mirror of
https://github.com/iperov/DeepFaceLab.git
synced 2025-08-20 21:43:21 -07:00
New script:
5.XSeg) data_dst/src mask for XSeg trainer - fetch.bat Copies faces containing XSeg polygons to aligned_xseg\ dir. Useful only if you want to collect labeled faces and reuse them in other fakes. Now you can use trained XSeg mask in the SAEHD training process. It’s mean default ‘full_face’ mask obtained from landmarks will be replaced with the mask obtained from the trained XSeg model. use 5.XSeg.optional) trained mask for data_dst/data_src - apply.bat 5.XSeg.optional) trained mask for data_dst/data_src - remove.bat Normally you don’t need it. You can use it, if you want to use ‘face_style’ and ‘bg_style’ with obstructions. XSeg trainer : now you can choose type of face XSeg trainer : now you can restart training in “override settings” Merger: XSeg-* modes now can be used with all types of faces. Therefore old MaskEditor, FANSEG models, and FAN-x modes have been removed, because the new XSeg solution is better, simpler and more convenient, which costs only 1 hour of manual masking for regular deepfake.
This commit is contained in:
Colombo
parent
e5bad483ca
commit
6d3607a13d
30 changed files with 279 additions and 1520 deletions
Binary file not shown.
|
|
@ -9,7 +9,6 @@ import numpy.linalg as npla
|
|||
from core import imagelib
|
||||
from core import mathlib
|
||||
from facelib import FaceType
|
||||
from core.imagelib import IEPolys
|
||||
from core.mathlib.umeyama import umeyama
|
||||
|
||||
landmarks_2D = np.array([
|
||||
|
|
@ -374,7 +373,7 @@ def expand_eyebrows(lmrks, eyebrows_expand_mod=1.0):
|
|||
|
||||
|
||||
|
||||
def get_image_hull_mask (image_shape, image_landmarks, eyebrows_expand_mod=1.0, ie_polys=None ):
|
||||
def get_image_hull_mask (image_shape, image_landmarks, eyebrows_expand_mod=1.0 ):
|
||||
hull_mask = np.zeros(image_shape[0:2]+(1,),dtype=np.float32)
|
||||
|
||||
lmrks = expand_eyebrows(image_landmarks, eyebrows_expand_mod)
|
||||
|
|
@ -393,9 +392,6 @@ def get_image_hull_mask (image_shape, image_landmarks, eyebrows_expand_mod=1.0,
|
|||
merged = np.concatenate(item)
|
||||
cv2.fillConvexPoly(hull_mask, cv2.convexHull(merged), (1,) )
|
||||
|
||||
if ie_polys is not None:
|
||||
ie_polys.overlay_mask(hull_mask)
|
||||
|
||||
return hull_mask
|
||||
|
||||
def get_image_eye_mask (image_shape, image_landmarks):
|
||||
|
|
@ -647,13 +643,13 @@ def mirror_landmarks (landmarks, val):
|
|||
result[:,0] = val - result[:,0] - 1
|
||||
return result
|
||||
|
||||
def get_face_struct_mask (image_shape, image_landmarks, eyebrows_expand_mod=1.0, ie_polys=None, color=(1,) ):
|
||||
def get_face_struct_mask (image_shape, image_landmarks, eyebrows_expand_mod=1.0, color=(1,) ):
|
||||
mask = np.zeros(image_shape[0:2]+( len(color),),dtype=np.float32)
|
||||
lmrks = expand_eyebrows(image_landmarks, eyebrows_expand_mod)
|
||||
draw_landmarks (mask, image_landmarks, color=color, draw_circles=False, thickness=2, ie_polys=ie_polys)
|
||||
draw_landmarks (mask, image_landmarks, color=color, draw_circles=False, thickness=2)
|
||||
return mask
|
||||
|
||||
def draw_landmarks (image, image_landmarks, color=(0,255,0), draw_circles=True, thickness=1, transparent_mask=False, ie_polys=None):
|
||||
def draw_landmarks (image, image_landmarks, color=(0,255,0), draw_circles=True, thickness=1, transparent_mask=False):
|
||||
if len(image_landmarks) != 68:
|
||||
raise Exception('get_image_eye_mask works only with 68 landmarks')
|
||||
|
||||
|
|
@ -683,11 +679,11 @@ def draw_landmarks (image, image_landmarks, color=(0,255,0), draw_circles=True,
|
|||
cv2.circle(image, (x, y), 2, color, lineType=cv2.LINE_AA)
|
||||
|
||||
if transparent_mask:
|
||||
mask = get_image_hull_mask (image.shape, image_landmarks, ie_polys=ie_polys)
|
||||
mask = get_image_hull_mask (image.shape, image_landmarks)
|
||||
image[...] = ( image * (1-mask) + image * mask / 2 )[...]
