def ConvertMaskedFace(cfg, frame_info, img_bgr_uint8, img_bgr,
img_face_landmarks):
#if debug:
# debugs = [img_bgr.copy()]
img_size = img_bgr.shape[1], img_bgr.shape[0]
img_face_mask_a = LandmarksProcessor.get_image_hull_mask(
img_bgr.shape, img_face_landmarks)
if cfg.mode == 'original':
if cfg.export_mask_alpha:
img_bgr = np.concatenate([img_bgr, img_face_mask_a], -1)
return img_bgr, img_face_mask_a
out_img = img_bgr.copy()
out_merging_mask = None
output_size = cfg.predictor_input_shape[0]
if cfg.super_resolution_mode != 0:
output_size *= 2
face_mat = LandmarksProcessor.get_transform_mat(img_face_landmarks,
output_size,
face_type=cfg.face_type)
face_output_mat = LandmarksProcessor.get_transform_mat(
img_face_landmarks,
output_size,
face_type=cfg.face_type,
scale=1.0 + 0.01 * cfg.output_face_scale)
dst_face_bgr = cv2.warpAffine(img_bgr,
face_mat, (output_size, output_size),
flags=cv2.INTER_CUBIC)
dst_face_mask_a_0 = cv2.warpAffine(img_face_mask_a,
face_mat, (output_size, output_size),
flags=cv2.INTER_CUBIC)
predictor_input_bgr = cv2.resize(dst_face_bgr,
cfg.predictor_input_shape[0:2])
if cfg.predictor_masked:
prd_face_bgr, prd_face_mask_a_0 = cfg.predictor_func(
predictor_input_bgr)
prd_face_bgr = np.clip(prd_face_bgr, 0, 1.0)
prd_face_mask_a_0 = np.clip(prd_face_mask_a_0, 0.0, 1.0)
else:
predicted = cfg.predictor_func(predictor_input_bgr)
prd_face_bgr = np.clip(predicted, 0, 1.0)
prd_face_mask_a_0 = cv2.resize(dst_face_mask_a_0,
cfg.predictor_input_shape[0:2])
if cfg.super_resolution_mode:
#if debug:
# tmp = cv2.resize (prd_face_bgr, (output_size,output_size), cv2.INTER_CUBIC)
# debugs += [ np.clip( cv2.warpAffine( tmp, face_output_mat, img_size, img_bgr.copy(), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT ), 0, 1.0) ]
prd_face_bgr = cfg.superres_func(cfg.super_resolution_mode,
prd_face_bgr)
#if debug:
# debugs += [ np.clip( cv2.warpAffine( prd_face_bgr, face_output_mat, img_size, img_bgr.copy(), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT ), 0, 1.0) ]
if cfg.predictor_masked:
prd_face_mask_a_0 = cv2.resize(prd_face_mask_a_0,
(output_size, output_size),
cv2.INTER_CUBIC)
else:
prd_face_mask_a_0 = cv2.resize(dst_face_mask_a_0,
(output_size, output_size),
cv2.INTER_CUBIC)
if cfg.mask_mode == 2: #dst
prd_face_mask_a_0 = cv2.resize(dst_face_mask_a_0,
(output_size, output_size),
cv2.INTER_CUBIC)
elif cfg.mask_mode >= 3 and cfg.mask_mode <= 7:
if cfg.mask_mode == 3 or cfg.mask_mode == 5 or cfg.mask_mode == 6:
prd_face_fanseg_bgr = cv2.resize(prd_face_bgr,
(cfg.fanseg_input_size, ) * 2)
prd_face_fanseg_mask = cfg.fanseg_extract_func(
FaceType.FULL, prd_face_fanseg_bgr)
FAN_prd_face_mask_a_0 = cv2.resize(prd_face_fanseg_mask,
(output_size, output_size),
cv2.INTER_CUBIC)
if cfg.mask_mode >= 4 or cfg.mask_mode <= 7:
full_face_fanseg_mat = LandmarksProcessor.get_transform_mat(
img_face_landmarks,
cfg.fanseg_input_size,
face_type=FaceType.FULL)
dst_face_fanseg_bgr = cv2.warpAffine(img_bgr,
full_face_fanseg_mat,
(cfg.fanseg_input_size, ) * 2,
flags=cv2.INTER_CUBIC)
dst_face_fanseg_mask = cfg.fanseg_extract_func(
FaceType.FULL, dst_face_fanseg_bgr)
if cfg.face_type == FaceType.FULL:
FAN_dst_face_mask_a_0 = cv2.resize(dst_face_fanseg_mask,
(output_size, output_size),
cv2.INTER_CUBIC)
elif cfg.face_type == FaceType.HALF:
half_face_fanseg_mat = LandmarksProcessor.get_transform_mat(
img_face_landmarks,
cfg.fanseg_input_size,
face_type=FaceType.HALF)
fanseg_rect_corner_pts = np.array(
[[0, 0], [cfg.fanseg_input_size - 1, 0],
[0, cfg.fanseg_input_size - 1]],
dtype=np.float32)
a = LandmarksProcessor.transform_points(fanseg_rect_corner_pts,
half_face_fanseg_mat,
invert=True)
b = LandmarksProcessor.transform_points(
a, full_face_fanseg_mat)
m = cv2.getAffineTransform(b, fanseg_rect_corner_pts)
FAN_dst_face_mask_a_0 = cv2.warpAffine(
dst_face_fanseg_mask,
m, (cfg.fanseg_input_size, ) * 2,
flags=cv2.INTER_CUBIC)
FAN_dst_face_mask_a_0 = cv2.resize(FAN_dst_face_mask_a_0,
(output_size, output_size),
cv2.INTER_CUBIC)
else:
raise ValueError("cfg.face_type unsupported")
if cfg.mask_mode == 3: #FAN-prd
prd_face_mask_a_0 = FAN_prd_face_mask_a_0
elif cfg.mask_mode == 4: #FAN-dst
prd_face_mask_a_0 = FAN_dst_face_mask_a_0
elif cfg.mask_mode == 5:
prd_face_mask_a_0 = FAN_prd_face_mask_a_0 * FAN_dst_face_mask_a_0
elif cfg.mask_mode == 6:
prd_face_mask_a_0 = prd_face_mask_a_0 * FAN_prd_face_mask_a_0 * FAN_dst_face_mask_a_0
elif cfg.mask_mode == 7:
prd_face_mask_a_0 = prd_face_mask_a_0 * FAN_dst_face_mask_a_0
prd_face_mask_a_0[prd_face_mask_a_0 < 0.001] = 0.0
prd_face_mask_a = prd_face_mask_a_0[..., np.newaxis]
prd_face_mask_aaa = np.repeat(prd_face_mask_a, (3, ), axis=-1)
img_face_mask_aaa = cv2.warpAffine(prd_face_mask_aaa,
face_output_mat,
img_size,
np.zeros(img_bgr.shape,
dtype=np.float32),
flags=cv2.WARP_INVERSE_MAP
| cv2.INTER_CUBIC)
img_face_mask_aaa = np.clip(img_face_mask_aaa, 0.0, 1.0)
img_face_mask_aaa[img_face_mask_aaa <= 0.1] = 0.0 #get rid of noise
#if debug:
# debugs += [img_face_mask_aaa.copy()]
if 'raw' in cfg.mode:
face_corner_pts = np.array(
[[0, 0], [output_size - 1, 0], [output_size - 1, output_size - 1],
[0, output_size - 1]],
dtype=np.float32)
square_mask = np.zeros(img_bgr.shape, dtype=np.float32)
cv2.fillConvexPoly(square_mask, \
LandmarksProcessor.transform_points (face_corner_pts, face_output_mat, invert=True ).astype(np.int), \
(1,1,1) )
if cfg.mode == 'raw-rgb':
out_merging_mask = square_mask
if cfg.mode == 'raw-rgb' or cfg.mode == 'raw-rgb-mask':
out_img = cv2.warpAffine(prd_face_bgr, face_output_mat, img_size,
out_img,
cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC,
cv2.BORDER_TRANSPARENT)
if cfg.mode == 'raw-rgb-mask':
out_img = np.concatenate(
[out_img,
np.expand_dims(img_face_mask_aaa[:, :, 0], -1)], -1)
out_merging_mask = square_mask
elif cfg.mode == 'raw-mask-only':
out_img = img_face_mask_aaa
out_merging_mask = img_face_mask_aaa
elif cfg.mode == 'raw-predicted-only':
out_img = cv2.warpAffine(prd_face_bgr, face_output_mat, img_size,
np.zeros(img_bgr.shape, dtype=np.float32),
cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC,
cv2.BORDER_TRANSPARENT)
out_merging_mask = square_mask
out_img = np.clip(out_img, 0.0, 1.0)
else:
#averaging [lenx, leny, maskx, masky] by grayscale gradients of upscaled mask
ar = []
for i in range(1, 10):
maxregion = np.argwhere(img_face_mask_aaa > i / 10.0)
if maxregion.size != 0:
miny, minx = maxregion.min(axis=0)[:2]
maxy, maxx = maxregion.max(axis=0)[:2]
lenx = maxx - minx
leny = maxy - miny
if min(lenx, leny) >= 4:
ar += [[lenx, leny]]
if len(ar) > 0:
lenx, leny = np.mean(ar, axis=0)
lowest_len = min(lenx, leny)
#if debug:
# io.log_info ("lenx/leny:(%d/%d) " % (lenx, leny ) )
# io.log_info ("lowest_len = %f" % (lowest_len) )
if cfg.erode_mask_modifier != 0:
ero = int(lowest_len * (0.126 - lowest_len * 0.00004551365) *
0.01 * cfg.erode_mask_modifier)
#if debug:
# io.log_info ("erode_size = %d" % (ero) )
if ero > 0:
img_face_mask_aaa = cv2.erode(img_face_mask_aaa,
cv2.getStructuringElement(
cv2.MORPH_ELLIPSE,
(ero, ero)),
iterations=1)
elif ero < 0:
img_face_mask_aaa = cv2.dilate(img_face_mask_aaa,
cv2.getStructuringElement(
cv2.MORPH_ELLIPSE,
(-ero, -ero)),
iterations=1)
if cfg.clip_hborder_mask_per > 0: #clip hborder before blur
prd_hborder_rect_mask_a = np.ones(prd_face_mask_a.shape,
dtype=np.float32)
prd_border_size = int(prd_hborder_rect_mask_a.shape[1] *
cfg.clip_hborder_mask_per)
prd_hborder_rect_mask_a[:, 0:prd_border_size, :] = 0
prd_hborder_rect_mask_a[:, -prd_border_size:, :] = 0
prd_hborder_rect_mask_a[-prd_border_size:, :, :] = 0
prd_hborder_rect_mask_a = np.expand_dims(
cv2.blur(prd_hborder_rect_mask_a,
(prd_border_size, prd_border_size)), -1)
img_prd_hborder_rect_mask_a = cv2.warpAffine(
prd_hborder_rect_mask_a, face_output_mat, img_size,
np.zeros(img_bgr.shape, dtype=np.float32),
cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC)
img_prd_hborder_rect_mask_a = np.expand_dims(
img_prd_hborder_rect_mask_a, -1)
img_face_mask_aaa *= img_prd_hborder_rect_mask_a
img_face_mask_aaa = np.clip(img_face_mask_aaa, 0, 1.0)
#if debug:
# debugs += [img_face_mask_aaa.copy()]
if cfg.blur_mask_modifier > 0:
blur = int(lowest_len * 0.10 * 0.01 * cfg.blur_mask_modifier)
#if debug:
# io.log_info ("blur_size = %d" % (blur) )
if blur > 0:
img_face_mask_aaa = cv2.blur(img_face_mask_aaa,
(blur, blur))
img_face_mask_aaa = np.clip(img_face_mask_aaa, 0, 1.0)
#if debug:
# debugs += [img_face_mask_aaa.copy()]
if 'seamless' not in cfg.mode and cfg.color_transfer_mode != 0:
if cfg.color_transfer_mode == 1:
#if debug:
# debugs += [ np.clip( cv2.warpAffine( prd_face_bgr, face_output_mat, img_size, np.zeros(img_bgr.shape, dtype=np.float32), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT ), 0, 1.0) ]
prd_face_bgr = imagelib.reinhard_color_transfer(
np.clip((prd_face_bgr * 255).astype(np.uint8), 0, 255),
np.clip((dst_face_bgr * 255).astype(np.uint8), 0, 255),
source_mask=prd_face_mask_a,
target_mask=prd_face_mask_a)
prd_face_bgr = np.clip(
prd_face_bgr.astype(np.float32) / 255.0, 0.0, 1.0)
#if debug:
# debugs += [ np.clip( cv2.warpAffine( prd_face_bgr, face_output_mat, img_size, np.zeros(img_bgr.shape, dtype=np.float32), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT ), 0, 1.0) ]
elif cfg.color_transfer_mode == 2:
#if debug:
# debugs += [ np.clip( cv2.warpAffine( prd_face_bgr, face_output_mat, img_size, np.zeros(img_bgr.shape, dtype=np.float32), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT ), 0, 1.0) ]
prd_face_bgr = imagelib.linear_color_transfer(
prd_face_bgr, dst_face_bgr)
prd_face_bgr = np.clip(prd_face_bgr, 0.0, 1.0)
#if debug:
# debugs += [ np.clip( cv2.warpAffine( prd_face_bgr, face_output_mat, img_size, np.zeros(img_bgr.shape, dtype=np.float32), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT ), 0, 1.0) ]
if cfg.mode == 'hist-match-bw':
prd_face_bgr = cv2.cvtColor(prd_face_bgr, cv2.COLOR_BGR2GRAY)
prd_face_bgr = np.repeat(np.expand_dims(prd_face_bgr, -1),
(3, ), -1)
if cfg.mode == 'hist-match' or cfg.mode == 'hist-match-bw':
#if debug:
# debugs += [ cv2.warpAffine( prd_face_bgr, face_output_mat, img_size, np.zeros(img_bgr.shape, dtype=np.float32), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT ) ]
hist_mask_a = np.ones(prd_face_bgr.shape[:2] + (1, ),
dtype=np.float32)
if cfg.masked_hist_match:
hist_mask_a *= prd_face_mask_a
white = (1.0 - hist_mask_a) * np.ones(
prd_face_bgr.shape[:2] + (1, ), dtype=np.float32)
hist_match_1 = prd_face_bgr * hist_mask_a + white
hist_match_1[hist_match_1 > 1.0] = 1.0
hist_match_2 = dst_face_bgr * hist_mask_a + white
hist_match_2[hist_match_1 > 1.0] = 1.0
prd_face_bgr = imagelib.color_hist_match(
hist_match_1, hist_match_2, cfg.hist_match_threshold)
#if cfg.masked_hist_match:
# prd_face_bgr -= white
if cfg.mode == 'hist-match-bw':
prd_face_bgr = prd_face_bgr.astype(dtype=np.float32)
out_img = cv2.warpAffine(prd_face_bgr, face_output_mat, img_size,
out_img,
cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC,
cv2.BORDER_TRANSPARENT)
out_img = np.clip(out_img, 0.0, 1.0)
#if debug:
# debugs += [out_img.copy()]
if cfg.mode == 'overlay':
pass
if 'seamless' in cfg.mode:
#mask used for cv2.seamlessClone
img_face_seamless_mask_a = None
img_face_mask_a = img_face_mask_aaa[..., 0:1]
for i in range(1, 10):
a = img_face_mask_a > i / 10.0
if len(np.argwhere(a)) == 0:
continue
img_face_seamless_mask_a = img_face_mask_aaa[...,
0:1].copy()
img_face_seamless_mask_a[a] = 1.0
img_face_seamless_mask_a[img_face_seamless_mask_a <= i /
10.0] = 0.0
break
try:
#calc same bounding rect and center point as in cv2.seamlessClone to prevent jittering (not flickering)
l, t, w, h = cv2.boundingRect(
(img_face_seamless_mask_a * 255).astype(np.uint8))
s_maskx, s_masky = int(l + w / 2), int(t + h / 2)
out_img = cv2.seamlessClone(
(out_img * 255).astype(np.uint8), img_bgr_uint8,
(img_face_seamless_mask_a * 255).astype(np.uint8),
(s_maskx, s_masky), cv2.NORMAL_CLONE)
out_img = out_img.astype(dtype=np.float32) / 255.0
except Exception as e:
#seamlessClone may fail in some cases
e_str = traceback.format_exc()
if 'MemoryError' in e_str:
raise Exception(
"Seamless fail: " + e_str
) #reraise MemoryError in order to reprocess this data by other processes
else:
print("Seamless fail: " + e_str)
#if debug:
# debugs += [out_img.copy()]
out_img = img_bgr * (1 - img_face_mask_aaa) + (out_img *
img_face_mask_aaa)
out_face_bgr = cv2.warpAffine(out_img, face_mat,
(output_size, output_size))
if 'seamless' in cfg.mode and cfg.color_transfer_mode != 0:
if cfg.color_transfer_mode == 1:
#if debug:
# debugs += [ np.clip( cv2.warpAffine( out_face_bgr, face_output_mat, img_size, np.zeros(img_bgr.shape, dtype=np.float32), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT ), 0, 1.0) ]
face_mask_aaa = cv2.warpAffine(img_face_mask_aaa, face_mat,
(output_size, output_size))
out_face_bgr = imagelib.reinhard_color_transfer(
np.clip((out_face_bgr * 255).astype(np.uint8), 0, 255),
np.clip((dst_face_bgr * 255).astype(np.uint8), 0, 255),
source_mask=face_mask_aaa,
target_mask=face_mask_aaa)
out_face_bgr = np.clip(
out_face_bgr.astype(np.float32) / 255.0, 0.0, 1.0)
#if debug:
# debugs += [ np.clip( cv2.warpAffine( out_face_bgr, face_output_mat, img_size, np.zeros(img_bgr.shape, dtype=np.float32), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT ), 0, 1.0) ]
elif cfg.color_transfer_mode == 2:
#if debug:
# debugs += [ np.clip( cv2.warpAffine( out_face_bgr, face_output_mat, img_size, np.zeros(img_bgr.shape, dtype=np.float32), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT ), 0, 1.0) ]
out_face_bgr = imagelib.linear_color_transfer(
out_face_bgr, dst_face_bgr)
out_face_bgr = np.clip(out_face_bgr, 0.0, 1.0)
#if debug:
# debugs += [ np.clip( cv2.warpAffine( out_face_bgr, face_output_mat, img_size, np.zeros(img_bgr.shape, dtype=np.float32), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT ), 0, 1.0) ]
if cfg.mode == 'seamless-hist-match':
out_face_bgr = imagelib.color_hist_match(
out_face_bgr, dst_face_bgr, cfg.hist_match_threshold)
cfg_mp = cfg.motion_blur_power / 100.0
if cfg_mp != 0:
k_size = int(frame_info.motion_power * cfg_mp)
if k_size >= 1:
k_size = np.clip(k_size + 1, 2, 50)
if cfg.super_resolution_mode:
k_size *= 2
out_face_bgr = imagelib.LinearMotionBlur(
out_face_bgr, k_size, frame_info.motion_deg)
if cfg.sharpen_mode != 0 and cfg.sharpen_amount != 0:
out_face_bgr = cfg.sharpen_func(out_face_bgr, cfg.sharpen_mode,
3, cfg.sharpen_amount)
new_out = cv2.warpAffine(out_face_bgr, face_mat, img_size,
img_bgr.copy(),
cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC,
cv2.BORDER_TRANSPARENT)
out_img = np.clip(
img_bgr * (1 - img_face_mask_aaa) +
(new_out * img_face_mask_aaa), 0, 1.0)
if cfg.color_degrade_power != 0:
#if debug:
# debugs += [out_img.copy()]
out_img_reduced = imagelib.reduce_colors(out_img, 256)
if cfg.color_degrade_power == 100:
out_img = out_img_reduced
else:
alpha = cfg.color_degrade_power / 100.0
out_img = (out_img * (1.0 - alpha) +
out_img_reduced * alpha)
if cfg.export_mask_alpha:
out_img = np.concatenate(
[out_img, img_face_mask_aaa[:, :, 0:1]], -1)
out_merging_mask = img_face_mask_aaa
#if debug:
# debugs += [out_img.copy()]
return out_img, out_merging_mask
def process(sample,
sample_process_options,
output_sample_types,
debug,
ct_sample=None):
SPTF = SampleProcessor.Types
sample_bgr = sample.load_bgr()
ct_sample_bgr = None
ct_sample_mask = None
h, w, c = sample_bgr.shape
is_face_sample = sample.landmarks is not None
