def generator(Z, out_dim):
layer = [layers.Dense(Z, 16)]
layer.append(layers.Activation(layer[-1], T.leaky_relu))
layer.append(layers.Dense(layer[-1], 16))
layer.append(layers.Activation(layer[-1], T.leaky_relu))
layer.append(layers.Dense(layer[-1], out_dim))
return layer
def encoder(X, latent_dim):
layer = [layers.Dense(X, 32)]
layer.append(layers.Activation(layer[-1], T.leaky_relu))
layer.append(layers.Dense(layer[-1], 32))
layer.append(layers.Activation(layer[-1], T.leaky_relu))
layer.append(layers.Dense(layer[-1], latent_dim * 2))
return layer
def discriminator(X):
layer = [layers.Dense(X, 32)]
layer.append(layers.Activation(layer[-1], T.leaky_relu))
layer.append(layers.Dense(layer[-1], 32))
layer.append(layers.Activation(layer[-1], T.leaky_relu))
layer.append(layers.Dense(layer[-1], 2))
return layer
label = T.Placeholder((BS, ), 'int32')
deterministic = T.Placeholder((1, ), 'bool')
# first layer
NN = 32
if L > 0:
x, y, = T.meshgrid(T.linspace(-5, 5, NN), T.linspace(-5, 5, NN))
grid = T.stack([x.flatten(), y.flatten()], 1)
cov = T.Variable(np.eye(2), name='cov')
gaussian = T.exp(-(grid.dot(cov.T().dot(cov)) * grid).sum(1)).reshape(
(1, 1, NN, NN))
layer = [
layers.Conv2D(tf, 1, (NN, NN), strides=(6, 6), W=gaussian, b=None)
]
layer[-1].add_variable(cov)
layer.append(layers.Activation(layer[-1],
lambda x: T.log(T.abs(x) + 0.01)))
else:
layer = [layers.Activation(tf + 0.01, T.log)]
layer.append(layers.Conv2D(layer[-1], 16, (3, 3)))
layer.append(layers.BatchNormalization(layer[-1], [0, 2, 3], deterministic))
layer.append(layers.Activation(layer[-1], T.leaky_relu))
layer.append(layers.Pool2D(layer[-1], (3, 3)))
layer.append(layers.Conv2D(layer[-1], 16, (3, 3)))
layer.append(layers.BatchNormalization(layer[-1], [0, 2, 3], deterministic))
layer.append(layers.Activation(layer[-1], T.leaky_relu))
layer.append(layers.Pool2D(layer[-1], (3, 3)))
layer.append(layers.Conv2D(layer[-1], 16, (3, 3)))
layer.append(layers.BatchNormalization(layer[-1], [0, 2, 3], deterministic))