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_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,
gray=False,
use_transform=True)
img = net(img)
img = data.tensor2im(img)
return img
def loadimage(imagepaths, maskpaths, opt, test_flag=False):
batchsize = len(imagepaths)
images = np.zeros((batchsize, 3, opt.finesize, opt.finesize),
dtype=np.float32)
masks = np.zeros((batchsize, 1, opt.finesize, opt.finesize),
dtype=np.float32)
for i in range(len(imagepaths)):
img = impro.resize(impro.imread(imagepaths[i]), opt.loadsize)
mask = impro.resize(impro.imread(maskpaths[i], mod='gray'),
opt.loadsize)
img, mask = data.random_transform_image(img, mask, opt.finesize,
test_flag)
images[i] = (img.transpose((2, 0, 1)) / 255.0)
masks[i] = (mask.reshape(1, 1, opt.finesize, opt.finesize) / 255.0)
images = Totensor(images, opt.use_gpu)
masks = Totensor(masks, opt.use_gpu)
return images, masks
def run_segment(img, net, size=360, use_gpu=True):
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 = opt.N
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'))
mask_avg = mask.astype(np.float64)
mask_flag = True
else:
mask_avg += mask.astype(np.float64)
mask_avg = np.clip(mask_avg / len(imagepaths), 0, 255).astype('uint8')
mask_avg = impro.mask_threshold(mask_avg, 20, 64)
if not opt.all_mosaic_area:
mask_avg = impro.find_mostlikely_ROI(mask_avg)
# x, y, size, area = impro.boundingSquare(mask_avg, Ex_mul=random.uniform(1.1, 1.5))
cnt = 0
for i in range(len(imagepaths)):
x, y, size, area = impro.boundingSquare(masks[i], Ex_mul=1.5)
if area > opt.minmaskarea and size > opt.minsize * 1.5 and impro.Q_lapulase(imgs[i]) > opt.quality:
img = impro.resize(imgs[i][y - size:y + size, x - size:x + size], opt.outsize, interpolation=cv2.INTER_CUBIC)
mask = impro.resize(masks[i][y - size:y + size, x - size:x + size], opt.outsize, interpolation=cv2.INTER_CUBIC)
img_mosaic = mosaic.addmosaic_random(img, mask)
cv2.imwrite(os.path.join(test_A_path, str(0) + '_' + '%05d' % (i + 1) + '.jpg'), img_mosaic)
cv2.imwrite(os.path.join(test_B_path, str(0) + '_' + '%05d' % (i + 1) + '.jpg'), img)
else:
print(imagepaths[i])
cnt += 1
print("bad pic:", cnt)
'''
python3 z_make_images_dataset.py --datadir ../datasets/demosaic/video2images --savedir ../datasets/demosaic
'''