def __getitem__(self, index):
self.A, self.B, self.I, seq_idx = self.update_frame_idx(self.A_paths, index)
tG = self.opt.n_frames_G
A_img = Image.open(self.A_paths[seq_idx][0]).convert('RGB')
params = get_img_params(self.opt, A_img.size)
transform_scaleB = get_transform(self.opt, params)
transform_scaleA = get_transform(self.opt, params, method=Image.NEAREST, normalize=False) if self.A_is_label else transform_scaleB
frame_range = list(range(tG)) if self.A is None else [tG-1]
for i in frame_range:
A_path = self.A_paths[seq_idx][self.frame_idx + i]
Ai = self.get_image(A_path, transform_scaleA, is_label=self.A_is_label)
self.A = concat_frame(self.A, Ai, tG)
if self.use_real:
B_path = self.B_paths[seq_idx][self.frame_idx + i]
Bi = self.get_image(B_path, transform_scaleB)
self.B = concat_frame(self.B, Bi, tG)
else:
self.B = 0
if self.opt.use_instance:
I_path = self.I_paths[seq_idx][self.frame_idx + i]
Ii = self.get_image(I_path, transform_scaleA) * 255.0
self.I = concat_frame(self.I, Ii, tG)
else:
self.I = 0
self.frame_idx += 1
return_list = {'A': self.A, 'B': self.B, 'inst': self.I, 'A_path': A_path, 'change_seq': self.change_seq}
return return_list
def __getitem__(self, index):
TParsing, SPose, SParsing, SFG, seq_idx = self.update_frame_idx_parser(
self.sparsing_paths, index)
sparsing_paths = self.sparsing_paths[seq_idx]
sfg_paths = self.sfg_paths[seq_idx]
n_frames_total, start_idx, t_step = get_video_params(
self.opt, self.n_frames_total, len(sparsing_paths), self.frame_idx)
sparsing = Image.open(sparsing_paths[start_idx])
sfg = Image.open(sfg_paths[start_idx]).convert('RGB')
size = sfg.size
BigSizeFlag = True
if size[0] / size[1] > 1:
BigSizeFlag = True
else:
BigSizeFlag = False
if BigSizeFlag:
params = get_img_params(self.opt, (1920, 1080))
else:
params = get_img_params(self.opt, size)
tparsing_path = self.tparsing_paths[seq_idx][0]
TParsing = self.get_TImage(tparsing_path, size, params, BigSizeFlag)
TParsing = self.crop(TParsing)
frame_range = list(range(n_frames_total)) if (
self.opt.isTrain
or self.TPose is None) else [self.opt.n_frames_G - 1]
for i in frame_range:
sparsing_path = sparsing_paths[start_idx + i * t_step]
spose_path = self.spose_paths[seq_idx][start_idx + i * t_step]
sfg_path = sfg_paths[start_idx + i * t_step]
SPose_i, SParsing_i, SFG_i = self.get_SImage(
spose_path, sparsing_path, sfg_path, size, params, BigSizeFlag)
SParsing_i = self.crop(SParsing_i)
SPose_i = self.crop(SPose_i)
SFG_i = self.crop(SFG_i)
SPose = concat_frame(SPose, SPose_i, n_frames_total)
SParsing = concat_frame(SParsing, SParsing_i, n_frames_total)
SFG = concat_frame(SFG, SFG_i, n_frames_total)
if not self.opt.isTrain:
self.TParsing, self.SPose, self.SParsing, self.SFG = TParsing, SPose, SParsing, SFG
self.frame_idx += 1
change_seq = False if self.opt.isTrain else self.change_seq
return_list = {
'TParsing': TParsing,
'SPose': SPose,
'SParsing': SParsing,
'SFG': SFG,
'A_path': sparsing_path,
'change_seq': change_seq
}
return return_list
def __getitem__(self, index):
A, B, _, seq_idx = self.update_frame_idx(self.img_paths, index)
img_paths = self.img_paths[seq_idx]
n_frames_total, start_idx, t_step = get_video_params(
self.opt, self.n_frames_total, len(img_paths), self.frame_idx)
img = Image.open(img_paths[start_idx]).convert('RGB')
size = img.size
params = get_img_params(self.opt, size)
frame_range = list(range(n_frames_total)) if (
self.opt.isTrain or self.A is None) else [self.opt.n_frames_G - 1]
for i in frame_range:
img_path = img_paths[start_idx + i * t_step]
if not self.opt.openpose_only:
dp_path = self.dp_paths[seq_idx][start_idx + i * t_step]
Di = self.get_image(dp_path,
size,
params,
input_type='densepose')
Di[2, :, :] = (
(Di[2, :, :] * 0.5 + 0.5) * 255 / 24 - 0.5) / 0.5
if not self.opt.densepose_only:
op_path = self.op_paths[seq_idx][start_idx + i * t_step]
Oi = self.get_image(op_path,
size,
params,
input_type='openpose')
if self.opt.openpose_only:
Ai = Oi
elif self.opt.densepose_only:
Ai = Di
else:
Ai = torch.cat([Di, Oi])
Bi = self.get_image(img_path, size, params, input_type='img')
Ai, Bi = self.crop(Ai), self.crop(
Bi) # only crop the central half region to save time
A = concat_frame(A, Ai, n_frames_total)
B = concat_frame(B, Bi, n_frames_total)
if not self.opt.isTrain:
