def loaddata():
video_index = random.randint(0, len(videos) - 1)
video = videos[video_index]
img_index = random.randint(N, lengths[video_index] - N)
input_img = np.zeros((SIZE, SIZE, 3 * N + 1), dtype='uint8')
for i in range(0, N):
# print('./dataset/'+video+'/mosaic/output_'+'%05d'%(img_index+i-int(N/2))+'.png')
img = cv2.imread('./dataset/' + video + '/mosaic/output_' + '%05d' %
(img_index + i - int(N / 2)) + '.png')
img = impro.resize(img, SIZE)
input_img[:, :, i * 3:(i + 1) * 3] = img
mask = cv2.imread(
'./dataset/' + video + '/mask/output_' + '%05d' % (img_index) + '.png',
0)
mask = impro.resize(mask, 256)
mask = impro.mask_threshold(mask, 15, 128)
input_img[:, :, -1] = mask
input_img = data.im2tensor(input_img,
bgr2rgb=False,
use_gpu=opt.use_gpu,
use_transform=False)
ground_true = cv2.imread('./dataset/' + video + '/ori/output_' + '%05d' %
(img_index) + '.png')
ground_true = impro.resize(ground_true, SIZE)
# ground_true = im2tensor(ground_true,use_gpu)
ground_true = data.im2tensor(ground_true,
bgr2rgb=False,
use_gpu=opt.use_gpu,
use_transform=False)
return input_img, ground_true
def run_styletransfer(opt, net, img):
if opt.output_size != 0:
if 'resize' in opt.preprocess and 'resize_scale_width' not in opt.preprocess:
img = impro.resize(img, opt.output_size)
elif 'resize_scale_width' in opt.preprocess:
img = cv2.resize(img, (opt.output_size, opt.output_size))
img = img[0:4 * int(img.shape[0] / 4), 0:4 * int(img.shape[1] / 4), :]
if 'edges' in opt.preprocess:
if opt.canny > 100:
canny_low = opt.canny - 50
canny_high = np.clip(opt.canny + 50, 0, 255)
elif opt.canny < 50:
canny_low = np.clip(opt.canny - 25, 0, 255)
canny_high = opt.canny + 25
else:
canny_low = opt.canny - int(opt.canny / 2)
canny_high = opt.canny + int(opt.canny / 2)
img = cv2.Canny(img, opt.canny - 50, opt.canny + 50)
if opt.only_edges:
return img
img = data.im2tensor(img,
use_gpu=opt.use_gpu,
gray=True,
use_transform=False,
is0_1=False)
else:
img = data.im2tensor(img, use_gpu=opt.use_gpu)
img = net(img)
img = data.tensor2im(img)
return img
def loaddata(video_index):
videoname = videonames[video_index]
img_index = random.randint(
int(N / 2) + 1, lengths[video_index] - int(N / 2) - 1)
input_img = np.zeros((opt.loadsize, opt.loadsize, 3 * N + 1),
dtype='uint8')
# this frame
this_mask = impro.imread(os.path.join(opt.dataset, videoname, 'mask',
'%05d' % (img_index) + '.png'),
'gray',
loadsize=opt.loadsize)
input_img[:, :, -1] = this_mask
#print(os.path.join(opt.dataset,videoname,'origin_image','%05d'%(img_index)+'.jpg'))
ground_true = impro.imread(os.path.join(opt.dataset, videoname,
'origin_image',
'%05d' % (img_index) + '.jpg'),
loadsize=opt.loadsize)
mosaic_size, mod, rect_rat, father = mosaic.get_random_parameter(
ground_true, this_mask)
# merge other frame
for i in range(0, N):
img = impro.imread(os.path.join(
opt.dataset, videoname, 'origin_image',
'%05d' % (img_index + i - int(N / 2)) + '.jpg'),
loadsize=opt.loadsize)
mask = impro.imread(os.path.join(
opt.dataset, videoname, 'mask',
'%05d' % (img_index + i - int(N / 2)) + '.png'),
'gray',
loadsize=opt.loadsize)
img_mosaic = mosaic.addmosaic_base(img,
mask,
mosaic_size,
model=mod,
rect_rat=rect_rat,
father=father)
input_img[:, :, i * 3:(i + 1) * 3] = img_mosaic
# to tensor
input_img, ground_true = data.random_transform_video(
input_img, ground_true, opt.finesize, N)
input_img = data.im2tensor(input_img,
bgr2rgb=False,
use_gpu=opt.use_gpu,
use_transform=False,
is0_1=False)
