def imgint(img1, img2):
warnings.filterwarnings("ignore")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
torch.set_grad_enabled(False)
if torch.cuda.is_available():
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True
# parser = argparse.ArgumentParser(description='Interpolation for a pair of images')
# parser.add_argument('--img', dest='img', nargs=2, required=True)
# parser.add_argument('--exp', default=4, type=int)
# args = parser.parse_args()
model = Model()
model.load_model('./train_log', -1)
model.eval()
model.device()
open_cv_image1 = np.array(img1)
# Convert RGB to BGR
open_cv_image1 = open_cv_image1[:, :, ::-1].copy()
open_cv_image2 = np.array(img2)
# Convert RGB to BGR
open_cv_image2 = open_cv_image2[:, :, ::-1].copy()
img0 = open_cv_image1
img1 = open_cv_image2
img0 = (torch.tensor(img0.transpose(2, 0, 1)).to(device) / 255.).unsqueeze(0)
img1 = (torch.tensor(img1.transpose(2, 0, 1)).to(device) / 255.).unsqueeze(0)
n, c, h, w = img0.shape
ph = ((h - 1) // 32 + 1) * 32
pw = ((w - 1) // 32 + 1) * 32
padding = (0, pw - w, 0, ph - h)
img0 = F.pad(img0, padding)
img1 = F.pad(img1, padding)
img_list = [img0, img1]
for i in range(4):
tmp = []
for j in range(len(img_list) - 1):
mid = model.inference(img_list[j], img_list[j + 1])
tmp.append(img_list[j])
tmp.append(mid)
tmp.append(img1)
img_list = tmp
# if not os.path.exists('output'):
# os.mkdir('output')
return img_list, h, w
write_buffer = Queue(maxsize=mp.cpu_count() - 3)
incoming_read_buffer = Queue(maxsize=500)
outgoing_read_buffer = Queue(maxsize=500)
_thread.start_new_thread(
build_read_buffer,
(args.incoming, incoming_read_buffer, incoming_files_list))
_thread.start_new_thread(
build_read_buffer,
(args.outgoing, outgoing_read_buffer, outgoing_files_list))
if 'v1.8.model' in args.model:
from model.RIFE_HD import Model # type: ignore
else:
from model.RIFE_HDv2 import Model # type: ignore
model = Model()
model.load_model(args.model, -1)
model.eval()
model.device()
print('Trained model loaded: %s' % args.model)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
if torch.cuda.is_available():
torch.set_grad_enabled(False)
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True
_thread.start_new_thread(clear_write_buffer,
(args.output, write_buffer, input_duration))
rstep = 1 / (input_duration + 1)
writer_val.add_scalar('psnr', np.array(psnr_list).mean(), nr_eval)
if __name__ == "__main__":
parser = argparse.ArgumentParser(description='slomo')
parser.add_argument('--epoch', default=300, type=int)
parser.add_argument('--batch_size',
default=16,
type=int,
help='minibatch size')
parser.add_argument('--local_rank', default=0, type=int, help='local rank')
parser.add_argument('--world_size', default=4, type=int, help='world size')
parser.add_argument('--model',
dest='model',
type=str,
default='./trained_models/default/v1.8.model')
args = parser.parse_args()
torch.distributed.init_process_group(backend="nccl",
world_size=args.world_size)
torch.cuda.set_device(args.local_rank)
device = torch.device("cuda", args.local_rank)
seed = 1234
random.seed(seed)
np.random.seed(seed)
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed)
torch.backends.cudnn.benchmark = True
model = Model(args.local_rank)
model.load_model(args.model, args.local_rank)
train(model, args.local_rank)
import warnings
warnings.filterwarnings("ignore")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
torch.set_grad_enabled(False)
if torch.cuda.is_available():
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True
parser = argparse.ArgumentParser(
