M = 10
values, times = initialize_tree(tree, D)
def a(t):
return c / (1 - t)
def log_a(t):
return T.log(c / (1 - t))
def A(t):
return -c * T.log(1 - t)
def create_harmonic(M):
return np.cumsum(1.0 / np.arange(1, M + 1)).astype(np.float32)
T.set_default_device('/cpu:0')
c = T.scalar(name='c')
segments = T.matrix(dtype='int32', name='segments')
a_idx = segments[:, 0]
b_idx = segments[:, 1]
leaf_segment = segments[:, 2]
m = segments[:, 3]
log_fac = segments[:, 4]
x = T.matrix(name='x')
e = T.matrix(name='e')
q_network = Vector(X.shape[1], placeholder=x, is_input=False) >> Repeat(Tanh(200), 2)
q_mu_network = q_network >> Linear(D)
q_mu = q_mu_network.get_outputs()[0].get_placeholder()
from deep_trees.util import load_mnist, sample_minibatch
from deep_trees.likelihood import VAE, BernoulliLikelihoodModel
def parse_args():
argparser = ArgumentParser()
argparser.add_argument('--subset_size', type=int, default=1000)
argparser.add_argument('--embedding_size', type=int, default=20)
argparser.add_argument('--default_device', default='/cpu:0')
argparser.add_argument('--no-tree', action='store_true')
argparser.add_argument('--batch_size', type=int, default=100)
return argparser.parse_args()
if __name__ == "__main__":
args = parse_args()
T.set_default_device(args.default_device)
# X, y = load_mnist(args.subset_size, one_hot=False)
X, y = np.eye(args.subset_size).astype(np.float32), np.ones(args.subset_size)
N, D = X.shape
p_network = Tanh(5)
q_network = Tanh(5)
print("Creating tree prior...")
if args.no_tree:
tree_prior = GaussianPrior(N, args.embedding_size)
else:
tree_prior = DDTPrior(N, args.embedding_size, c=0.1, sigma0=1)
print("Creating likelihood model...")
likelihood_model = BernoulliLikelihoodModel(args.embedding_size, D, p_network)