def get_problem(config):
# retrieve the parameter of the problem
dataset = config['data']
batch_size, lmbd = config['batch_size'], config['lmbd']
seed = config.get('seed')
# Setup the training constant and a test set
if dataset == 'artificial':
from adaopt.simple_problem_generator import SimpleProblemGenerator
from adaopt.simple_problem_generator import create_dictionary
# retrieve specific parameters for the problem
K, p, rho = config['K'], config['p'], config['rho']
seed_D, corr = config.get('seed_D'), config.get('corr', 0)
D = create_dictionary(K, p, seed=seed_D)
pb = SimpleProblemGenerator(D,
lmbd,
rho=rho,
batch_size=batch_size,
corr=corr,
seed=seed)
elif dataset == 'adverse':
from adaopt.simple_problem_generator import SimpleProblemGenerator
from data_handlers.dictionaries import create_adversarial_dictionary
# retrieve specific parameters for the problem
K, p, rho = config['K'], config['p'], config['rho']
seed_D, corr = config.get('seed_D'), config.get('corr', 0)
D = create_adversarial_dictionary(K, p, seed=seed_D)
pb = SimpleProblemGenerator(D,
lmbd,
rho=rho,
batch_size=batch_size,
corr=corr,
seed=seed)
elif dataset == 'mnist':
from adaopt.mnist_problem_generator import MnistProblemGenerator
from adaopt.mnist_problem_generator import create_dictionary_dl
K, save_dir = config['K'], config['save_dir']
D = create_dictionary_dl(lmbd, K, N=10000, dir_mnist=save_dir)
pb = MnistProblemGenerator(D,
lmbd,
batch_size=batch_size,
dir_mnist=save_dir,
seed=seed)
elif dataset == 'images':
from adaopt.image_problem_generator import ImageProblemGenerator
from adaopt.image_problem_generator import create_dictionary_haar
p = config['p']
D = create_dictionary_haar(p)
pb = ImageProblemGenerator(D, lmbd, batch_size=batch_size, seed=seed)
else:
raise NameError("dataset {} not reconized by the script"
"".format(dataset))
return pb, D
def get_problem(config):
# retrieve the parameter of the problem
dataset = config['data']
batch_size, lmbd = config['batch_size'], config['lmbd']
seed = config.get('seed')
# Setup the training constant and a test set
if dataset == 'artificial':
from adaopt.simple_problem_generator import SimpleProblemGenerator
from adaopt.simple_problem_generator import create_dictionary
# retrieve specific parameters for the problem
K, p, rho = config['K'], config['p'], config['rho']
seed_D, corr = config.get('seed_D'), config.get('corr', 0)
D = create_dictionary(K, p, seed=seed_D)
pb = SimpleProblemGenerator(D, lmbd, rho=rho, batch_size=batch_size,
corr=corr, seed=seed)
elif dataset == 'adverse':
from adaopt.simple_problem_generator import SimpleProblemGenerator
from data_handlers.dictionaries import create_adversarial_dictionary
# retrieve specific parameters for the problem
K, p, rho = config['K'], config['p'], config['rho']
seed_D, corr = config.get('seed_D'), config.get('corr', 0)
D = create_adversarial_dictionary(K, p, seed=seed_D)
pb = SimpleProblemGenerator(D, lmbd, rho=rho, batch_size=batch_size,
corr=corr, seed=seed)
elif dataset == 'mnist':
from adaopt.mnist_problem_generator import MnistProblemGenerator
from adaopt.mnist_problem_generator import create_dictionary_dl
K, save_dir = config['K'], config['save_dir']
D = create_dictionary_dl(lmbd, K, N=10000, dir_mnist=save_dir)
pb = MnistProblemGenerator(D, lmbd, batch_size=batch_size,
dir_mnist=save_dir, seed=seed)
elif dataset == 'images':
from adaopt.image_problem_generator import ImageProblemGenerator
from adaopt.image_problem_generator import create_dictionary_haar
p = config['p']
D = create_dictionary_haar(p)
pb = ImageProblemGenerator(D, lmbd, batch_size=batch_size,
seed=seed)
else:
raise NameError("dataset {} not reconized by the script"
"".format(dataset))
return pb, D
action="store_true",
help='Create a figure with a guassian dictionary')
parser.add_argument('--noshow',
action="store_true",
help='Do not display the graph')
parser.add_argument('--seaborn',
action="store_true",
help='Load the seaborn style')
args = parser.parse_args()
if args.gaussian:
K, p = 100, 64
D = create_gaussian_dictionary(K, p, seed=290890)
else:
K, p = 256, 50
D = create_adversarial_dictionary(K, p, seed=420829)
cmap = sns.cubehelix_palette(8,
start=.5,
rot=-.75,
dark=.2,
reverse=True,
as_cmap=True)
fig = plt.figure("Dictionary")
ax = fig.add_subplot(1, 1, 1)
fig.subplots_adjust(bottom=.12, top=.99, right=.99)
ax.imshow(D.T, aspect=K / p * h / w, cmap=cmap, interpolation="none")
ax.set_xlabel("$m$", fontsize='x-large')
ax.set_ylabel(" $n$", fontsize='x-large')
ax.set_xticks([])
ax.set_yticks([])
parser.add_argument('--save', type=str, default=None,
help='')
parser.add_argument('--gaussian', action="store_true",
help='Create a figure with a guassian dictionary')
parser.add_argument('--noshow', action="store_true",
help='Do not display the graph')
parser.add_argument('--seaborn', action="store_true",
help='Load the seaborn style')
args = parser.parse_args()
if args.gaussian:
K, p = 100, 64
D = create_gaussian_dictionary(K, p, seed=290890)
else:
K, p = 256, 50
D = create_adversarial_dictionary(K, p, seed=420829)
cmap = sns.cubehelix_palette(8, start=.5, rot=-.75, dark=.2, reverse=True,
as_cmap=True)
fig = plt.figure("Dictionary")
ax = fig.add_subplot(1, 1, 1)
fig.subplots_adjust(bottom=.12, top=.99, right=.99)
ax.imshow(D.T, aspect=K/p*h/w, cmap=cmap, interpolation="none")
ax.set_xlabel("$K$", fontsize='xx-large')
ax.set_ylabel("$p$", fontsize='xx-large')
ax.set_xticks([])
ax.set_yticks([])
if args.seaborn:
import seaborn
seaborn.set_color_codes(palette='deep')