ground_true = data.im2tensor(ground_true,
bgr2rgb=False,
use_gpu=opt.use_gpu,
use_transform=False,
is0_1=False)
return input_img, ground_true
def run_pix2pix(img, net, opt):
if opt.netG == 'HD':
img = impro.resize(img, 512)
else:
img = impro.resize(img, 128)
img = data.im2tensor(img, use_gpu=opt.use_gpu)
img_fake = net(img)
img_fake = data.tensor2im(img_fake)
return img_fake
def run_segment(img, net, size=360, use_gpu=0):
img = impro.resize(img, size)
img = data.im2tensor(img,
use_gpu=use_gpu,
bgr2rgb=False,
use_transform=False,
is0_1=True)
mask = net(img)
mask = data.tensor2im(mask, gray=True, rgb2bgr=False, is0_1=True)
return mask
def cleanmosaic_video_fusion(opt,netG,netM):
path = opt.media_path
N = 25
INPUT_SIZE = 128
fps,imagepaths = video_init(opt,path)
positions = []
# get position
for i,imagepath in enumerate(imagepaths,1):
img_origin = impro.imread(os.path.join('./tmp/video2image',imagepath))
# x,y,size = runmodel.get_mosaic_position(img_origin,net_mosaic_pos,opt)[:3]
x,y,size,mask = runmodel.get_mosaic_position(img_origin,netM,opt)
cv2.imwrite(os.path.join('./tmp/mosaic_mask',imagepath), mask)
positions.append([x,y,size])
print('\r','Find mosaic location:'+str(i)+'/'+str(len(imagepaths)),util.get_bar(100*i/len(imagepaths),num=40),end='')
print('\nOptimize mosaic locations...')
positions =np.array(positions)
for i in range(3):positions[:,i] = filt.medfilt(positions[:,i],opt.medfilt_num)
# clean mosaic
for i,imagepath in enumerate(imagepaths,0):
x,y,size = positions[i][0],positions[i][1],positions[i][2]
img_origin = impro.imread(os.path.join('./tmp/video2image',imagepath))
mask = cv2.imread(os.path.join('./tmp/mosaic_mask',imagepath),0)
if size==0:
cv2.imwrite(os.path.join('./tmp/replace_mosaic',imagepath),img_origin)
else:
mosaic_input = np.zeros((INPUT_SIZE,INPUT_SIZE,3*N+1), dtype='uint8')
for j in range(0,N):
img = impro.imread(os.path.join('./tmp/video2image',imagepaths[np.clip(i+j-12,0,len(imagepaths)-1)]))
img = img[y-size:y+size,x-size:x+size]
img = impro.resize(img,INPUT_SIZE)
mosaic_input[:,:,j*3:(j+1)*3] = img
mask = impro.resize(mask,np.min(img_origin.shape[:2]))
mask = mask[y-size:y+size,x-size:x+size]
mask = impro.resize(mask, INPUT_SIZE)
mosaic_input[:,:,-1] = mask
mosaic_input = data.im2tensor(mosaic_input,bgr2rgb=False,use_gpu=opt.use_gpu,use_transform = False,is0_1 = False)
unmosaic_pred = netG(mosaic_input)
#unmosaic_pred = (unmosaic_pred.cpu().detach().numpy()*255)[0]
#img_fake = unmosaic_pred.transpose((1, 2, 0))
img_fake = data.tensor2im(unmosaic_pred,rgb2bgr = False ,is0_1 = False)
img_result = impro.replace_mosaic(img_origin,img_fake,x,y,size,opt.no_feather)
cv2.imwrite(os.path.join('./tmp/replace_mosaic',imagepath),img_result)
print('\r','Clean Mosaic:'+str(i+1)+'/'+str(len(imagepaths)),util.get_bar(100*i/len(imagepaths),num=40),end='')
print()
ffmpeg.image2video( fps,
'./tmp/replace_mosaic/output_%05d.'+opt.tempimage_type,
'./tmp/voice_tmp.mp3',
os.path.join(opt.result_dir,os.path.splitext(os.path.basename(path))[0]+'_clean.mp4'))
def cleanmosaic_video_fusion(opt,netG,netM):
path = opt.media_path
N = 25
if 'HD' in os.path.basename(opt.model_path):
INPUT_SIZE = 256
else:
INPUT_SIZE = 128
fps,imagepaths,height,width = video_init(opt,path)
positions = get_mosaic_positions(opt,netM,imagepaths,savemask=True)
# clean mosaic
img_pool = np.zeros((height,width,3*N), dtype='uint8')
for i,imagepath in enumerate(imagepaths,0):
x,y,size = positions[i][0],positions[i][1],positions[i][2]
# image read stream
mask = cv2.imread(os.path.join('./tmp/mosaic_mask',imagepath),0)
if i==0 :
for j in range(0,N):
img_pool[:,:,j*3:(j+1)*3] = impro.imread(os.path.join('./tmp/video2image',imagepaths[np.clip(i+j-12,0,len(imagepaths)-1)]))
else:
img_pool[:,:,0:(N-1)*3] = img_pool[:,:,3:N*3]
img_pool[:,:,(N-1)*3:] = impro.imread(os.path.join('./tmp/video2image',imagepaths[np.clip(i+12,0,len(imagepaths)-1)]))
img_origin = img_pool[:,:,int((N-1)/2)*3:(int((N-1)/2)+1)*3]
if size==0: # can not find mosaic,
cv2.imwrite(os.path.join('./tmp/replace_mosaic',imagepath),img_origin)
else:
mosaic_input = np.zeros((INPUT_SIZE,INPUT_SIZE,3*N+1), dtype='uint8')
mosaic_input[:,:,0:N*3] = impro.resize(img_pool[y-size:y+size,x-size:x+size,:], INPUT_SIZE)
mask_input = impro.resize(mask,np.min(img_origin.shape[:2]))[y-size:y+size,x-size:x+size]
mosaic_input[:,:,-1] = impro.resize(mask_input, INPUT_SIZE)
mosaic_input = data.im2tensor(mosaic_input,bgr2rgb=False,use_gpu=opt.use_gpu,use_transform = False,is0_1 = False)
unmosaic_pred = netG(mosaic_input)
img_fake = data.tensor2im(unmosaic_pred,rgb2bgr = False ,is0_1 = False)
img_result = impro.replace_mosaic(img_origin,img_fake,mask,x,y,size,opt.no_feather)
cv2.imwrite(os.path.join('./tmp/replace_mosaic',imagepath),img_result)
print('\r','Clean Mosaic:'+str(i+1)+'/'+str(len(imagepaths)),util.get_bar(100*i/len(imagepaths),num=35),end='')
print()
ffmpeg.image2video( fps,
'./tmp/replace_mosaic/output_%05d.'+opt.tempimage_type,
'./tmp/voice_tmp.mp3',
os.path.join(opt.result_dir,os.path.splitext(os.path.basename(path))[0]+'_clean.mp4'))
def run_pix2pix(img, net, size=128, use_gpu=True):
img = impro.resize(img, size)
img = data.im2tensor(img, use_gpu=use_gpu)
img_fake = net(img)
img_fake = data.tensor2im(img_fake)
return img_fake
#test
if os.path.isdir('./test'):
netG.eval()
test_names = os.listdir('./test')
test_names.sort()
result = np.zeros((opt.finesize*2,opt.finesize*len(test_names),3), dtype='uint8')
for cnt,test_name in enumerate(test_names,0):
img_names = os.listdir(os.path.join('./test',test_name,'image'))
img_names.sort()
inputdata = np.zeros((opt.finesize,opt.finesize,3*N+1), dtype='uint8')
for i in range(0,N):
img = impro.imread(os.path.join('./test',test_name,'image',img_names[i]))
img = impro.resize(img,opt.finesize)
inputdata[:,:,i*3:(i+1)*3] = img
mask = impro.imread(os.path.join('./test',test_name,'mask.png'),'gray')
mask = impro.resize(mask,opt.finesize)
mask = impro.mask_threshold(mask,15,128)
inputdata[:,:,-1] = mask
result[0:opt.finesize,opt.finesize*cnt:opt.finesize*(cnt+1),:] = inputdata[:,:,int((N-1)/2)*3:(int((N-1)/2)+1)*3]
inputdata = data.im2tensor(inputdata,bgr2rgb=False,use_gpu=opt.use_gpu,use_transform = False,is0_1 = False)
pred = netG(inputdata)
pred = data.tensor2im(pred,rgb2bgr = False, is0_1 = False)
result[opt.finesize:opt.finesize*2,opt.finesize*cnt:opt.finesize*(cnt+1),:] = pred
cv2.imwrite(os.path.join(dir_checkpoint,str(iter+1)+'_test.jpg'), result)
netG.train()
def run_segment(img, net, size=360, gpu_id='-1'):
img = impro.resize(img, size)
img = data.im2tensor(img, gpu_id=gpu_id, bgr2rgb=False, is0_1=True)
mask = net(img)
mask = data.tensor2im(mask, gray=True, is0_1=True)
return mask
def cleanmosaic_video_fusion(opt, netG, netM):
path = opt.media_path
N, T, S = 2, 5, 3
LEFT_FRAME = (N * S)
POOL_NUM = LEFT_FRAME * 2 + 1
INPUT_SIZE = 256
FRAME_POS = np.linspace(0, (T - 1) * S, T, dtype=np.int64)
img_pool = []
