('model={:s}', 'vae'),
('z={:02d}', args.z),
('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)
vae = VAE(z_dim=args.z, name=model_name).to(device)
if args.train:
writer = ut.prepare_writer(model_name, overwrite_existing=True)
train(model=vae,
train_loader=train_loader,
labeled_subset=labeled_subset,
device=device,
tqdm=tqdm.tqdm,
writer=writer,
iter_max=args.iter_max,
iter_save=args.iter_save)
ut.evaluate_lower_bound(vae, labeled_subset, run_iwae=args.train == 2)
x = vae.sample_x(100).view(100, 1, 28, 28)
db.printTensor(x)
ImUtil.showBatch(x, show=True)
input('Press key to exit')
else:
ut.load_model_by_name(vae, global_step=args.iter_max)
ut.evaluate_lower_bound(vae, labeled_subset, run_iwae=True)
('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)
vae = VAE(z_dim=args.z, name=model_name).to(device)
if args.train:
writer = ut.prepare_writer(model_name, overwrite_existing=True)
train(model=vae,
train_loader=train_loader,
labeled_subset=labeled_subset,
device=device,
tqdm=tqdm.tqdm,
writer=writer,
iter_max=args.iter_max,
iter_save=args.iter_save)
ut.evaluate_lower_bound(vae, labeled_subset, run_iwae=args.train == 2)
else:
ut.load_model_by_name(vae, global_step=args.iter_max)
# Set run_iwae to false so I could generate the images
ut.evaluate_lower_bound(vae, labeled_subset, run_iwae=False)
samples = vae.sample_x(200)
img = samples.view(200, 1, 28, 28)
utils.save_image(img, "VAEDigitsGrid.png", nrow=20)
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}', 'vae'), ('z={:02d}', args.z),
('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)
vae = VAE(z_dim=args.z, name=model_name).to(device)
ut.load_model_by_name(vae, global_step=args.iter_max)
ut.evaluate_lower_bound(vae, labeled_subset, run_iwae=False)
samples = torch.reshape(vae.sample_x(200), (10, 20, 28, 28))
#print(torch.reshape(vae.sample_x(200), (200, 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()
('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)
vae = VAE(z_dim=args.z, name=model_name).to(device)
if args.train:
writer = ut.prepare_writer(model_name, overwrite_existing=True)
train(model=vae,
train_loader=train_loader,
labeled_subset=labeled_subset,
device=device,
tqdm=tqdm.tqdm,
writer=writer,
iter_max=args.iter_max,
iter_save=args.iter_save)
ut.evaluate_lower_bound(vae, labeled_subset, run_iwae=args.train == 2)
else:
ut.load_model_by_name(vae, global_step=args.iter_max)
ut.evaluate_lower_bound(vae, labeled_subset, run_iwae=True)
if args.sample:
with torch.no_grad():
images = vae.sample_x(200)
save_image(images.view(200, 1, 28, 28), 'vae_sample.png', nrow=20)