description='Interpolation for a pair of images')
parser.add_argument('--img', dest='img', nargs=2, required=True)
parser.add_argument('--exp', default=4, type=int)
args = parser.parse_args()
model = Model()
model.load_model('./train_log', -1)
model.eval()
model.device()
if args.img[0].endswith('.exr') and args.img[1].endswith('.exr'):
img0 = cv2.imread(args.img[0], cv2.IMREAD_COLOR | cv2.IMREAD_ANYDEPTH)
img1 = cv2.imread(args.img[1], cv2.IMREAD_COLOR | cv2.IMREAD_ANYDEPTH)
img0 = (torch.tensor(img0.transpose(2, 0, 1)).to(device)).unsqueeze(0)
img1 = (torch.tensor(img1.transpose(2, 0, 1)).to(device)).unsqueeze(0)
else:
img0 = cv2.imread(args.img[0])
img1 = cv2.imread(args.img[1])
img0 = (torch.tensor(img0.transpose(2, 0, 1)).to(device) /
255.).unsqueeze(0)
dest='png',
action='store_true',
help='whether to vid_out png format vid_outs')
parser.add_argument('--ext',
dest='ext',
type=str,
default='mp4',
help='vid_out video extension')
parser.add_argument('--exp', dest='exp', type=int, default=1)
args = parser.parse_args()
assert (not args.video is None or not args.img is None)
if not args.img is None:
args.png = True
from model.RIFE_HD import Model
model = Model()
model.load_model('./train_log', -1)
model.eval()
model.device()
if not args.video is None:
videoCapture = cv2.VideoCapture(args.video)
fps = videoCapture.get(cv2.CAP_PROP_FPS)
tot_frame = videoCapture.get(cv2.CAP_PROP_FRAME_COUNT)
videoCapture.release()
if args.fps is None:
fpsNotAssigned = True
args.fps = fps * (2**args.exp)
else:
fpsNotAssigned = False
videogen = skvideo.io.vreader(args.video)
# interpolation progression
first_half = make_inference(I0, middle, exp=exp - 1, sec_batch=True)
second_half = make_inference(middle, I1, exp=exp - 1, sec_batch=True)
# return 3 imgs
return [*first_half, middle, *second_half]
if args.img:
args.png = True
if args.model == 1:
from model.RIFE_HD import Model
else:
from model.RIFE_HDv2 import Model
model = Model()
model_path = os.path.join(os.path.dirname(os.path.realpath(__file__)),
'train_log')
# Pls Manually Mkdir for train_log\1.8, train_log\2.0 to store datasets for RIFE
model_v1 = os.path.join(model_path, "1.8")
model_v2 = os.path.join(model_path, "2.0")
if os.path.exists(model_v1) and args.model == 1:
model.load_model(model_v1, -1)
elif os.path.exists(model_v2) and args.model == 2:
model.load_model(model_v2, -1)
else:
model.load_model(
os.path.join(os.path.dirname(os.path.realpath(__file__)), 'train_log'),
-1)
model.eval()
import warnings
warnings.filterwarnings("ignore")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
torch.set_grad_enabled(False)
if torch.cuda.is_available():
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True
parser = argparse.ArgumentParser(
description='Interpolation for a pair of images')
parser.add_argument('--img', dest='img', nargs=2, required=True)
parser.add_argument('--exp', default=4, type=int)
args = parser.parse_args()
model = Model()
model.load_model(
os.path.join(os.path.dirname(os.path.realpath(__file__)), 'train_log'), -1)
model.eval()
model.device()
if args.img[0].endswith('.exr') and args.img[1].endswith('.exr'):
img0 = cv2.imread(args.img[0], cv2.IMREAD_COLOR | cv2.IMREAD_ANYDEPTH)
img1 = cv2.imread(args.img[1], cv2.IMREAD_COLOR | cv2.IMREAD_ANYDEPTH)
img0 = (torch.tensor(img0.transpose(2, 0, 1)).to(device)).unsqueeze(0)
img1 = (torch.tensor(img1.transpose(2, 0, 1)).to(device)).unsqueeze(0)
else:
img0 = cv2.imread(args.img[0])
img1 = cv2.imread(args.img[1])
img0 = (torch.tensor(img0.transpose(2, 0, 1)).to(device) /