previous_frame = None
init_flag = True
fps, imagepaths, height, width = video_init(opt, path)
positions = get_mosaic_positions(opt, netM, imagepaths, savemask=True)
t1 = time.time()
if not opt.no_preview:
cv2.namedWindow('clean', cv2.WINDOW_NORMAL)
# clean mosaic
print('Step:3/4 -- Clean Mosaic:')
length = len(imagepaths)
for i, imagepath in enumerate(imagepaths, 0):
x, y, size = positions[i][0], positions[i][1], positions[i][2]
input_stream = []
# image read stream
if i == 0: # init
for j in range(POOL_NUM):
img_pool.append(
impro.imread(
os.path.join(
opt.temp_dir + '/video2image',
imagepaths[np.clip(i + j - LEFT_FRAME, 0,
len(imagepaths) - 1)])))
else: # load next frame
img_pool.pop(0)
img_pool.append(
impro.imread(
os.path.join(
opt.temp_dir + '/video2image',
imagepaths[np.clip(i + LEFT_FRAME, 0,
len(imagepaths) - 1)])))
img_origin = img_pool[LEFT_FRAME]
img_result = img_origin.copy()
if size > 50:
try: #Avoid unknown errors
for pos in FRAME_POS:
input_stream.append(
impro.resize(
img_pool[pos][y - size:y + size,
x - size:x + size],
INPUT_SIZE)[:, :, ::-1])
if init_flag:
init_flag = False
previous_frame = input_stream[N]
previous_frame = data.im2tensor(previous_frame,
bgr2rgb=True,
gpu_id=opt.gpu_id)
input_stream = np.array(input_stream).reshape(
1, T, INPUT_SIZE, INPUT_SIZE, 3).transpose((0, 4, 1, 2, 3))
input_stream = data.to_tensor(data.normalize(input_stream),
gpu_id=opt.gpu_id)
with torch.no_grad():
unmosaic_pred = netG(input_stream, previous_frame)
img_fake = data.tensor2im(unmosaic_pred, rgb2bgr=True)
previous_frame = unmosaic_pred
# previous_frame = data.tensor2im(unmosaic_pred,rgb2bgr = True)
mask = cv2.imread(
os.path.join(opt.temp_dir + '/mosaic_mask', imagepath), 0)
img_result = impro.replace_mosaic(img_origin, img_fake, mask,
x, y, size, opt.no_feather)
except Exception as e:
init_flag = True
print('Error:', e)
else:
init_flag = True
cv2.imwrite(os.path.join(opt.temp_dir + '/replace_mosaic', imagepath),
img_result)
os.remove(os.path.join(opt.temp_dir + '/video2image', imagepath))
#preview result and print
if not opt.no_preview:
cv2.imshow('clean', img_result)
cv2.waitKey(1) & 0xFF
t2 = time.time()
print('\r',
str(i + 1) + '/' + str(length),
util.get_bar(100 * i / length, num=35),
util.counttime(t1, t2, i + 1, len(imagepaths)),
end='')
print()
if not opt.no_preview:
cv2.destroyAllWindows()
print('Step:4/4 -- Convert images to video')
ffmpeg.image2video(
fps,
opt.temp_dir + '/replace_mosaic/output_%06d.' + opt.tempimage_type,
opt.temp_dir + '/voice_tmp.mp3',
os.path.join(
opt.result_dir,
os.path.splitext(os.path.basename(path))[0] + '_clean.mp4'))
def cleanmosaic_video_fusion(opt):
net = loadmodel.pix2pix(opt)
net_mosaic_pos = loadmodel.unet_clean(opt)
path = opt.media_path
N = 25
util.clean_tempfiles()
fps = ffmpeg.get_video_infos(path)[0]
ffmpeg.video2voice(path, './tmp/voice_tmp.mp3')
ffmpeg.video2image(path,
'./tmp/video2image/output_%05d.' + opt.tempimage_type)
positions = []
imagepaths = os.listdir('./tmp/video2image')
imagepaths.sort()
# get position
for imagepath in imagepaths:
img_origin = impro.imread(os.path.join('./tmp/video2image', imagepath))
# x,y,size = runmodel.get_mosaic_position(img_origin,net_mosaic_pos,opt)[:3]
x, y, size, mask = runmodel.get_mosaic_position(
img_origin, net_mosaic_pos, opt)
cv2.imwrite(os.path.join('./tmp/mosaic_mask', imagepath), mask)
positions.append([x, y, size])
print('Find mosaic location:', imagepath)
print('Optimize mosaic locations...')