self.A, self.B = A, B
self.frame_idx += 1
change_seq = False if self.opt.isTrain else self.change_seq
return_list = {
'A': A,
'B': B,
'inst': 0,
'A_path': img_path,
'change_seq': change_seq
}
return return_list
def __getitem__(self, index):
A, B, I, seq_idx = self.update_frame_idx(self.A_paths, index)
A_paths = self.A_paths[seq_idx]
B_paths = self.B_paths[seq_idx]
n_frames_total, start_idx, t_step = get_video_params(
self.opt, self.n_frames_total, len(A_paths), self.frame_idx)
B_img = Image.open(B_paths[0]).convert('RGB')
B_size = B_img.size
points = np.loadtxt(A_paths[0], delimiter=',')
is_first_frame = self.opt.isTrain or not hasattr(self, 'min_x')
if is_first_frame: # crop only the face region
self.get_crop_coords(points, B_size)
params = get_img_params(self.opt, self.crop(B_img).size)
transform_scaleA = get_transform(self.opt,
params,
method=Image.BILINEAR,
normalize=False)
transform_label = get_transform(self.opt,
params,
method=Image.NEAREST,
normalize=False)
transform_scaleB = get_transform(self.opt, params)
# read in images
frame_range = list(range(n_frames_total)) if self.A is None else [
self.opt.n_frames_G - 1
]
for i in frame_range:
A_path = A_paths[start_idx + i * t_step]
B_path = B_paths[start_idx + i * t_step]
B_img = Image.open(B_path)
Ai, Li = self.get_face_image(A_path, transform_scaleA,
transform_label, B_size, B_img)
Bi = transform_scaleB(self.crop(B_img))
A = concat_frame(A, Ai, n_frames_total)
B = concat_frame(B, Bi, n_frames_total)
I = concat_frame(I, Li, n_frames_total)
if not self.opt.isTrain:
self.A, self.B, self.I = A, B, I
self.frame_idx += 1
change_seq = False if self.opt.isTrain else self.change_seq
return_list = {
'A': A,
'B': B,
'inst': I,
'A_path': A_path,
'change_seq': change_seq
}
return return_list
def __getitem__(self, index):
TParsing, TFG, SPose, SParsing, SFG, SFG_full, BG, BG_flag, SI, seq_idx = self.update_frame_idx_composer(
self.simg_paths, index)
simg_paths = self.simg_paths[seq_idx]
n_frames_total, start_idx, t_step = get_video_params(
self.opt, self.n_frames_total, len(simg_paths), self.frame_idx)
simg = Image.open(simg_paths[start_idx]).convert('RGB')
size = simg.size
BigSizeFlag = True
if size[0] / size[1] > 1:
BigSizeFlag = True
else:
BigSizeFlag = False
if BigSizeFlag:
params = get_img_params(self.opt, (1920, 1080))
else:
params = get_img_params(self.opt, size)
tparsing_path = self.tparsing_paths[seq_idx][0]
timg_path = self.timg_paths[seq_idx][0]
video_name = timg_path[timg_path.rfind('video'):timg_path.rfind('/timg'
)]
bg_path = self.dir_bg + '/' + video_name + '.jpg'
BG_i, BG_flag = self.get_bg_image(bg_path, size, params, BigSizeFlag)
TParsing, TFG = self.get_TImage(tparsing_path, timg_path, size, params,
BigSizeFlag)
TParsing, TFG = self.crop(TParsing), self.crop(TFG)
frame_range = list(range(n_frames_total)) if (
self.opt.isTrain
or self.TPose is None) else [self.opt.n_frames_G - 1]
for i in frame_range:
simg_path = simg_paths[start_idx + i * t_step]
sfg_path = self.sfg_paths[seq_idx][start_idx + i * t_step]
spose_path = self.spose_paths[seq_idx][start_idx + i * t_step]
sparsing_path = self.sparsing_paths[seq_idx][start_idx +
i * t_step]
SPose_i, SParsing_i, SFG_i, SFG_full_i, SI_i = self.get_SImage(
spose_path, sparsing_path, sfg_path, simg_path, size, params,
BigSizeFlag)
SParsing_i = self.crop(SParsing_i)
SFG_i = self.crop(SFG_i)
SPose_i, SFG_full_i, SI_i = self.crop(SPose_i), self.crop(
SFG_full_i), self.crop(SI_i)
SPose = concat_frame(SPose, SPose_i, n_frames_total)
SParsing = concat_frame(SParsing, SParsing_i, n_frames_total)
SFG = concat_frame(SFG, SFG_i, n_frames_total)
SFG_full = concat_frame(SFG_full, SFG_full_i, n_frames_total)
SI = concat_frame(SI, SI_i, n_frames_total)
BG = concat_frame(BG, BG_i, n_frames_total)
if not self.opt.isTrain:
self.TParsing, self.TFG, self.SPose, self.SParsing, self.SFG, self.SFG_full, self.BG, self.BG_flag, self.SI = TParsing, TFG, SPose, SParsing, SFG, SFG_full, BG, BG_flag, SI
self.frame_idx += 1
change_seq = False if self.opt.isTrain else self.change_seq
return_list = {
'TParsing': TParsing,
'TFG': TFG,
'SPose': SPose,
'SParsing': SParsing,
'SFG': SFG,
'SFG_full': SFG_full,
'BG': BG,
'BG_flag': BG_flag,
'SI': SI,
'A_path': simg_path,
'change_seq': change_seq
}
return return_list
