > 0.1] += 1
|
||||
clip[clip > 0.1] += 1
|
||||
return clip
|
||||
|
||||
def get_mouth_mask():
|
||||
mouth_mask = LandmarksProcessor.get_image_mouth_mask (sample_bgr.shape, sample_landmarks)
|
||||
# set eye masks to 2-3
|
||||
clip = np.clip(mouth_mask, 0, 1)
|
||||
return a[a > 0.1] += 2
|
||||
clip[clip > 0.1] += 2
|
||||
return clip
|
||||
|
||||
is_face_sample = sample_landmarks is not None
|
||||
|
||||
|
|
@ -200,18 +202,14 @@ class SampleProcessor(object):
|
|||
if ct_mode is not None and ct_sample is not None or ct_mode == 'fs-aug':
|
||||
if 'fs-aug':
|
||||
img = imagelib.color_augmentation(img)
|
||||
elif:
|
||||
else:
|
||||
if ct_sample_bgr is None:
|
||||
ct_sample_bgr = ct_sample.load_bgr()
|
||||
img = imagelib.color_transfer (ct_mode, img, cv2.resize( ct_sample_bgr, (resolution,resolution), interpolation=cv2.INTER_LINEAR ) )
|
||||
|
||||
|
||||
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)
|
||||
|
||||
if motion_blur is not None:
|
||||
random_mask = sd.random_circle_faded ([resolution,resolution], rnd_state=np.random.RandomState (sample_rnd_seed+2)) if random_circle_mask else None
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue