def test_sample_image(self): xmask = asarray([ [1, 1], [1, 0]], dtype='bool') ymask = asarray([ [0, 0], [0, 1]], dtype='bool') img_init = asarray([ [1., 2.], [3., 4.]]) model = MCGSM(3, 1) img_sample = sample_image(img_init, model, xmask, ymask) # only the bottom right-pixel should have been replaced self.assertLess(max(abs((img_init - img_sample).ravel()[:3])), 1e-10) # test using preconditioner wt = WhiteningPreconditioner(randn(3, 1000), randn(1, 1000)) sample_image(img_init, model, xmask, ymask, wt) # test what happens if invalid preconditioner is given self.assertRaises(TypeError, sample_image, (img_init, model, xmask, ymask, 10.)) self.assertRaises(TypeError, sample_image, (img_init, model, xmask, ymask, model))
def main(argv):
# load image and turn into grayscale
img = rgb2gray(imread('media/newyork.png'))
# generate data
inputs, outputs = generate_data_from_image(
img, input_mask, output_mask, 220000)
# split data into training, test, and validation sets
inputs = split(inputs, [100000, 200000], 1)
outputs = split(outputs, [100000, 200000], 1)
data_train = inputs[0], outputs[0]
data_test = inputs[1], outputs[1]
data_valid = inputs[2], outputs[2]
# compute normalizing transformation
pre = WhiteningPreconditioner(*data_train)
# intialize model
model = MCGSM(
dim_in=data_train[0].shape[0],
dim_out=data_train[1].shape[0],
num_components=8,
num_scales=4,
num_features=32)
# fit parameters
model.initialize(*pre(*data_train))
model.train(*chain(pre(*data_train), pre(*data_valid)),
parameters={
'verbosity': 1,
'max_iter': 1000,
'threshold': 1e-7,
'val_iter': 5,
'val_look_ahead': 10,
'num_grad': 20,
})
# evaluate model
print 'Average log-likelihood: {0:.4f} [bit/px]'.format(
-model.evaluate(data_test[0], data_test[1], pre))
# synthesize a new image
img_sample = sample_image(img, model, input_mask, output_mask, pre)
imwrite('newyork_sample.png', img_sample,
cmap='gray',
vmin=min(img),
vmax=max(img))
# save model
with open('image_model.pck', 'wb') as handle:
dump({
'model': model,
'input_mask': input_mask,
'output_mask': output_mask}, handle, 1)
return 0
def main(argv):
# load image and turn into grayscale
img = rgb2ycc(imread('media/newyork.png'))
# generate masks for grayscale and color model, respectively
input_mask0, output_mask0 = generate_masks(7, 1)
input_mask1, output_mask1 = generate_masks([5, 7, 7], 1, [1, 0, 0])
# train model
model0, pre0 = train_model(img[:, :, 0], input_mask0, output_mask0)
model1, pre1 = train_model(img, input_mask1, output_mask1)
# synthesize a new image
img_sample = img.copy()
# sample intensities
img_sample[:, :, 0] = sample_image(img_sample[:, :, 0], model0,
input_mask0, output_mask0, pre0)
# sample color
img_sample = sample_image(img_sample, model1, input_mask1, output_mask1,
pre1)
# convert back to RGB and enforce constraints
img_sample = ycc2rgb(img_sample)
imwrite('newyork_sample.png', img_sample, vmin=0, vmax=255)
# save model
with open('image_model.pck', 'wb') as handle:
dump(
{
'model0': model0,
'model1': model1,
'input_mask0': input_mask0,
'input_mask1': input_mask1,
'output_mask0': output_mask0,
'output_mask1': output_mask1
}, handle, 1)
return 0
def test_sample_image(self):
xmask = asarray([[1, 1], [1, 0]], dtype='bool')
ymask = asarray([[0, 0], [0, 1]], dtype='bool')
img_init = asarray([[1., 2.], [3., 4.]])
model = MCGSM(3, 1)
img_sample = sample_image(img_init, model, xmask, ymask)
# only the bottom right-pixel should have been replaced
self.assertLess(max(abs((img_init - img_sample).ravel()[:3])), 1e-10)
# test using preconditioner
wt = WhiteningPreconditioner(randn(3, 1000), randn(1, 1000))
sample_image(img_init, model, xmask, ymask, wt)
# test what happens if invalid preconditioner is given
self.assertRaises(TypeError, sample_image,
(img_init, model, xmask, ymask, 10.))
self.assertRaises(TypeError, sample_image,
(img_init, model, xmask, ymask, model))
def main(argv):
# load image and turn into grayscale
img = rgb2ycc(imread('media/newyork.png'))
# generate masks for grayscale and color model, respectively
input_mask0, output_mask0 = generate_masks(7, 1)
input_mask1, output_mask1 = generate_masks([5, 7, 7], 1, [1, 0, 0])
# train model
model0, pre0 = train_model(img[:, :, 0], input_mask0, output_mask0)
model1, pre1 = train_model(img, input_mask1, output_mask1)
# synthesize a new image
img_sample = img.copy()
# sample intensities
img_sample[:, :, 0] = sample_image(
img_sample[:, :, 0], model0, input_mask0, output_mask0, pre0)
# sample color
img_sample = sample_image(
img_sample, model1, input_mask1, output_mask1, pre1)
# convert back to RGB and enforce constraints
img_sample = ycc2rgb(img_sample)
imwrite('newyork_sample.png', img_sample, vmin=0, vmax=255)
# save model
with open('image_model.pck', 'wb') as handle:
dump({
'model0': model0,
'model1': model1,
'input_mask0': input_mask0,
'input_mask1': input_mask1,
'output_mask0': output_mask0,
'output_mask1': output_mask1}, handle, 1)
return 0
def main(argv):
experiment = Experiment()
parser = ArgumentParser(argv[0], description=__doc__)
parser.add_argument('--model', '-m', type=str, required=True)
parser.add_argument('--data',
'-d',
type=str,
default='data/deadleaves_train.mat')
parser.add_argument('--width', '-W', type=int, default=512)
parser.add_argument('--height', '-H', type=int, default=512)
parser.add_argument('--crop', '-C', type=int, default=16)
parser.add_argument('--log', '-L', type=int, default=0)
parser.add_argument('--output',
'-o',
type=str,
default='results/sample.png')
args = parser.parse_args(argv[1:])
images = loadmat(args.data)['data']
vmin = percentile(images, 0.02)
vmax = percentile(images, 98.)
experiment = Experiment(args.model)
img = empty([args.height + args.crop, args.width + 2 * args.crop])
img.ravel()[:] = images.ravel()[random_select(img.size, images.size)]
img = sample_image(img,
experiment['model'],
experiment['input_mask'],
experiment['output_mask'],
experiment['preconditioner'],
min_value=vmin,
max_value=vmax)
if args.log:
# linearize and gamma-correct
img = power(exp(img), .45)
vmin = power(exp(vmin), .45)
vmax = power(exp(vmax), .45)
imwrite(
args.output,
imformat(img[args.crop:, args.crop:-args.crop],
vmin=vmin,
vmax=vmax,
symmetric=False))
savez('sample.npz', sample=img)
return 0
def main(argv):
experiment = Experiment()
parser = ArgumentParser(argv[0], description=__doc__)
parser.add_argument('--model', '-m', type=str, required=True)
parser.add_argument('--data', '-d', type=str, default='data/deadleaves_train.mat')
parser.add_argument('--width', '-W', type=int, default=512)
parser.add_argument('--height', '-H', type=int, default=512)
parser.add_argument('--crop', '-C', type=int, default=16)
parser.add_argument('--log', '-L', type=int, default=0)
parser.add_argument('--output', '-o', type=str, default='results/sample.png')
args = parser.parse_args(argv[1:])
images = loadmat(args.data)['data']
vmin = percentile(images, 0.02)
vmax = percentile(images, 98.)
experiment = Experiment(args.model)
img = empty([args.height + args.crop, args.width + 2 * args.crop])
img.ravel()[:] = images.ravel()[random_select(img.size, images.size)]
img = sample_image(
img,
experiment['model'],
experiment['input_mask'],
experiment['output_mask'],
experiment['preconditioner'],
min_value=vmin,
max_value=vmax)
if args.log:
# linearize and gamma-correct
img = power(exp(img), .45)
vmin = power(exp(vmin), .45)
vmax = power(exp(vmax), .45)
imwrite(args.output, imformat(img[args.crop:, args.crop:-args.crop], vmin=vmin, vmax=vmax, symmetric=False))
savez('sample.npz', sample=img)
return 0
def main(argv):
# load image and turn into grayscale
img = rgb2gray(imread('media/newyork.png'))
# generate data
inputs, outputs = generate_data_from_image(img, input_mask, output_mask,
220000)
# split data into training, test, and validation sets
inputs = split(inputs, [100000, 200000], 1)
outputs = split(outputs, [100000, 200000], 1)
data_train = inputs[0], outputs[0]
data_test = inputs[1], outputs[1]
data_valid = inputs[2], outputs[2]
# compute normalizing transformation
pre = WhiteningPreconditioner(*data_train)
# intialize model
model = MCGSM(dim_in=data_train[0].shape[0],
dim_out=data_train[1].shape[0],
num_components=8,
num_scales=4,
num_features=32)
# fit parameters
model.initialize(*pre(*data_train))
model.train(*chain(pre(*data_train), pre(*data_valid)),
parameters={
'verbosity': 1,
'max_iter': 1000,
'threshold': 1e-7,
'val_iter': 5,
'val_look_ahead': 10,
'num_grad': 20,
})
# evaluate model
print 'Average log-likelihood: {0:.4f} [bit/px]'.format(
-model.evaluate(data_test[0], data_test[1], pre))
# synthesize a new image
img_sample = sample_image(img, model, input_mask, output_mask, pre)
imwrite('newyork_sample.png',
img_sample,
cmap='gray',
vmin=min(img),
vmax=max(img))
# save model
with open('image_model.pck', 'wb') as handle:
dump(
{
'model': model,
'input_mask': input_mask,
'output_mask': output_mask
}, handle, 1)
return 0