if debug and is_face_sample:
LandmarksProcessor.draw_landmarks(sample_bgr, sample.landmarks,
(0, 1, 0))
params = imagelib.gen_warp_params(
sample_bgr,
sample_process_options.random_flip,
rotation_range=sample_process_options.rotation_range,
scale_range=sample_process_options.scale_range,
tx_range=sample_process_options.tx_range,
ty_range=sample_process_options.ty_range)
cached_images = collections.defaultdict(dict)
sample_rnd_seed = np.random.randint(0x80000000)
SPTF_FACETYPE_TO_FACETYPE = {
SPTF.FACE_TYPE_HALF: FaceType.HALF,
SPTF.FACE_TYPE_FULL: FaceType.FULL,
SPTF.FACE_TYPE_HEAD: FaceType.HEAD,
SPTF.FACE_TYPE_FULL_NO_ALIGN: FaceType.FULL_NO_ALIGN
}
outputs = []
for opts in output_sample_types:
resolution = opts.get('resolution', 0)
types = opts.get('types', [])
random_sub_res = opts.get('random_sub_res', 0)
normalize_std_dev = opts.get('normalize_std_dev', False)
normalize_vgg = opts.get('normalize_vgg', False)
motion_blur = opts.get('motion_blur', None)
apply_ct = opts.get('apply_ct', False)
normalize_tanh = opts.get('normalize_tanh', False)
img_type = SPTF.NONE
target_face_type = SPTF.NONE
face_mask_type = SPTF.NONE
mode_type = SPTF.NONE
for t in types:
if t >= SPTF.IMG_TYPE_BEGIN and t < SPTF.IMG_TYPE_END:
img_type = t
elif t >= SPTF.FACE_TYPE_BEGIN and t < SPTF.FACE_TYPE_END:
target_face_type = t
elif t >= SPTF.MODE_BEGIN and t < SPTF.MODE_END:
mode_type = t
if img_type == SPTF.NONE:
raise ValueError('expected IMG_ type')
if img_type == SPTF.IMG_LANDMARKS_ARRAY:
l = sample.landmarks
l = np.concatenate([
np.expand_dims(l[:, 0] / w, -1),
np.expand_dims(l[:, 1] / h, -1)
], -1)
l = np.clip(l, 0.0, 1.0)
img = l
elif img_type == SPTF.IMG_PITCH_YAW_ROLL or img_type == SPTF.IMG_PITCH_YAW_ROLL_SIGMOID:
pitch_yaw_roll = sample.pitch_yaw_roll
if pitch_yaw_roll is not None:
pitch, yaw, roll = pitch_yaw_roll
else:
pitch, yaw, roll = LandmarksProcessor.estimate_pitch_yaw_roll(
sample.landmarks)
if params['flip']:
yaw = -yaw
if img_type == SPTF.IMG_PITCH_YAW_ROLL_SIGMOID:
pitch = (pitch + 1.0) / 2.0
yaw = (yaw + 1.0) / 2.0
roll = (roll + 1.0) / 2.0
img = (pitch, yaw, roll)
else:
if mode_type == SPTF.NONE:
raise ValueError('expected MODE_ type')
def do_transform(img, mask):
warp = (img_type == SPTF.IMG_WARPED
or img_type == SPTF.IMG_WARPED_TRANSFORMED)
transform = (img_type == SPTF.IMG_WARPED_TRANSFORMED
or img_type == SPTF.IMG_TRANSFORMED)
flip = img_type != SPTF.IMG_WARPED
img = imagelib.warp_by_params(params, img, warp, transform,
flip, True)
if mask is not None:
mask = imagelib.warp_by_params(params, mask, warp,
transform, flip, False)
if len(mask.shape) == 2:
mask = mask[..., np.newaxis]
img = np.concatenate((img, mask), -1)
return img
img = cached_images.get(img_type, None)
if img is None:
img = sample_bgr
mask = None
cur_sample = sample
if is_face_sample:
if motion_blur is not None:
chance, mb_range = motion_blur
chance = np.clip(chance, 0, 100)
if np.random.randint(100) < chance:
mb_range = [3, 5, 7,
9][:np.clip(mb_range, 0, 3) + 1]
dim = mb_range[np.random.randint(
len(mb_range))]
img = imagelib.LinearMotionBlur(
img, dim, np.random.randint(180))
mask = cur_sample.load_fanseg_mask(
) #using fanseg_mask if exist
if mask is None:
mask = LandmarksProcessor.get_image_hull_mask(
img.shape, cur_sample.landmarks)
if cur_sample.ie_polys is not None:
cur_sample.ie_polys.overlay_mask(mask)
if sample.face_type == FaceType.MARK_ONLY:
if mask is not None:
img = np.concatenate((img, mask), -1)
else:
img = do_transform(img, mask)
cached_images[img_type] = img
if is_face_sample and target_face_type != SPTF.NONE:
ft = SPTF_FACETYPE_TO_FACETYPE[target_face_type]
if ft > sample.face_type:
raise Exception(
'sample %s type %s does not match model requirement %s. Consider extract necessary type of faces.'
% (sample.filename, sample.face_type, ft))
if sample.face_type == FaceType.MARK_ONLY:
img = cv2.warpAffine(
img,
LandmarksProcessor.get_transform_mat(
sample.landmarks, sample.shape[0],
ft), (sample.shape[0], sample.shape[0]),
flags=cv2.INTER_CUBIC)
mask = img[..., 3:4] if img.shape[2] > 3 else None
img = img[..., 0:3]
img = do_transform(img, mask)
img = cv2.resize(img, (resolution, resolution),
cv2.INTER_CUBIC)
else:
img = cv2.warpAffine(
img,
LandmarksProcessor.get_transform_mat(
sample.landmarks, resolution,
ft), (resolution, resolution),
flags=cv2.INTER_CUBIC)
else:
img = cv2.resize(img, (resolution, resolution),
cv2.INTER_CUBIC)
if random_sub_res != 0:
sub_size = resolution - random_sub_res
rnd_state = np.random.RandomState(sample_rnd_seed +
random_sub_res)
start_x = rnd_state.randint(sub_size + 1)
start_y = rnd_state.randint(sub_size + 1)
img = img[start_y:start_y + sub_size,
start_x:start_x + sub_size, :]
img = np.clip(img, 0, 1)
img_bgr = img[..., 0:3]
img_mask = img[..., 3:4]
if apply_ct and ct_sample is not None:
if ct_sample_bgr is None:
ct_sample_bgr = ct_sample.load_bgr()
ct_sample_bgr_resized = cv2.resize(
ct_sample_bgr, (resolution, resolution),
cv2.INTER_LINEAR)
img_bgr = imagelib.linear_color_transfer(
img_bgr, ct_sample_bgr_resized)
img_bgr = np.clip(img_bgr, 0.0, 1.0)
if normalize_std_dev:
img_bgr = (img_bgr - img_bgr.mean((0, 1))) / img_bgr.std(
