Converter: added new mask modes: FAN-prd, FAN-dst

This commit is contained in:
iperov 2019-03-21 21:19:03 +04:00
parent 9849bcc1e5
commit c4f41a7e76
5 changed files with 11426 additions and 11214 deletions

View file

@ -2,6 +2,7 @@ import traceback
from .Converter import Converter
from facelib import LandmarksProcessor
from facelib import FaceType
from facelib import FANSegmentator
import cv2
import numpy as np
from utils import image_utils
@ -65,9 +66,15 @@ class ConverterMasked(Converter):
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 face_type == FaceType.FULL:
self.mask_mode = io.input_int ("Mask mode: (1) learned, (2) dst, (3) FAN-prd, (4) FAN-dst (?) help. Default - %d : " % (1) , 1, help_message="If you learned 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.")
else:
self.mask_mode = io.input_int ("Mask mode: (1) learned, (2) dst . Default - %d : " % (1) , 1)
self.use_predicted_mask = io.input_bool("Use predicted mask? (y/n skip:y) : ", True)
if self.mask_mode == 3 or self.mask_mode == 4:
self.fan_seg = None
if self.mode != 'raw':
self.erode_mask_modifier = base_erode_mask_modifier + np.clip ( io.input_int ("Choose erode mask modifier [-200..200] (skip:%d) : " % (default_erode_mask_modifier), default_erode_mask_modifier), -200, 200)
self.blur_mask_modifier = base_blur_mask_modifier + np.clip ( io.input_int ("Choose blur mask modifier [-200..200] (skip:%d) : " % (default_blur_mask_modifier), default_blur_mask_modifier), -200, 200)
@ -93,7 +100,9 @@ class ConverterMasked(Converter):
#override
def convert_face (self, img_bgr, img_face_landmarks, debug):
if (self.mask_mode == 3 or self.mask_mode == 4) and self.fan_seg == None:
self.fan_seg = FANSegmentator(256, FaceType.toString(FaceType.FULL) )
if self.over_res != 1:
img_bgr = cv2.resize ( img_bgr, ( img_bgr.shape[1]*self.over_res, img_bgr.shape[0]*self.over_res ) )
img_face_landmarks = img_face_landmarks*self.over_res
@ -120,9 +129,18 @@ class ConverterMasked(Converter):
prd_face_bgr = np.clip (predicted_bgra[:,:,0:3], 0, 1.0 )
prd_face_mask_a_0 = np.clip (predicted_bgra[:,:,3], 0.0, 1.0)
if not self.use_predicted_mask:
if self.mask_mode == 2: #dst
prd_face_mask_a_0 = predictor_input_mask_a_0
elif self.mask_mode == 3: #FAN-prd
prd_face_bgr_256 = cv2.resize (prd_face_bgr, (256,256) )
prd_face_bgr_256_mask = self.fan_seg.extract_from_bgr( np.expand_dims(prd_face_bgr_256,0) ) [0]
prd_face_mask_a_0 = cv2.resize (prd_face_bgr_256_mask, (self.predictor_input_size, self.predictor_input_size))
elif self.mask_mode == 4: #FAN-dst
face_256_mat = LandmarksProcessor.get_transform_mat (img_face_landmarks, 256, face_type=FaceType.FULL)
dst_face_256_bgr = cv2.warpAffine(img_bgr, face_256_mat, (256, 256), flags=cv2.INTER_LANCZOS4 )
dst_face_256_mask = self.fan_seg.extract_from_bgr( np.expand_dims(dst_face_256_bgr,0) ) [0]
prd_face_mask_a_0 = cv2.resize (dst_face_256_mask, (self.predictor_input_size, self.predictor_input_size))
prd_face_mask_a_0[ prd_face_mask_a_0 < 0.001 ] = 0.0
prd_face_mask_a = np.expand_dims (prd_face_mask_a_0, axis=-1)

Binary file not shown.

File diff suppressed because one or more lines are too long

Binary file not shown.