positions = np.array(positions)
for i in range(3):
positions[:, i] = filt.medfilt(positions[:, i], opt.medfilt_num)
# clean mosaic
print('Clean mosaic...')
for i, imagepath in enumerate(imagepaths, 0):
print('Clean mosaic:', imagepath)
x, y, size = positions[i][0], positions[i][1], positions[i][2]
img_origin = impro.imread(os.path.join('./tmp/video2image', imagepath))
mask = cv2.imread(os.path.join('./tmp/mosaic_mask', imagepath), 0)
if size == 0:
cv2.imwrite(os.path.join('./tmp/replace_mosaic', imagepath),
img_origin)
else:
mosaic_input = np.zeros((256, 256, 3 * N + 1), dtype='uint8')
for j in range(0, N):
img = impro.imread(
os.path.join(
'./tmp/video2image',
imagepaths[np.clip(i + j - 12, 0,
len(imagepaths) - 1)]))
img = img[y - size:y + size, x - size:x + size]
img = impro.resize(img, 256)
mosaic_input[:, :, j * 3:(j + 1) * 3] = img
mask = impro.resize(mask, np.min(img_origin.shape[:2]))
mask = mask[y - size:y + size, x - size:x + size]
mask = impro.resize(mask, 256)
mosaic_input[:, :, -1] = mask
mosaic_input = data.im2tensor(mosaic_input,
bgr2rgb=False,
use_gpu=opt.use_gpu,
use_transform=False)
unmosaic_pred = net(mosaic_input)
unmosaic_pred = (unmosaic_pred.cpu().detach().numpy() * 255)[0]
img_fake = unmosaic_pred.transpose((1, 2, 0))
img_result = impro.replace_mosaic(img_origin, img_fake, x, y, size,
opt.no_feather)
cv2.imwrite(os.path.join('./tmp/replace_mosaic', imagepath),
img_result)
ffmpeg.image2video(
fps, './tmp/replace_mosaic/output_%05d.' + opt.tempimage_type,
'./tmp/voice_tmp.mp3',
os.path.join(
opt.result_dir,
os.path.splitext(os.path.basename(path))[0] + '_clean.mp4'))
loss_L2.item(),loss_VGG.item(),psnr,ssmi) )
t_strat = time.time()
'''
--------------------------Test--------------------------
'''
if train_iter % opt.showresult_freq == 0 and os.path.isdir(opt.dataset_test):
show_imgs = []
videos = os.listdir(opt.dataset_test)
sorted(videos)
for video in videos:
frames = os.listdir(os.path.join(opt.dataset_test,video,'image'))
sorted(frames)
for step in range(5):
mosaic_stream = []
for i in range(opt.T):
_mosaic = impro.imread(os.path.join(opt.dataset_test,video,'image',frames[i*opt.S+step]),loadsize=opt.finesize,rgb=True)
mosaic_stream.append(_mosaic)
if step == 0:
previous = impro.imread(os.path.join(opt.dataset_test,video,'image',frames[opt.N*opt.S-1]),loadsize=opt.finesize,rgb=True)
previous = data.im2tensor(previous,bgr2rgb = False, gpu_id = opt.gpu_id, is0_1 = False)
mosaic_stream = (np.array(mosaic_stream).astype(np.float32)/255.0-0.5)/0.5
mosaic_stream = mosaic_stream.reshape(1,opt.T,opt.finesize,opt.finesize,3).transpose((0,4,1,2,3))
mosaic_stream = data.to_tensor(mosaic_stream, opt.gpu_id)
with torch.no_grad():
out = netG(mosaic_stream,previous)
previous = out