|
||||
|
||||
def draw_rect_landmarks (image, rect, image_landmarks, face_type, face_size=256, transparent_mask=False, ie_polys=None, landmarks_color=(0,255,0)):
|
||||
draw_landmarks(image, image_landmarks, color=landmarks_color, transparent_mask=transparent_mask, ie_polys=ie_polys)
|
||||
def draw_rect_landmarks (image, rect, image_landmarks, face_type, face_size=256, transparent_mask=False, landmarks_color=(0,255,0)):
|
||||
draw_landmarks(image, image_landmarks, color=landmarks_color, transparent_mask=transparent_mask)
|
||||
imagelib.draw_rect (image, rect, (255,0,0), 2 )
|
||||
|
||||
image_to_face_mat = get_transform_mat (image_landmarks, face_size, face_type)
|
||||
|
|
|
|||
|
|
@ -1,139 +0,0 @@
|
|||
import os
|
||||
import pickle
|
||||
from functools import partial
|
||||
from pathlib import Path
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
|
||||
from core.interact import interact as io
|
||||
from core.leras import nn
|
||||
|
||||
class TernausNet(object):
|
||||
VERSION = 1
|
||||
|
||||
def __init__ (self, name, resolution, load_weights=True, weights_file_root=None, training=False, place_model_on_cpu=False, run_on_cpu=False, optimizer=None, data_format="NHWC"):
|
||||
nn.initialize(data_format=data_format)
|
||||
tf = nn.tf
|
||||
|
||||
if weights_file_root is not None:
|
||||
weights_file_root = Path(weights_file_root)
|
||||
else:
|
||||
weights_file_root = Path(__file__).parent
|
||||
self.weights_file_root = weights_file_root
|
||||
|
||||
with tf.device ('/CPU:0'):
|
||||
#Place holders on CPU
|
||||
self.input_t = tf.placeholder (nn.floatx, nn.get4Dshape(resolution,resolution,3) )
|
||||
self.target_t = tf.placeholder (nn.floatx, nn.get4Dshape(resolution,resolution,1) )
|
||||
|
||||
# Initializing model classes
|
||||
with tf.device ('/CPU:0' if place_model_on_cpu else '/GPU:0'):
|
||||
self.net = nn.Ternaus(3, 64, name='Ternaus')
|
||||
self.net_weights = self.net.get_weights()
|
||||
|
||||
model_name = f'{name}_{resolution}'
|
||||
|
||||
self.model_filename_list = [ [self.net, f'{model_name}.npy'] ]
|
||||
|
||||
if training:
|
||||
if optimizer is None:
|
||||
raise ValueError("Optimizer should be provided for traning mode.")
|
||||
|
||||
self.opt = optimizer
|
||||
self.opt.initialize_variables (self.net_weights, vars_on_cpu=place_model_on_cpu)
|
||||
self.model_filename_list += [ [self.opt, f'{model_name}_opt.npy' ] ]
|
||||
else:
|
||||
with tf.device ('/CPU:0' if run_on_cpu else '/GPU:0'):
|
||||
_, pred = self.net([self.input_t])
|
||||
|
||||
def net_run(input_np):
|
||||
return nn.tf_sess.run ( [pred], feed_dict={self.input_t :input_np})[0]
|
||||
self.net_run = net_run
|
||||
|
||||
# Loading/initializing all models/optimizers weights
|
||||
for model, filename in self.model_filename_list:
|
||||
do_init = not load_weights
|
||||
|
||||
if not do_init:
|
||||
do_init = not model.load_weights( self.weights_file_root / filename )
|
||||
|
||||
if do_init:
|
||||
model.init_weights()
|
||||
if model == self.net:
|
||||
try:
|
||||
with open( Path(__file__).parent / 'vgg11_enc_weights.npy', 'rb' ) as f:
|
||||
d = pickle.loads (f.read())
|
||||
|
||||
for i in [0,3,6,8,11,13,16,18]:
|
||||
model.get_layer_by_name ('features_%d' % i).set_weights ( d['features.%d' % i] )
|
||||
except:
|
||||
io.log_err("Unable to load VGG11 pretrained weights from vgg11_enc_weights.npy")
|
||||
|
||||
def save_weights(self):
|
||||
for model, filename in io.progress_bar_generator(self.model_filename_list, "Saving", leave=False):
|
||||
model.save_weights( self.weights_file_root / filename )
|
||||
|
||||
def extract (self, input_image):
|
||||
input_shape_len = len(input_image.shape)
|
||||
if input_shape_len == 3:
|
||||
input_image = input_image[None,...]
