'''
models
'''
# symbols
sym_y_g = T.ivector()
sym_z_input = T.matrix()
sym_z_rand = theano_rng.uniform(size=(batch_size_g, n_z))
sym_z_shared = T.tile(theano_rng.uniform((batch_size_g/num_classes, n_z)), (num_classes, 1))
# generator y2x: p_g(x, y) = p(y) p_g(x | y) where x = G(z, y), z follows p_g(z)
gen_in_z = ll.InputLayer(shape=(None, n_z))
gen_in_y = ll.InputLayer(shape=(None,))
gen_layers = [gen_in_z]
if args.dataset == 'svhn' or args.dataset == 'cifar10':
gen_layers.append(MLPConcatLayer([gen_layers[-1], gen_in_y], num_classes, name='gen-00'))
gen_layers.append(nn.batch_norm(ll.DenseLayer(gen_layers[-1], num_units=4*4*512, W=Normal(0.05), nonlinearity=nn.relu, name='gen-01'), g=None, name='gen-02'))
gen_layers.append(ll.ReshapeLayer(gen_layers[-1], (-1,512,4,4), name='gen-03'))
gen_layers.append(ConvConcatLayer([gen_layers[-1], gen_in_y], num_classes, name='gen-10'))
gen_layers.append(nn.batch_norm(nn.Deconv2DLayer(gen_layers[-1], (None,256,8,8), (5,5), W=Normal(0.05), nonlinearity=nn.relu, name='gen-11'), g=None, name='gen-12')) # 4 -> 8
gen_layers.append(ConvConcatLayer([gen_layers[-1], gen_in_y], num_classes, name='gen-20'))
gen_layers.append(nn.batch_norm(nn.Deconv2DLayer(gen_layers[-1], (None,128,16,16), (5,5), W=Normal(0.05), nonlinearity=nn.relu, name='gen-21'), g=None, name='gen-22')) # 8 -> 16
gen_layers.append(ConvConcatLayer([gen_layers[-1], gen_in_y], num_classes, name='gen-30'))
gen_layers.append(nn.weight_norm(nn.Deconv2DLayer(gen_layers[-1], (None,3,32,32), (5,5), W=Normal(0.05), nonlinearity=gen_final_non, name='gen-31'), train_g=True, init_stdv=0.1, name='gen-32')) # 16 -> 32
elif args.dataset == 'mnist':
gen_layers.append(MLPConcatLayer([gen_layers[-1], gen_in_y], num_classes, name='gen-1'))
gen_layers.append(ll.batch_norm(ll.DenseLayer(gen_layers[-1], num_units=500, nonlinearity=ln.softplus, name='gen-2'), name='gen-3'))
gen_layers.append(MLPConcatLayer([gen_layers[-1], gen_in_y], num_classes, name='gen-4'))
gen_layers.append(ll.batch_norm(ll.DenseLayer(gen_layers[-1], num_units=500, nonlinearity=ln.softplus, name='gen-5'), name='gen-6'))
gen_layers.append(MLPConcatLayer([gen_layers[-1], gen_in_y], num_classes, name='gen-7'))
gen_layers.append(nn.l2normalize(ll.DenseLayer(gen_layers[-1], num_units=28**2, nonlinearity=gen_final_non, name='gen-8')))
cla_layers.append(ll.GlobalPoolLayer(cla_layers[-1]))
cla_layers.append(
ll.DenseLayer(cla_layers[-1],
num_units=num_classes,
W=lasagne.init.Normal(1e-2, 0),
nonlinearity=ln.softmax,
name='cla-6'))
#################
gen_in_z = ll.InputLayer(shape=(None, n_z))
gen_in_y = ll.InputLayer(shape=(None, ))
gen_layers = [gen_in_z]
gen_layers.append(
MLPConcatLayer([gen_layers[-1], gen_in_y], num_classes, name='gen-5'))
gen_layers.append(
nn.batch_norm(ll.DenseLayer(gen_layers[-1],
num_units=512 * 4 * 4,
nonlinearity=ln.linear,
name='gen-6'),
g=None,
name='gen-61'))
gen_layers.append(
ll.ReshapeLayer(gen_layers[-1], (-1, 512, 4, 4), name='gen-7'))
gen_layers.append(