(0, 1))
elif normalize_vgg:
img_bgr = np.clip(img_bgr * 255, 0, 255)
img_bgr[:, :, 0] -= 103.939
img_bgr[:, :, 1] -= 116.779
img_bgr[:, :, 2] -= 123.68
if mode_type == SPTF.MODE_BGR:
img = img_bgr
elif mode_type == SPTF.MODE_BGR_SHUFFLE:
rnd_state = np.random.RandomState(sample_rnd_seed)
img = np.take(img_bgr,
rnd_state.permutation(img_bgr.shape[-1]),
axis=-1)
elif mode_type == SPTF.MODE_G:
img = np.concatenate((np.expand_dims(
cv2.cvtColor(img_bgr, cv2.COLOR_BGR2GRAY),
-1), img_mask), -1)
elif mode_type == SPTF.MODE_GGG:
img = np.concatenate((np.repeat(
np.expand_dims(
cv2.cvtColor(img_bgr, cv2.COLOR_BGR2GRAY), -1),
(3, ), -1), img_mask), -1)
elif mode_type == SPTF.MODE_M and is_face_sample:
img = img_mask
if not debug:
if normalize_tanh:
img = np.clip(img * 2.0 - 1.0, -1.0, 1.0)
else:
img = np.clip(img, 0.0, 1.0)
outputs.append(img)
if debug:
result = []
for output in outputs:
if output.shape[2] < 4:
result += [
output,
]
elif output.shape[2] == 4:
result += [
output[..., 0:3] * output[..., 3:4],
]
return result
else:
return outputs
def process(samples,
sample_process_options,
output_sample_types,
debug,
ct_sample=None):
SPTF = SampleProcessor.Types
sample_rnd_seed = np.random.randint(0x80000000)
outputs = []
for sample in samples:
sample_bgr = sample.load_bgr()
ct_sample_bgr = None
ct_sample_mask = None
h, w, c = sample_bgr.shape
is_face_sample = sample.landmarks is not None
if debug and is_face_sample:
LandmarksProcessor.draw_landmarks(sample_bgr, sample.landmarks,
(0, 1, 0))
params = imagelib.gen_warp_params(
sample_bgr,
sample_process_options.random_flip,
rotation_range=sample_process_options.rotation_range,
scale_range=sample_process_options.scale_range,
tx_range=sample_process_options.tx_range,
ty_range=sample_process_options.ty_range,
rnd_seed=sample_rnd_seed)
outputs_sample = []
for opts in output_sample_types:
resolution = opts.get('resolution', 0)
types = opts.get('types', [])
border_replicate = opts.get('border_replicate', True)
random_sub_res = opts.get('random_sub_res', 0)
normalize_std_dev = opts.get('normalize_std_dev', False)
normalize_vgg = opts.get('normalize_vgg', False)
motion_blur = opts.get('motion_blur', None)
gaussian_blur = opts.get('gaussian_blur', None)
ct_mode = opts.get('ct_mode', 'None')
normalize_tanh = opts.get('normalize_tanh', False)
img_type = SPTF.NONE
target_face_type = SPTF.NONE
face_mask_type = SPTF.NONE
mode_type = SPTF.NONE
for t in types:
if t >= SPTF.IMG_TYPE_BEGIN and t < SPTF.IMG_TYPE_END:
img_type = t
elif t >= SPTF.FACE_TYPE_BEGIN and t < SPTF.FACE_TYPE_END:
target_face_type = t
elif t >= SPTF.MODE_BEGIN and t < SPTF.MODE_END:
mode_type = t
if img_type == SPTF.NONE:
raise ValueError('expected IMG_ type')
if img_type == SPTF.IMG_LANDMARKS_ARRAY:
l = sample.landmarks
l = np.concatenate([
np.expand_dims(l[:, 0] / w, -1),
np.expand_dims(l[:, 1] / h, -1)
], -1)
l = np.clip(l, 0.0, 1.0)
img = l
elif img_type == SPTF.IMG_PITCH_YAW_ROLL or img_type == SPTF.IMG_PITCH_YAW_ROLL_SIGMOID:
pitch_yaw_roll = sample.pitch_yaw_roll
if pitch_yaw_roll is not None:
pitch, yaw, roll = pitch_yaw_roll
else:
pitch, yaw, roll = LandmarksProcessor.estimate_pitch_yaw_roll(
sample.landmarks)
if params['flip']:
yaw = -yaw
if img_type == SPTF.IMG_PITCH_YAW_ROLL_SIGMOID:
pitch = (pitch + 1.0) / 2.0
yaw = (yaw + 1.0) / 2.0
roll = (roll + 1.0) / 2.0
img = (pitch, yaw, roll)
else:
if mode_type == SPTF.NONE:
raise ValueError('expected MODE_ type')
def do_transform(img, mask):
warp = (img_type == SPTF.IMG_WARPED
or img_type == SPTF.IMG_WARPED_TRANSFORMED)
transform = (img_type == SPTF.IMG_WARPED_TRANSFORMED
or img_type == SPTF.IMG_TRANSFORMED)
flip = img_type != SPTF.IMG_WARPED
img = imagelib.warp_by_params(params, img, warp,
transform, flip,
border_replicate)
if mask is not None:
mask = imagelib.warp_by_params(
params, mask, warp, transform, flip, False)
if len(mask.shape) == 2:
mask = mask[..., np.newaxis]
return img, mask
img = sample_bgr
### Prepare a mask
mask = None
if is_face_sample:
mask = sample.load_fanseg_mask(
) #using fanseg_mask if exist
if mask is None:
if sample.eyebrows_expand_mod is not None:
mask = LandmarksProcessor.get_image_hull_mask(
img.shape,
sample.landmarks,
eyebrows_expand_mod=sample.
eyebrows_expand_mod)
else:
mask = LandmarksProcessor.get_image_hull_mask(
img.shape, sample.landmarks)
if sample.ie_polys is not None:
sample.ie_polys.overlay_mask(mask)
##################
if motion_blur is not None:
chance, mb_max_size = motion_blur
chance = np.clip(chance, 0, 100)
if np.random.randint(100) < chance:
img = imagelib.LinearMotionBlur(
img,
np.random.randint(mb_max_size) + 1,
np.random.randint(360))
if gaussian_blur is not None:
chance, kernel_max_size = gaussian_blur
chance = np.clip(chance, 0, 100)
if np.random.randint(100) < chance:
img = cv2.GaussianBlur(
img,
(np.random.randint(kernel_max_size) * 2 + 1, )
* 2, 0)
if is_face_sample and target_face_type != SPTF.NONE:
target_ft = SampleProcessor.SPTF_FACETYPE_TO_FACETYPE[
target_face_type]
if target_ft > sample.face_type:
raise Exception(
'sample %s type %s does not match model requirement %s. Consider extract necessary type of faces.'
%
(sample.filename, sample.face_type, target_ft))
if sample.face_type == FaceType.MARK_ONLY:
#first warp to target facetype
img = cv2.warpAffine(
img,
LandmarksProcessor.get_transform_mat(
sample.landmarks, sample.shape[0],
target_ft),
(sample.shape[0], sample.shape[0]),
flags=cv2.INTER_CUBIC)
mask = cv2.warpAffine(
mask,
LandmarksProcessor.get_transform_mat(
sample.landmarks, sample.shape[0],
target_ft),
(sample.shape[0], sample.shape[0]),
flags=cv2.INTER_CUBIC)
#then apply transforms
img, mask = do_transform(img, mask)
img = np.concatenate((img, mask), -1)
img = cv2.resize(img, (resolution, resolution),
cv2.INTER_CUBIC)
else:
img, mask = do_transform(img, mask)
mat = LandmarksProcessor.get_transform_mat(
sample.landmarks, resolution, target_ft)
img = cv2.warpAffine(
img,
mat, (resolution, resolution),
borderMode=(cv2.BORDER_REPLICATE
if border_replicate else
cv2.BORDER_CONSTANT),
flags=cv2.INTER_CUBIC)
mask = cv2.warpAffine(
mask,
mat, (resolution, resolution),
borderMode=cv2.BORDER_CONSTANT,
flags=cv2.INTER_CUBIC)
img = np.concatenate((img, mask[..., None]), -1)
else:
img, mask = do_transform(img, mask)
img = np.concatenate((img, mask), -1)
img = cv2.resize(img, (resolution, resolution),
cv2.INTER_CUBIC)
if random_sub_res != 0:
sub_size = resolution - random_sub_res
rnd_state = np.random.RandomState(sample_rnd_seed +
random_sub_res)
start_x = rnd_state.randint(sub_size + 1)
start_y = rnd_state.randint(sub_size + 1)
img = img[start_y:start_y + sub_size,
start_x:start_x + sub_size, :]
img = np.clip(img, 0, 1).astype(np.float32)
img_bgr = img[..., 0:3]
img_mask = img[..., 3:4]
if ct_mode is not None and ct_sample is not None:
if ct_sample_bgr is None:
ct_sample_bgr = ct_sample.load_bgr()
ct_sample_bgr_resized = cv2.resize(
ct_sample_bgr, (resolution, resolution),
cv2.INTER_LINEAR)
if ct_mode == 'lct':
img_bgr = imagelib.linear_color_transfer(
img_bgr, ct_sample_bgr_resized)
img_bgr = np.clip(img_bgr, 0.0, 1.0)
elif ct_mode == 'rct':
img_bgr = imagelib.reinhard_color_transfer(
np.clip((img_bgr * 255).astype(np.uint8), 0,
255),
np.clip((ct_sample_bgr_resized * 255).astype(
np.uint8), 0, 255))
img_bgr = np.clip(
img_bgr.astype(np.float32) / 255.0, 0.0, 1.0)
elif ct_mode == 'mkl':
img_bgr = imagelib.color_transfer_mkl(
img_bgr, ct_sample_bgr_resized)
elif ct_mode == 'idt':
img_bgr = imagelib.color_transfer_idt(
img_bgr, ct_sample_bgr_resized)
elif ct_mode == 'sot':
img_bgr = imagelib.color_transfer_sot(
img_bgr, ct_sample_bgr_resized)
img_bgr = np.clip(img_bgr, 0.0, 1.0)
if normalize_std_dev:
img_bgr = (img_bgr - img_bgr.mean(
(0, 1))) / img_bgr.std((0, 1))
elif normalize_vgg:
img_bgr = np.clip(img_bgr * 255, 0, 255)
img_bgr[:, :, 0] -= 103.939
img_bgr[:, :, 1] -= 116.779
img_bgr[:, :, 2] -= 123.68
if mode_type == SPTF.MODE_BGR:
img = img_bgr
elif mode_type == SPTF.MODE_BGR_SHUFFLE:
rnd_state = np.random.RandomState(sample_rnd_seed)
img = np.take(img_bgr,
rnd_state.permutation(img_bgr.shape[-1]),
axis=-1)
elif mode_type == SPTF.MODE_BGR_RANDOM_HSV_SHIFT:
rnd_state = np.random.RandomState(sample_rnd_seed)
hsv = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2HSV)
h, s, v = cv2.split(hsv)
h = (h + rnd_state.randint(360)) % 360
s = np.clip(s + rnd_state.random() - 0.5, 0, 1)
v = np.clip(v + rnd_state.random() - 0.5, 0, 1)
hsv = cv2.merge([h, s, v])
img = np.clip(cv2.cvtColor(hsv, cv2.COLOR_HSV2BGR), 0,
1)
elif mode_type == SPTF.MODE_G:
img = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2GRAY)[...,
None]
elif mode_type == SPTF.MODE_GGG:
img = np.repeat(
np.expand_dims(
cv2.cvtColor(img_bgr, cv2.COLOR_BGR2GRAY), -1),
(3, ), -1)
elif mode_type == SPTF.MODE_M and is_face_sample:
img = img_mask
if not debug:
if normalize_tanh:
img = np.clip(img * 2.0 - 1.0, -1.0, 1.0)
else:
img = np.clip(img, 0.0, 1.0)
outputs_sample.append(img)
outputs += [outputs_sample]
return outputs
def process(sample, sample_process_options, output_sample_types, debug):
SPTF = SampleProcessor.TypeFlags
sample_bgr = sample.load_bgr()
h, w, c = sample_bgr.shape
is_face_sample = sample.landmarks is not None
if debug and is_face_sample:
LandmarksProcessor.draw_landmarks(sample_bgr, sample.landmarks,
(0, 1, 0))
close_sample = sample.close_target_list[np.random.randint(
0, len(sample.close_target_list)
)] if sample.close_target_list is not None else None
close_sample_bgr = close_sample.load_bgr(
) if close_sample is not None else None
if debug and close_sample_bgr is not None:
LandmarksProcessor.draw_landmarks(close_sample_bgr,
close_sample.landmarks,
(0, 1, 0))
params = imagelib.gen_warp_params(
sample_bgr,
sample_process_options.random_flip,
rotation_range=sample_process_options.rotation_range,
scale_range=sample_process_options.scale_range,
tx_range=sample_process_options.tx_range,
ty_range=sample_process_options.ty_range)
images = [[None] * 3 for _ in range(30)]
sample_rnd_seed = np.random.randint(0x80000000)
outputs = []
for sample_type in output_sample_types:
f = sample_type[0]
size = sample_type[1]
random_sub_size = 0 if len(sample_type) < 3 else min(
sample_type[2], size)
if f & SPTF.SOURCE != 0:
img_type = 0
elif f & SPTF.WARPED != 0:
img_type = 1
elif f & SPTF.WARPED_TRANSFORMED != 0:
img_type = 2
elif f & SPTF.TRANSFORMED != 0:
img_type = 3
elif f & SPTF.LANDMARKS_ARRAY != 0:
img_type = 4
else:
raise ValueError('expected SampleTypeFlags type')
if f & SPTF.RANDOM_CLOSE != 0:
img_type += 10
elif f & SPTF.MORPH_TO_RANDOM_CLOSE != 0:
img_type += 20
face_mask_type = 0
if f & SPTF.FACE_MASK_FULL != 0:
face_mask_type = 1
elif f & SPTF.FACE_MASK_EYES != 0:
face_mask_type = 2
target_face_type = -1
if f & SPTF.FACE_TYPE_HALF != 0:
target_face_type = FaceType.HALF
elif f & SPTF.FACE_TYPE_FULL != 0:
target_face_type = FaceType.FULL
elif f & SPTF.FACE_TYPE_HEAD != 0:
target_face_type = FaceType.HEAD
elif f & SPTF.FACE_TYPE_AVATAR != 0:
target_face_type = FaceType.AVATAR
apply_motion_blur = f & SPTF.OPT_APPLY_MOTION_BLUR != 0
if img_type == 4:
l = sample.landmarks
l = np.concatenate([
np.expand_dims(l[:, 0] / w, -1),