View file

@ -8,16 +8,16 @@ from interact import interact as io
class FANSegmentator(object):
def __init__ (self, resolution, face_type_str, load_weights=True, weights_file_root=None, training=False):
exec( nnlib.import_all(), locals(), globals() )
self.model = FANSegmentator.BuildModel(resolution, ngf=32)
if weights_file_root:
weights_file_root = Path(weights_file_root)
else:
weights_file_root = Path(__file__).parent
self.weights_path = weights_file_root / ('FANSeg_%d_%s.h5' % (resolution, face_type_str) )
if load_weights:
self.model.load_weights (str(self.weights_path))
else:
@ -33,19 +33,19 @@ class FANSegmentator(object):
def __enter__(self):
return self
def __exit__(self, exc_type=None, exc_value=None, traceback=None):
return False #pass exception between __enter__ and __exit__ to outter level
def save_weights(self):
self.model.save_weights (str(self.weights_path))
def train_on_batch(self, inp, outp):
return self.model.train_on_batch(inp, outp)
def extract_from_bgr (self, input_image):
return np.clip ( (self.model.predict(input_image) + 1) / 2.0, 0, 1.0 )
@staticmethod
def BuildModel ( resolution, ngf=64):
exec( nnlib.import_all(), locals(), globals() )
@ -55,7 +55,7 @@ class FANSegmentator(object):
x = FANSegmentator.DecFlow(ngf=ngf)(x)
model = Model(inp,x)
return model
@staticmethod
def EncFlow(ngf=64, num_downs=4):
exec( nnlib.import_all(), locals(), globals() )
@ -67,19 +67,19 @@ class FANSegmentator(object):
def downscale (dim):
def func(x):
return LeakyReLU(0.1)(XNormalization(Conv2D(dim, kernel_size=5, strides=2, padding='same', kernel_initializer=RandomNormal(0, 0.02))(x)))
return func
def func(input):
return func
def func(input):
x = input
result = []
for i in range(num_downs):
x = downscale ( min(ngf*(2**i), ngf*8) )(x)
result += [x]
x = downscale ( min(ngf*(2**i), ngf*8) )(x)
result += [x]
return result
return func
@staticmethod
def DecFlow(output_nc=1, ngf=64, activation='tanh'):
exec (nnlib.import_all(), locals(), globals())
@ -87,23 +87,22 @@ class FANSegmentator(object):
use_bias = True
def XNormalization(x):
return InstanceNormalization (axis=3, gamma_initializer=RandomNormal(1., 0.02))(x)
def Conv2D (filters, kernel_size, strides=(1, 1), padding='valid', data_format=None, dilation_rate=(1, 1), activation=None, use_bias=use_bias, kernel_initializer=RandomNormal(0, 0.02), bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, bias_constraint=None):
return keras.layers.Conv2D( filters=filters, kernel_size=kernel_size, strides=strides, padding=padding, data_format=data_format, dilation_rate=dilation_rate, activation=activation, use_bias=use_bias, kernel_initializer=kernel_initializer, bias_initializer=bias_initializer, kernel_regularizer=kernel_regularizer, bias_regularizer=bias_regularizer, activity_regularizer=activity_regularizer, kernel_constraint=kernel_constraint, bias_constraint=bias_constraint )
def upscale (dim):
def func(x):
return SubpixelUpscaler()( LeakyReLU(0.1)(XNormalization(Conv2D(dim, kernel_size=3, strides=1, padding='same', kernel_initializer=RandomNormal(0, 0.02))(x))))
return func
return func
def func(input):
input_len = len(input)
x = input[input_len-1]
for i in range(input_len-1, -1, -1):
for i in range(input_len-1, -1, -1):
x = upscale( min(ngf* (2**i) *4, ngf*8 *4 ) )(x)
if i != 0:
x = Concatenate(axis=3)([ input[i-1] , x])
return Conv2D(output_nc, 3, 1, 'same', activation=activation)(x)
return func