|
||||
|
||||
result = np.clip ( self.net_run(input_image), 0, 1.0 )
|
||||
result[result < 0.1] = 0 #get rid of noise
|
||||
|
||||
if input_shape_len == 3:
|
||||
result = result[0]
|
||||
|
||||
return result
|
||||
|
||||
"""
|
||||
if load_weights:
|
||||
self.net.load_weights (self.weights_path)
|
||||
else:
|
||||
self.net.init_weights()
|
||||
|
||||
if load_weights:
|
||||
self.opt.load_weights (self.opt_path)
|
||||
else:
|
||||
self.opt.init_weights()
|
||||
"""
|
||||
"""
|
||||
if training:
|
||||
try:
|
||||
with open( Path(__file__).parent / 'vgg11_enc_weights.npy', 'rb' ) as f:
|
||||
d = pickle.loads (f.read())
|
||||
|
||||
for i in [0,3,6,8,11,13,16,18]:
|
||||
s = 'features.%d' % i
|
||||
|
||||
self.model.get_layer (s).set_weights ( d[s] )
|
||||
except:
|
||||
io.log_err("Unable to load VGG11 pretrained weights from vgg11_enc_weights.npy")
|
||||
|
||||
conv_weights_list = []
|
||||
for layer in self.model.layers:
|
||||
if 'CA.' in layer.name:
|
||||
conv_weights_list += [layer.weights[0]] #Conv2D kernel_weights
|
||||
CAInitializerMP ( conv_weights_list )
|
||||
"""
|
||||
|
||||
|
||||
|
||||
"""
|
||||
if training:
|
||||
inp_t = Input ( (resolution, resolution, 3) )
|
||||
real_t = Input ( (resolution, resolution, 1) )
|
||||
out_t = self.model(inp_t)
|
||||
|
||||
loss = K.mean(10*K.binary_crossentropy(real_t,out_t) )
|
||||
|
||||
out_t_diff1 = out_t[:, 1:, :, :] - out_t[:, :-1, :, :]
|
||||
out_t_diff2 = out_t[:, :, 1:, :] - out_t[:, :, :-1, :]
|
||||
|
||||
total_var_loss = K.mean( 0.1*K.abs(out_t_diff1), axis=[1, 2, 3] ) + K.mean( 0.1*K.abs(out_t_diff2), axis=[1, 2, 3] )
|
||||
|
||||
opt = Adam(lr=0.0001, beta_1=0.5, beta_2=0.999, tf_cpu_mode=2)
|
||||
|
||||
self.train_func = K.function ( [inp_t, real_t], [K.mean(loss)], opt.get_updates( [loss], self.model.trainable_weights) )
|
||||
"""
|
||||
|
|
@ -14,20 +14,22 @@ class XSegNet(object):
|
|||
VERSION = 1
|
||||
|
||||
def __init__ (self, name,
|
||||
resolution,
|
||||
resolution=256,
|
||||
load_weights=True,
|
||||
weights_file_root=None,
|
||||
training=False,
|
||||
place_model_on_cpu=False,
|
||||
run_on_cpu=False,
|
||||
optimizer=None,
|
||||
data_format="NHWC"):
|
||||
|
||||
data_format="NHWC",
|
||||
raise_on_no_model_files=False):
|
||||
|
||||
self.resolution = resolution
|
||||
self.weights_file_root = Path(weights_file_root) if weights_file_root is not None else Path(__file__).parent
|
||||
|
||||
nn.initialize(data_format=data_format)
|
||||
tf = nn.tf
|
||||
|
||||
self.weights_file_root = Path(weights_file_root) if weights_file_root is not None else Path(__file__).parent
|
||||
|
||||
with tf.device ('/CPU:0'):
|
||||
#Place holders on CPU
|
||||
self.input_t = tf.placeholder (nn.floatx, nn.get4Dshape(resolution,resolution,3) )
|
||||
|
|
@ -62,11 +64,17 @@ class XSegNet(object):
|
|||
do_init = not load_weights
|
||||
|
||||
if not do_init:
|
||||
do_init = not model.load_weights( self.weights_file_root / filename )
|
||||
model_file_path = self.weights_file_root / filename
|
||||
do_init = not model.load_weights( model_file_path )
|
||||
if do_init and raise_on_no_model_files:
|
||||
raise Exception(f'{model_file_path} does not exists.')
|
||||
|
||||
if do_init:
|
||||
model.init_weights()
|
||||
|
||||
|
||||
def get_resolution(self):
|
||||
return self.resolution
|
||||
|
||||
def flow(self, x):
|
||||
return self.model(x)
|
||||
|
||||
|
|
@ -78,7 +86,7 @@ class XSegNet(object):
|
|||
model.save_weights( self.weights_file_root / filename )
|
||||
|
||||
def extract (self, input_image):
|
||||
input_shape_len = len(input_image.shape)
|
||||
input_shape_len = len(input_image.shape)
|
||||
if input_shape_len == 3:
|
||||
input_image = input_image[None,...]
|
||||
|
||||
|
|
|
|||
|
|
@ -2,5 +2,4 @@ from .FaceType import FaceType
|
|||
from .S3FDExtractor import S3FDExtractor
|
||||
from .FANExtractor import FANExtractor
|
||||
from .FaceEnhancer import FaceEnhancer
|
||||
from .TernausNet import TernausNet
|
||||
from .XSegNet import XSegNet
|
||||
Binary file not shown.
Loading…
Add table
Add a link
Reference in a new issue