np.expand_dims(l[:, 1] / h, -1)
], -1)
l = np.clip(l, 0.0, 1.0)
img = l
else:
if images[img_type][face_mask_type] is None:
if img_type >= 10 and img_type <= 19: #RANDOM_CLOSE
img_type -= 10
img = close_sample_bgr
cur_sample = close_sample
elif img_type >= 20 and img_type <= 29: #MORPH_TO_RANDOM_CLOSE
img_type -= 20
res = sample.shape[0]
s_landmarks = sample.landmarks.copy()
d_landmarks = close_sample.landmarks.copy()
idxs = list(range(len(s_landmarks)))
#remove landmarks near boundaries
for i in idxs[:]:
s_l = s_landmarks[i]
d_l = d_landmarks[i]
if s_l[0] < 5 or s_l[1] < 5 or s_l[0] >= res-5 or s_l[1] >= res-5 or \
d_l[0] < 5 or d_l[1] < 5 or d_l[0] >= res-5 or d_l[1] >= res-5:
idxs.remove(i)
#remove landmarks that close to each other in 5 dist
for landmarks in [s_landmarks, d_landmarks]:
for i in idxs[:]:
s_l = landmarks[i]
for j in idxs[:]:
if i == j:
continue
s_l_2 = landmarks[j]
diff_l = np.abs(s_l - s_l_2)
if np.sqrt(diff_l.dot(diff_l)) < 5:
idxs.remove(i)
break
s_landmarks = s_landmarks[idxs]
d_landmarks = d_landmarks[idxs]
s_landmarks = np.concatenate([
s_landmarks,
[[0, 0], [res // 2, 0], [res - 1, 0],
[0, res // 2], [res - 1, res // 2], [0, res - 1],
[res // 2, res - 1], [res - 1, res - 1]]
])
d_landmarks = np.concatenate([
d_landmarks,
[[0, 0], [res // 2, 0], [res - 1, 0],
[0, res // 2], [res - 1, res // 2], [0, res - 1],
[res // 2, res - 1], [res - 1, res - 1]]
])
img = imagelib.morph_by_points(sample_bgr, s_landmarks,
d_landmarks)
cur_sample = close_sample
else:
img = sample_bgr
cur_sample = sample
if is_face_sample:
if apply_motion_blur and sample_process_options.motion_blur is not None:
chance, mb_range = sample_process_options.motion_blur
if np.random.randint(100) < chance:
dim = mb_range[np.random.randint(
len(mb_range))]
img = imagelib.LinearMotionBlur(
img, dim, np.random.randint(180))
if face_mask_type == 1:
mask = cur_sample.load_fanseg_mask(
) #using fanseg_mask if exist
if mask is None:
mask = LandmarksProcessor.get_image_hull_mask(
img.shape, cur_sample.landmarks)
if cur_sample.ie_polys is not None:
cur_sample.ie_polys.overlay_mask(mask)
img = np.concatenate((img, mask), -1)
elif face_mask_type == 2:
mask = LandmarksProcessor.get_image_eye_mask(
img.shape, cur_sample.landmarks)
mask = np.expand_dims(
cv2.blur(mask, (w // 32, w // 32)), -1)
mask[mask > 0.0] = 1.0
img = np.concatenate((img, mask), -1)
images[img_type][face_mask_type] = imagelib.warp_by_params(
params, img, (img_type == 1 or img_type == 2),
(img_type == 2 or img_type == 3), img_type != 0,
face_mask_type == 0)
img = images[img_type][face_mask_type]
if is_face_sample and target_face_type != -1:
if target_face_type > sample.face_type:
raise Exception(
'sample %s type %s does not match model requirement %s. Consider extract necessary type of faces.'
% (sample.filename, sample.face_type,
target_face_type))
img = cv2.warpAffine(img,
LandmarksProcessor.get_transform_mat(
sample.landmarks, size,
target_face_type), (size, size),
flags=cv2.INTER_CUBIC)
else:
img = cv2.resize(img, (size, size), cv2.INTER_CUBIC)
if random_sub_size != 0:
sub_size = size - random_sub_size
rnd_state = np.random.RandomState(sample_rnd_seed +
random_sub_size)
start_x = rnd_state.randint(sub_size + 1)
start_y = rnd_state.randint(sub_size + 1)
img = img[start_y:start_y + sub_size,
start_x:start_x + sub_size, :]
img_bgr = img[..., 0:3]
img_mask = img[..., 3:4]
if f & SPTF.MODE_BGR != 0:
img = img_bgr
elif f & SPTF.MODE_BGR_SHUFFLE != 0:
rnd_state = np.random.RandomState(sample_rnd_seed)
img_bgr = np.take(img_bgr,
rnd_state.permutation(img_bgr.shape[-1]),
axis=-1)
img = np.concatenate((img_bgr, img_mask), -1)
elif f & SPTF.MODE_G != 0:
img = np.concatenate((np.expand_dims(
cv2.cvtColor(img_bgr, cv2.COLOR_BGR2GRAY),
-1), img_mask), -1)
elif f & SPTF.MODE_GGG != 0:
img = np.concatenate((np.repeat(
np.expand_dims(
cv2.cvtColor(img_bgr, cv2.COLOR_BGR2GRAY), -1),
(3, ), -1), img_mask), -1)
elif is_face_sample and f & SPTF.MODE_M != 0:
if face_mask_type == 0:
raise ValueError('no face_mask_type defined')
img = img_mask
else:
raise ValueError('expected SampleTypeFlags mode')
if not debug:
if sample_process_options.normalize_tanh:
img = np.clip(img * 2.0 - 1.0, -1.0, 1.0)
else:
img = np.clip(img, 0.0, 1.0)
outputs.append(img)
if debug:
result = []
for output in outputs:
if output.shape[2] < 4:
result += [
output,
]
elif output.shape[2] == 4:
result += [
output[..., 0:3] * output[..., 3:4],
]
return result
else:
return outputs
def process(sample,
sample_process_options,
output_sample_types,
debug,
ct_sample=None):
SPTF = SampleProcessor.Types
sample_bgr = sample.load_bgr()
ct_sample_bgr = None
ct_sample_mask = None
h, w, c = sample_bgr.shape
is_face_sample = sample.landmarks is not None
if debug and is_face_sample:
LandmarksProcessor.draw_landmarks(sample_bgr, sample.landmarks,
(0, 1, 0))
params = imagelib.gen_warp_params(
sample_bgr,
sample_process_options.random_flip,
rotation_range=sample_process_options.rotation_range,
scale_range=sample_process_options.scale_range,
tx_range=sample_process_options.tx_range,
ty_range=sample_process_options.ty_range)
cached_images = collections.defaultdict(dict)
sample_rnd_seed = np.random.randint(0x80000000)
outputs = []
for opts in output_sample_types:
resolution = opts.get('resolution', 0)
types = opts.get('types', [])
border_replicate = opts.get('border_replicate', True)
random_sub_res = opts.get('random_sub_res', 0)
normalize_std_dev = opts.get('normalize_std_dev', False)
normalize_vgg = opts.get('normalize_vgg', False)
motion_blur = opts.get('motion_blur', None)
apply_ct = opts.get('apply_ct', ColorTransferMode.NONE)
normalize_tanh = opts.get('normalize_tanh', False)
img_type = SPTF.NONE
target_face_type = SPTF.NONE
face_mask_type = SPTF.NONE
mode_type = SPTF.NONE
for t in types:
if t >= SPTF.IMG_TYPE_BEGIN and t < SPTF.IMG_TYPE_END:
img_type = t
elif t >= SPTF.FACE_TYPE_BEGIN and t < SPTF.FACE_TYPE_END:
target_face_type = t
elif t >= SPTF.MODE_BEGIN and t < SPTF.MODE_END:
mode_type = t
if img_type == SPTF.NONE:
