action='store_true',
default=False,
help='Disables plot of train/test losses')
parser.add_argument(
'--no-print',
action='store_true',
default=False,
help='Disables print of reached best values of metrics')
args = parser.parse_args()
if args.cp_path is None:
raise ValueError(
'There is no checkpoint/model path. Use arg --cp-path to indicate the path!'
)
generator = model_.Generator_toy(512)
ckpt = torch.load(args.cp_path, map_location=lambda storage, loc: storage)
generator.load_state_dict(ckpt['model_state'])
history = ckpt['history']
if not args.no_plots:
plot_learningcurves(history, 'gen_loss')
plot_learningcurves(history, 'disc_loss')
plot_learningcurves(history, 'FD')
plot_learningcurves(history, 'quality_samples')
plot_learningcurves(history, 'quality_modes')
if not args.no_print:
args.cuda = True if not args.no_cuda and torch.cuda.is_available() else False
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)
toy_data = ToyData(args.toy_dataset, args.toy_length)
train_loader = torch.utils.data.DataLoader(toy_data,
batch_size=args.batch_size,
num_workers=args.workers)
centers = toy_data.get_centers()
cov = toy_data.get_cov()
# hidden_size = 512
generator = model.Generator_toy(512).train()
disc = model.Discriminator_toy(512, optim.Adam, args.lr,
(args.beta1, args.beta2)).train()
optimizer = optim.Adam(generator.parameters(),
lr=args.lr,
betas=(args.beta1, args.beta2))
trainer = TrainLoop(generator,
disc,
optimizer,
args.toy_dataset,
centers,
cov,
train_loader=train_loader,