train_set = datasets.FashionMNIST(root='../MNIST-data', train=True, download=True, transform=transforms.Compose( [transforms.ToTensor()])) test_set = datasets.MNIST(root='../MNIST-data', train=False, download=True, transform=transforms.Compose([transforms.ToTensor() ])) CNN = False train_loader, labeled_subset, test_set = ut.get_mnist_data( device, train_set, test_set, use_test_subset=True, CNN=CNN) hkvae = HKVAE(rec_weight=args.recw, kl_xy_x_weight=args.kl_xy_xw, kl_xy_y_weight=args.kl_xy_yw, gen_weight=args.gw, class_weight=args.cw, name=model_name, CNN=CNN).to(device) Train = True if Train: writer = ut.prepare_writer(model_name, overwrite_existing=True) train(model=hkvae, train_loader=train_loader, labeled_subset=labeled_subset,
parser.add_argument('--k', type=int, default=500, help="Number mixture components in MoG prior") parser.add_argument('--iter_max', type=int, default=20000, help="Number of training iterations") parser.add_argument('--iter_save', type=int, default=10000, help="Save model every n iterations") parser.add_argument('--run', type=int, default=0, help="Run ID. In case you want to run replicates") args = parser.parse_args() layout = [ ('model={:s}', 'gmvae'), ('z={:02d}', args.z), ('k={:03d}', args.k), ('run={:04d}', args.run) ] model_name = '_'.join([t.format(v) for (t, v) in layout]) pprint(vars(args)) print('Model name:', model_name) device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') train_loader, labeled_subset, _ = ut.get_mnist_data(device, use_test_subset=True) gmvae = GMVAE(z_dim=args.z, k=args.k, name=model_name).to(device) ut.load_model_by_name(gmvae, global_step=args.iter_max) ut.evaluate_lower_bound(gmvae, labeled_subset, run_iwae=False) samples = torch.reshape(gmvae.sample_x(200), (10, 20, 28, 28)) f, axarr = plt.subplots(10,20) for i in range(samples.shape[0]): for j in range(samples.shape[1]): axarr[i,j].imshow(samples[i,j].detach().numpy()) axarr[i,j].axis('off') plt.show()
default=10000, help="Save model every n iterations") parser.add_argument('--run', type=int, default=0, help="Run ID. In case you want to run replicates") parser.add_argument('--train', type=int, default=1, help="Flag for training") args = parser.parse_args() layout = [('model={:s}', 'ssvae'), ('gw={:03d}', args.gw), ('cw={:03d}', args.cw), ('run={:04d}', args.run)] model_name = '_'.join([t.format(v) for (t, v) in layout]) pprint(vars(args)) print('Model name:', model_name) device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') train_loader, labeled_subset, test_set = ut.get_mnist_data( device, use_test_subset=False) ssvae = SSVAE(gen_weight=args.gw, class_weight=args.cw, name=model_name).to(device) if args.train: writer = ut.prepare_writer(model_name, overwrite_existing=True) train(model=ssvae, train_loader=train_loader, labeled_subset=labeled_subset, device=device, y_status='semisup', tqdm=tqdm.tqdm, writer=writer, iter_max=args.iter_max, iter_save=args.iter_save)