show_imgs+= [data.tensor2im(mosaic_stream[:,:,opt.N],rgb2bgr = False),data.tensor2im(out,rgb2bgr = False)]
show_img = impro.splice(show_imgs, (len(videos),2))
TBGlobalWriter.add_image('test', show_img,train_iter,dataformats='HWC')
def cleanmosaic_video_fusion(opt, netG, netM):
path = opt.media_path
N = 25
if 'HD' in os.path.basename(opt.model_path):
INPUT_SIZE = 256
else:
INPUT_SIZE = 128
fps, imagepaths, height, width = video_init(opt, path)
positions = get_mosaic_positions(opt, netM, imagepaths, savemask=True)
t1 = time.time()
if not opt.no_preview:
cv2.namedWindow('clean', cv2.WINDOW_NORMAL)
# clean mosaic
print('Clean Mosaic:')
length = len(imagepaths)
img_pool = np.zeros((height, width, 3 * N), dtype='uint8')
mosaic_input = np.zeros((INPUT_SIZE, INPUT_SIZE, 3 * N + 1), dtype='uint8')
for i, imagepath in enumerate(imagepaths, 0):
x, y, size = positions[i][0], positions[i][1], positions[i][2]
# image read stream
mask = cv2.imread(
os.path.join(opt.temp_dir + '/mosaic_mask', imagepath), 0)
if i == 0:
for j in range(0, N):
img_pool[:, :, j * 3:(j + 1) * 3] = impro.imread(
os.path.join(
opt.temp_dir + '/video2image',
imagepaths[np.clip(i + j - 12, 0,
len(imagepaths) - 1)]))
else:
img_pool[:, :, 0:(N - 1) * 3] = img_pool[:, :, 3:N * 3]
img_pool[:, :, (N - 1) * 3:] = impro.imread(
os.path.join(
opt.temp_dir + '/video2image',
imagepaths[np.clip(i + 12, 0,
len(imagepaths) - 1)]))
img_origin = img_pool[:, :,
int((N - 1) / 2) * 3:(int((N - 1) / 2) + 1) * 3]
img_result = img_origin.copy()
if size > 100:
try: #Avoid unknown errors
#reshape to network input shape
mosaic_input[:, :, 0:N * 3] = impro.resize(
img_pool[y - size:y + size, x - size:x + size, :],
INPUT_SIZE)
mask_input = impro.resize(mask, np.min(
img_origin.shape[:2]))[y - size:y + size,
x - size:x + size]
mosaic_input[:, :, -1] = impro.resize(mask_input, INPUT_SIZE)
mosaic_input_tensor = data.im2tensor(mosaic_input,
bgr2rgb=False,
use_gpu=opt.use_gpu,
use_transform=False,
is0_1=False)
unmosaic_pred = netG(mosaic_input_tensor)
img_fake = data.tensor2im(unmosaic_pred,
rgb2bgr=False,
is0_1=False)
img_result = impro.replace_mosaic(img_origin, img_fake, mask,
x, y, size, opt.no_feather)
except Exception as e:
print('Warning:', e)
cv2.imwrite(os.path.join(opt.temp_dir + '/replace_mosaic', imagepath),
img_result)
#preview result and print
if not opt.no_preview:
cv2.imshow('clean', img_result)
cv2.waitKey(1) & 0xFF
t2 = time.time()
print('\r',
str(i + 1) + '/' + str(length),
util.get_bar(100 * i / length, num=35),
util.counttime(t1, t2, i + 1, len(imagepaths)),
end='')
print()
if not opt.no_preview:
cv2.destroyAllWindows()
ffmpeg.image2video(
fps,
opt.temp_dir + '/replace_mosaic/output_%06d.' + opt.tempimage_type,
opt.temp_dir + '/voice_tmp.mp3',
os.path.join(
opt.result_dir,
os.path.splitext(os.path.basename(path))[0] + '_clean.mp4'))
