logger = SummaryWriter(log_dir=log_path)
model = ModelMixStyleWithV().to(device)
optimizer = torch.optim.Adam(model.parameters(),
lr=3e-4,
weight_decay=opt.weight_decay)
param = parse_yaml_file_unsafe('./param_oxford.yaml')
train_loader = DataLoader(DIVADataset(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_trajectory_dataset = KittiDataset(param, 'eval', opt) #2
dataloader_eval = DataLoader(eval_trajectory_dataset,
batch_size=1,
shuffle=False,
num_workers=1)
eval_samples = iter(dataloader_eval)
criterion = nn.MSELoss().to(device)
criterion_l1 = nn.SmoothL1Loss().to(device)
trajectory_criterion = torch.nn.MSELoss().to(device)
def show_traj_with_uncertainty(fake_traj,
real_traj,
step,
model_index,
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
max_x = 30.
trajectory_criterion = torch.nn.MSELoss().to(device)
latent_criterion = torch.nn.MSELoss().to(device)
e_optimizer = torch.optim.Adam(encoder.parameters(), lr=opt.lr, weight_decay=opt.weight_decay)
discriminator = Discriminator(input_dim=opt.vector_dim*2, output=1).to(device)
discriminator_criterion = nn.BCEWithLogitsLoss().to(device)
d_optimizer = torch.optim.Adam(discriminator.parameters(), lr=3e-4, weight_decay=opt.weight_decay)
param = parse_yaml_file_unsafe('./param_oxford.yaml')
train_loader = DataLoader(DIVADataset(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, img=None):
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
max_x = 30.
max_y = 30.
fig = plt.figure(figsize=(7, 7))