raise ValueError('expected IMG_ type')
if img_type == SPTF.IMG_LANDMARKS_ARRAY:
l = sample.landmarks
l = np.concatenate([
np.expand_dims(l[:, 0] / w, -1),
np.expand_dims(l[:, 1] / h, -1)
], -1)
l = np.clip(l, 0.0, 1.0)
img = l
elif img_type == SPTF.IMG_PITCH_YAW_ROLL or img_type == SPTF.IMG_PITCH_YAW_ROLL_SIGMOID:
pitch_yaw_roll = sample.pitch_yaw_roll
if pitch_yaw_roll is not None:
pitch, yaw, roll = pitch_yaw_roll
else:
pitch, yaw, roll = LandmarksProcessor.estimate_pitch_yaw_roll(
sample.landmarks)
if params['flip']:
yaw = -yaw
if img_type == SPTF.IMG_PITCH_YAW_ROLL_SIGMOID:
pitch = (pitch + 1.0) / 2.0
yaw = (yaw + 1.0) / 2.0
roll = (roll + 1.0) / 2.0
img = (pitch, yaw, roll)
else:
if mode_type == SPTF.NONE:
raise ValueError('expected MODE_ type')
def do_transform(img, mask):
warp = (img_type == SPTF.IMG_WARPED
or img_type == SPTF.IMG_WARPED_TRANSFORMED)
transform = (img_type == SPTF.IMG_WARPED_TRANSFORMED
or img_type == SPTF.IMG_TRANSFORMED)
flip = img_type != SPTF.IMG_WARPED
img = imagelib.warp_by_params(params, img, warp, transform,
flip, border_replicate)
if mask is not None:
mask = imagelib.warp_by_params(params, mask, warp,
transform, flip, False)
if len(mask.shape) == 2:
mask = mask[..., np.newaxis]
img = np.concatenate((img, mask), -1)
return img
img = sample_bgr
### Prepare a mask
mask = None
if is_face_sample:
mask = sample.load_fanseg_mask(
) #using fanseg_mask if exist
if mask is None:
if sample.eyebrows_expand_mod is not None:
mask = LandmarksProcessor.get_image_hull_mask(
img.shape,
sample.landmarks,
eyebrows_expand_mod=sample.eyebrows_expand_mod)
else:
mask = LandmarksProcessor.get_image_hull_mask(
img.shape, sample.landmarks)
if sample.ie_polys is not None:
sample.ie_polys.overlay_mask(mask)
##################
if motion_blur is not None:
chance, mb_max_size = motion_blur
chance = np.clip(chance, 0, 100)
if np.random.randint(100) < chance:
img = imagelib.LinearMotionBlur(
img,
np.random.randint(mb_max_size) + 1,
np.random.randint(360))
if is_face_sample and target_face_type != SPTF.NONE:
target_ft = SampleProcessor.SPTF_FACETYPE_TO_FACETYPE[
target_face_type]
if target_ft > sample.face_type:
raise Exception(
'sample %s type %s does not match model requirement %s. Consider extract necessary type of faces.'
% (sample.filename, sample.face_type, target_ft))
if sample.face_type == FaceType.MARK_ONLY:
#first warp to target facetype
img = cv2.warpAffine(
img,
LandmarksProcessor.get_transform_mat(
sample.landmarks, sample.shape[0],
target_ft), (sample.shape[0], sample.shape[0]),
flags=cv2.INTER_CUBIC)
mask = cv2.warpAffine(
mask,
LandmarksProcessor.get_transform_mat(
sample.landmarks, sample.shape[0],
target_ft), (sample.shape[0], sample.shape[0]),
flags=cv2.INTER_CUBIC)
#then apply transforms
img = do_transform(img, mask)
img = cv2.resize(img, (resolution, resolution),
cv2.INTER_CUBIC)
else:
img = do_transform(img, mask)
img = cv2.warpAffine(
img,
LandmarksProcessor.get_transform_mat(
sample.landmarks, resolution,
target_ft), (resolution, resolution),
borderMode=(cv2.BORDER_REPLICATE
if border_replicate else
cv2.BORDER_CONSTANT),
flags=cv2.INTER_CUBIC)
else:
img = do_transform(img, mask)
img = cv2.resize(img, (resolution, resolution),
cv2.INTER_CUBIC)
if random_sub_res != 0:
sub_size = resolution - random_sub_res
rnd_state = np.random.RandomState(sample_rnd_seed +
random_sub_res)
start_x = rnd_state.randint(sub_size + 1)
start_y = rnd_state.randint(sub_size + 1)
img = img[start_y:start_y + sub_size,
start_x:start_x + sub_size, :]
img = np.clip(img, 0, 1)
img_bgr = img[..., 0:3]
img_mask = img[..., 3:4]
if apply_ct and ct_sample is not None:
if ct_sample_bgr is None:
ct_sample_bgr = ct_sample.load_bgr()
if apply_ct == ColorTransferMode.LCT:
img_bgr = imagelib.linear_color_transfer(
img_bgr, ct_sample_bgr)
elif ColorTransferMode.RCT <= apply_ct <= ColorTransferMode.MASKED_RCT_PAPER_CLIP:
ct_options = {
ColorTransferMode.RCT: (False, False, False),
ColorTransferMode.RCT_CLIP: (False, False, True),
ColorTransferMode.RCT_PAPER: (False, True, False),
ColorTransferMode.RCT_PAPER_CLIP:
(False, True, True),
ColorTransferMode.MASKED_RCT: (True, False, False),
ColorTransferMode.MASKED_RCT_CLIP:
(True, False, True),
ColorTransferMode.MASKED_RCT_PAPER:
(True, True, False),
ColorTransferMode.MASKED_RCT_PAPER_CLIP:
(True, True, True),
}
use_masks, use_paper, use_clip = ct_options[apply_ct]
if not use_masks:
img_bgr = imagelib.reinhard_color_transfer(
img_bgr,
ct_sample_bgr,
clip=use_clip,
preserve_paper=use_paper)
else:
if ct_sample_mask is None:
ct_sample_mask = ct_sample.load_mask()
img_bgr = imagelib.reinhard_color_transfer(
img_bgr,
ct_sample_bgr,
clip=use_clip,
preserve_paper=use_paper,
source_mask=img_mask,
target_mask=ct_sample_mask)
if normalize_std_dev:
img_bgr = (img_bgr - img_bgr.mean((0, 1))) / img_bgr.std(
(0, 1))
elif normalize_vgg:
img_bgr = np.clip(img_bgr * 255, 0, 255)
img_bgr[:, :, 0] -= 103.939
img_bgr[:, :, 1] -= 116.779
img_bgr[:, :, 2] -= 123.68
if mode_type == SPTF.MODE_BGR:
img = img_bgr
elif mode_type == SPTF.MODE_BGR_SHUFFLE:
rnd_state = np.random.RandomState(sample_rnd_seed)
img = np.take(img_bgr,
rnd_state.permutation(img_bgr.shape[-1]),
axis=-1)
elif mode_type == SPTF.MODE_LAB_RAND_TRANSFORM:
rnd_state = np.random.RandomState(sample_rnd_seed)
img = random_color_transform(img_bgr, rnd_state)
elif mode_type == SPTF.MODE_G:
img = np.concatenate((np.expand_dims(
cv2.cvtColor(img_bgr, cv2.COLOR_BGR2GRAY),
-1), img_mask), -1)
elif mode_type == SPTF.MODE_GGG:
img = np.concatenate((np.repeat(
np.expand_dims(
cv2.cvtColor(img_bgr, cv2.COLOR_BGR2GRAY), -1),
(3, ), -1), img_mask), -1)
elif mode_type == SPTF.MODE_M and is_face_sample:
img = img_mask
if not debug:
if normalize_tanh:
img = np.clip(img * 2.0 - 1.0, -1.0, 1.0)
else:
img = np.clip(img, 0.0, 1.0)
outputs.append(img)
if debug:
result = []
for output in outputs:
if output.shape[2] < 4:
result += [
output,
]
elif output.shape[2] == 4:
result += [
output[..., 0:3] * output[..., 3:4],
]
return result
else:
return outputs
