def show_samples(model,
config,
pdf=None,
visdom=None,
size=32,
title="Generated images"):
'''Plot samples from a generative model in [pdf] and/or in [visdom].'''
# Set model to evaluation-mode
mode = model.training
model.eval()
# Generate samples from the model
sample, labels = model.sample(size)
image_tensor = sample.view(-1, config['channels'], config['size'],
config['size']).cpu()
# Plot generated images in [pdf] and/or [visdom]
if pdf is not None:
visual_plt.plot_images_from_tensor(image_tensor, pdf, title=title)
if visdom is not None:
visual_visdom.visualize_images(tensor=image_tensor,
name='generated samples ({})'.format(
visdom["graph"]),
env=visdom["env"])
# Set model back to initial mode
model.train(mode=mode)
def show_reconstruction(model,
dataset,
config,
pdf=None,
visdom=None,
size=32,
task=None,
collate_fn=None):
'''Plot reconstructed examples by an auto-encoder [model] on [dataset], in [pdf] and/or in [visdom].'''
# Set model to evaluation-mode
mode = model.training
model.eval()
# Get data
data_loader = utils.get_data_loader(dataset,
size,
shuffle=False,
cuda=model._is_on_cuda(),
collate_fn=collate_fn)
(data, labels) = next(iter(data_loader))
data, labels = data.to(model._device()), labels.to(model._device())
# Evaluate model
with torch.no_grad():
recon_batch, y_hat, mu, logvar, z = model(data, full=True)
# Plot original and reconstructed images
comparison = torch.cat([
data.view(-1, config['channels'], config['size'],
config['size'])[:size],
recon_batch.view(-1, config['channels'], config['size'],
config['size'])[:size]
]).cpu()
image_tensor = comparison.view(-1, config['channels'], config['size'],
config['size'])
# -number of rows
nrow = int(np.ceil(np.sqrt(size * 2)))
# -make plots
if pdf is not None:
task_stm = "" if task is None else " (task {})".format(task)
visual_plt.plot_images_from_tensor(image_tensor,
pdf,
nrow=nrow,
title="Reconstructions" + task_stm)
if visdom is not None:
visual_visdom.visualize_images(
tensor=image_tensor,
name='Reconstructions ({})'.format(visdom["graph"]),
env=visdom["env"],
nrow=nrow,
)
# Set model back to initial mode
model.train(mode=mode)
def show_reconstruction(model,
dataset,
config,
pdf=None,
visdom=None,
size=32,
task=None,
collate_fn=None):
'''Plot reconstructed examples by an auto-encoder [model] on [dataset], in [pdf] and/or in [visdom].'''
cuda = model._is_on_cuda()
# Set model to evaluation-mode
mode = model.training
model.eval()
# Get data
data_loader = utils.get_data_loader(dataset,
size,
cuda=cuda,
collate_fn=collate_fn)
(data, labels) = next(iter(data_loader))
# Evaluate model
data = Variable(data, volatile=True).cuda() if cuda else Variable(
data, volatile=True)
recon_batch, y_hat, mu, logvar, z = model(data, full=True)
# Plot original and reconstructed images
comparison = torch.cat([
data.view(-1, config['channels'], config['size'],
config['size'])[:size],
recon_batch.view(-1, config['channels'], config['size'],
config['size'])[:size]
]).cpu()
image_tensor = comparison.data.view(-1, config['channels'], config['size'],
config['size'])
if pdf is not None:
task_stm = "" if task is None else " (task {})".format(task)
visual_plt.plot_images_from_tensor(image_tensor,
pdf,
nrow=8,
title="Reconstructions" + task_stm)
if visdom is not None:
visual_visdom.visualize_images(
tensor=image_tensor,
name='reconstructed samples ({})'.format(visdom["graph"]),
env=visdom["env"],
)
# Set model back to initial mode
model.train(mode=mode)