ConvConcatLayer([gen_layers[-1], gen_in_y], num_classes, name='gen-8'))
gen_layers.append(
nn.batch_norm(nn.Deconv2DLayer(gen_layers[-1], (None, 256, 8, 8),
sym_unsup_weight = T.scalar('unsup_weight')
sym_b_c = T.scalar('adam_beta1')
sym_w_g = T.scalar('w_g')
shared_unlabel = theano.shared(x_unlabelled, borrow=True)
slice_x_u_d = T.ivector()
slice_x_u_c = T.ivector()
slice_x_u_i = T.ivector()
classifier = build_network()
# generator y2x: p_g(x, y) = p(y) p_g(x | y) where x = G(z, y), z follows p_g(z)
gen_in_z = ll.InputLayer(shape=(None, n_z))
gen_in_y = ll.InputLayer(shape=(None,))
gen_layers = [gen_in_z]
gen_layers.append(MLPConcatLayer([gen_layers[-1], gen_in_y], num_classes, name='gen-00'))
gen_layers.append(nn.batch_norm(ll.DenseLayer(gen_layers[-1], num_units=4*4*512, W=Normal(0.05), nonlinearity=nn.relu, name='gen-01'), g=None, name='gen-02'))
gen_layers.append(ll.ReshapeLayer(gen_layers[-1], (-1,512,4,4), name='gen-03'))
gen_layers.append(ConvConcatLayer([gen_layers[-1], gen_in_y], num_classes, name='gen-10'))
gen_layers.append(nn.batch_norm(nn.Deconv2DLayer(gen_layers[-1], (None,256,8,8), (5,5), W=Normal(0.05), nonlinearity=nn.relu, name='gen-11'), g=None, name='gen-12')) # 4 -> 8
gen_layers.append(ConvConcatLayer([gen_layers[-1], gen_in_y], num_classes, name='gen-20'))
gen_layers.append(nn.batch_norm(nn.Deconv2DLayer(gen_layers[-1], (None,128,16,16), (5,5), W=Normal(0.05), nonlinearity=nn.relu, name='gen-21'), g=None, name='gen-22')) # 8 -> 16
gen_layers.append(ConvConcatLayer([gen_layers[-1], gen_in_y], num_classes, name='gen-30'))
gen_layers.append(nn.weight_norm(nn.Deconv2DLayer(gen_layers[-1], (None,3,32,32), (5,5), W=Normal(0.05), nonlinearity=gen_final_non, name='gen-31'), train_g=True, init_stdv=0.1, name='gen-32')) # 16 -> 32
# discriminator xy2p: test a pair of input comes from p(x, y) instead of p_c or p_g
dis_in_x = ll.InputLayer(shape=(None, in_channels) + dim_input)
dis_in_y = ll.InputLayer(shape=(None,))
dis_layers = [dis_in_x]
dis_layers.append(ll.DropoutLayer(dis_layers[-1], p=0.2, name='dis-00'))
dis_layers.append(ConvConcatLayer([dis_layers[-1], dis_in_y], num_classes, name='dis-01'))
name='cla-5'))
cla_layers.append(ll.GlobalPoolLayer(cla_layers[-1]))
cla_layers.append(
ll.DenseLayer(cla_layers[-1],
num_units=num_classes,
W=lasagne.init.Normal(1e-2, 0),
nonlinearity=ln.softmax,
name='cla-6'))
classifier = cla_layers[-1]
# generator y2x: p_g(x, y) = p(y) p_g(x | y) where x = G(z, y), z follows p_g(z)
gen_in_z = ll.InputLayer(shape=(None, n_z))
gen_in_y = ll.InputLayer(shape=(None, ))
gen_layers = [gen_in_z]
gen_layers.append(
MLPConcatLayer([gen_layers[-1], gen_in_y], num_classes, name='gen-1'))
gen_layers.append(
ll.batch_norm(ll.DenseLayer(gen_layers[-1],
num_units=500,
nonlinearity=ln.softplus,
name='gen-2'),
name='gen-3'))
gen_layers.append(
MLPConcatLayer([gen_layers[-1], gen_in_y], num_classes, name='gen-4'))
gen_layers.append(
ll.batch_norm(ll.DenseLayer(gen_layers[-1],
num_units=500,
nonlinearity=ln.softplus,
name='gen-5'),
name='gen-6'))
gen_layers.append(