generator.load_state_dict( torch.load( 'result/saved_models/train-gan-costmap-vector16-01/generator_6000.pth') ) trajectory_criterion = torch.nn.MSELoss().to(device) e_optimizer = torch.optim.Adam(encoder.parameters(), lr=opt.lr, weight_decay=opt.weight_decay) # param = parse_yaml_file_unsafe('./param_oxford.yaml') # train_loader = DataLoader(OursDataset(param, mode='train', opt=opt), batch_size=opt.batch_size, shuffle=False, num_workers=opt.n_cpu) # train_samples = iter(train_loader) param = parse_yaml_file_unsafe('./param_kitti.yaml') eval_loader = DataLoader(KittiDataset(param, mode='eval', opt=opt), batch_size=1, shuffle=False, num_workers=1) eval_samples = iter(eval_loader) def show_traj(fake_traj, real_traj, t, step): fake_xy = fake_traj x = fake_xy[:, 0] * opt.max_dist y = fake_xy[:, 1] * opt.max_dist real_xy = real_traj real_x = real_xy[:, 0] * opt.max_dist real_y = real_xy[:, 1] * opt.max_dist
start_point_criterion = torch.nn.MSELoss() criterion = torch.nn.BCELoss() #.to(device) trajectory_criterion = torch.nn.MSELoss() g_optimizer = torch.optim.RMSprop(generator.parameters(), lr=opt.lr, weight_decay=opt.weight_decay) #g_optimizer = torch.optim.Adam(generator.parameters(), lr=opt.lr, weight_decay=opt.weight_decay) d_optimizer = torch.optim.RMSprop(discriminator.parameters(), lr=opt.lr, weight_decay=opt.weight_decay) #d_optimizer = torch.optim.Adam(discriminator.parameters(), lr=opt.lr, weight_decay=opt.weight_decay) # train_loader = DataLoader(CostMapDataset(data_index=[item for item in range(1,10)], opt=opt, dataset_path='/media/wang/DATASET/CARLA_HUMAN/town01/'), batch_size=opt.batch_size, shuffle=False, num_workers=opt.n_cpu) # test_loader = DataLoader(CostMapDataset(data_index=[10], opt=opt, dataset_path='/media/wang/DATASET/CARLA_HUMAN/town01/'), batch_size=1, shuffle=False, num_workers=1) # test_samples = iter(test_loader) param = parse_yaml_file_unsafe('./param_oxford.yaml') train_loader = DataLoader(GANDataset(param, mode='train', opt=opt), batch_size=opt.batch_size, shuffle=False, num_workers=opt.n_cpu) train_samples = iter(train_loader) test_loader = DataLoader(GANDataset(param, mode='eval', opt=opt), batch_size=1, shuffle=False, num_workers=1) test_samples = iter(test_loader) def test_traj(xs, ys, step): fig = plt.figure(figsize=(7, 7))
description = 'change costmap' log_path = 'result/log/' + opt.dataset_name + '/' os.makedirs('result/saved_models/%s' % opt.dataset_name, exist_ok=True) os.makedirs('result/output/%s' % opt.dataset_name, exist_ok=True) if not opt.test_mode: logger = SummaryWriter(log_dir=log_path) write_params(log_path, parser, description) model = ModelGRU(256).to(device) #model.load_state_dict(torch.load('result/saved_models/kitti-train-ours-01/model_396000.pth')) criterion = torch.nn.MSELoss().to(device) optimizer = torch.optim.Adam(model.parameters(), lr=opt.lr, weight_decay=opt.weight_decay) param = cu.parse_yaml_file_unsafe( '../../learning/robo_dataset_utils/params/param_kitti.yaml') trajectory_dataset = TrajectoryDataset(param, 'train') #7 dataloader = DataLoader(trajectory_dataset, batch_size=opt.batch_size, shuffle=False, num_workers=opt.n_cpu) eval_trajectory_dataset = TrajectoryDataset(param, 'eval') #2 dataloader_eval = DataLoader(eval_trajectory_dataset, batch_size=1, shuffle=False, num_workers=opt.n_cpu) eval_samples = iter(dataloader_eval) def xy2uv(x, y):
description = 'change costmap' log_path = 'result/log/' + opt.dataset_name + '/' os.makedirs('result/saved_models/%s' % opt.dataset_name, exist_ok=True) os.makedirs('result/output/%s' % opt.dataset_name, exist_ok=True) if not opt.test_mode: logger = SummaryWriter(log_dir=log_path) write_params(log_path, parser, description) model = RNN_MDN(256).to(device) criterion = torch.nn.MSELoss().to(device) optimizer = torch.optim.Adam(model.parameters(), lr=opt.lr, weight_decay=opt.weight_decay) param = cu.parse_yaml_file_unsafe('robo_dataset_utils/params/param_kitti.yaml') trajectory_dataset = TrajectoryDataset_CNNFC(param, 'train') #7 dataloader = DataLoader(trajectory_dataset, batch_size=opt.batch_size, shuffle=False, num_workers=opt.n_cpu) eval_trajectory_dataset = TrajectoryDataset_CNNFC(param, 'eval') #2 dataloader_eval = DataLoader(eval_trajectory_dataset, batch_size=1, shuffle=False, num_workers=1) eval_samples = iter(dataloader_eval) def xy2uv(x, y):
logger = SummaryWriter(log_dir=log_path) write_params(log_path, parser, description) sensor_dict = { 'camera': { 'transform': carla.Transform(carla.Location(x=0.5, y=0.0, z=2.5)), # 'callback':image_callback, }, 'lidar': { 'transform': carla.Transform(carla.Location(x=0.5, y=0.0, z=2.5)), # 'callback':lidar_callback, }, } # param = Param() param = cu.parse_yaml_file_unsafe('./param.yaml') sensor = cu.PesudoSensor(sensor_dict['camera']['transform'], config['camera']) sensor_master = CarlaSensorMaster(sensor, sensor_dict['camera']['transform'], binded=True) # collect_perspective = CollectPerspectiveImage(param, sensor_master) camera_param = cu.CameraParams(sensor) # import pdb; pdb.set_trace() pm = PerspectiveMapping(param, camera_param.K_augment, camera_param.T_img_imu) generator = Generator(opt.vector_dim + 256 + 1 + 1).to(device) discriminator = Discriminator(opt.points_num * 2 + 256 + 1).to(device) encoder = CNN(input_dim=3, out_dim=256).to(device) # discriminator.load_state_dict(torch.load('result/saved_models/train-cgan-12/discriminator_1000.pth')) # generator.load_state_dict(torch.load('result/saved_models/train-cgan-12/generator_1000.pth')) # encoder.load_state_dict(torch.load('result/saved_models/train-cgan-12/encoder_1000.pth'))