def handle2x(config, args):
# resize input
h1, w1, scale1 = pad_to_height(config.img_size[0], args.img1_height, args.img1_width)
h2, w2, scale2 = pad_to_height(config.img_size[0], args.img2_height, args.img2_width)
# load trained model
net = get_autoencoder(config)
net.load_state_dict(torch.load(args.model_path))
net.to(config.device)
net.eval()
# mean/std pose
mean_pose, std_pose = get_meanpose(config)
# get input
input1 = openpose2motion(args.vid1_json_dir, scale=scale1, max_frame=args.max_length)
input2 = openpose2motion(args.vid2_json_dir, scale=scale2, max_frame=args.max_length)
input1 = preprocess_motion2d(input1, mean_pose, std_pose)
input2 = preprocess_motion2d(input2, mean_pose, std_pose)
input1 = input1.to(config.device)
input2 = input2.to(config.device)
# transfer by network
out12 = net.transfer(input1, input2)
out21 = net.transfer(input2, input1)
# postprocessing the outputs
input1 = postprocess_motion2d(input1, mean_pose, std_pose, w1 // 2, h1 // 2)
input2 = postprocess_motion2d(input2, mean_pose, std_pose, w2 // 2, h2 // 2)
out12 = postprocess_motion2d(out12, mean_pose, std_pose, w2 // 2, h2 // 2)
out21 = postprocess_motion2d(out21, mean_pose, std_pose, w1 // 2, h1 // 2)
if not args.disable_smooth:
out12 = gaussian_filter1d(out12, sigma=2, axis=-1)
out21 = gaussian_filter1d(out21, sigma=2, axis=-1)
if args.out_dir is not None:
save_dir = args.out_dir
ensure_dir(save_dir)
color1 = hex2rgb(args.color1)
color2 = hex2rgb(args.color2)
np.savez(os.path.join(save_dir, 'results.npz'),
input1=input1,
input2=input2,
out12=out12,
out21=out21)
if args.render_video:
print("Generating videos...")
motion2video(input1, h1, w1, os.path.join(save_dir, 'input1.mp4'), color1, args.transparency,
fps=args.fps, save_frame=args.save_frame)
motion2video(input2, h2, w2, os.path.join(save_dir,'input2.mp4'), color2, args.transparency,
fps=args.fps, save_frame=args.save_frame)
motion2video(out12, h2, w2, os.path.join(save_dir,'out12.mp4'), color2, args.transparency,
fps=args.fps, save_frame=args.save_frame)
motion2video(out21, h1, w1, os.path.join(save_dir,'out21.mp4'), color1, args.transparency,
fps=args.fps, save_frame=args.save_frame)
print("Done.")
def motion_feature_extract(config, args):
# resize input
h1, w1, scale1 = pad_to_height(config.img_size[0], args.img1_height, args.img1_width)
# load trained model
net = get_autoencoder(config)
net.load_state_dict(torch.load(args.model_path))
net.to(config.device)
net.eval()
# mean/std pose
mean_pose, std_pose = get_meanpose(config)
# get input
input1 = openpose2motion(args.vid1_json_dir, scale=scale1, max_frame=args.max_length)
print("after motion")
print(input1.shape)
input1 = preprocess_motion2d(input1, mean_pose, std_pose)
print("after preprocess")
print(input1.shape)
if args.out_dir is not None:
save_dir = args.out_dir
ensure_dir(save_dir)
# color1 = hex2rgb(args.color1)
# color2 = hex2rgb(args.color2)
np.savez(os.path.join(save_dir, 'pose_feature.npz'), pose=input1)
input1 = input1.to(config.device)
# transfer by network
# out = net.transfer_three(input1, input2, input3)
out = net.forward(input1)
mot = net.mot_encoder(input1)
print(mot.shape)
# postprocessing the outputs
input1 = postprocess_motion2d(input1, mean_pose, std_pose, w1 // 2, h1 // 2)
out = postprocess_motion2d(out, mean_pose, std_pose, w1 // 2, h1 // 2)
print("after postprocess")
print(input1.shape)
if not args.disable_smooth:
out = gaussian_filter1d(out, sigma=2, axis=-1)
# if args.out_dir is not None:
# save_dir = args.out_dir
# ensure_dir(save_dir)
# # color1 = hex2rgb(args.color1)
# # color2 = hex2rgb(args.color2)
# np.savez(os.path.join(save_dir, 'results.npz'), pose=input1)
# input1=input1,
# input2=input2,
# input3=input3,
# out=out)
# if args.render_video:
# print("Generating videos...")
# motion2video(input1, h1, w1, os.path.join(save_dir,'input1.mp4'), color1, args.transparency,
# fps=args.fps, save_frame=args.save_frame)
# motion2video(input2, h2, w2, os.path.join(save_dir,'input2.mp4'), color2, args.transparency,
# fps=args.fps, save_frame=args.save_frame)
# motion2video(input3, h3, w3, os.path.join(save_dir,'input3.mp4'), color3, args.transparency,
# fps=args.fps, save_frame=args.save_frame)
# motion2video(out, h1, w1, os.path.join(save_dir,'out.mp4'), color2, args.transparency,
# fps=args.fps, save_frame=args.save_frame)
print("Done.")
parser.add_argument('--color1', type=str, default='#ff0000##aa0000#550000', help='color1')
parser.add_argument('--color2', type=str, default='#0000ff#0000aa#000055', help='color2')
parser.add_argument('-ch', '--cell_height', type=int, default=128, help="cell's height when saving the video")
parser.add_argument('--max_length', type=int, default=120, help='maximum input video length')
parser.add_argument('--transparency', action='store_true', help="make background transparent in resulting frames")
parser.add_argument('-g', '--gpu_ids', type=int, default=0, required=False)
args = parser.parse_args()
config.initialize(args)
# if keep no attribute, interpolate over all three latent space
if args.keep_attr == 'none':
assert args.form == 'line'
# clip and pad the video
h1, w1, scale1 = pad_to_height(config.img_size[0], args.img1_height, args.img1_width)
h2, w2, scale2 = pad_to_height(config.img_size[0], args.img2_height, args.img2_width)
# load trained model
net = get_autoencoder(config)
net.load_state_dict(torch.load(args.model_path))
net.to(config.device)
net.eval()
# mean/std pose
mean_pose, std_pose = get_meanpose(config)
# process input data
input1 = openpose2motion(args.vid1_json_dir, scale=scale1, max_frame=args.max_length)
input2 = openpose2motion(args.vid2_json_dir, scale=scale2, max_frame=args.max_length)
if input1.shape[-1] != input2.shape[-1]: