def discrim(X, w, b, w2, g2, b2, w3, g3, b3, w4, g4, b4, wy, wy1):
h0 = dnn_conv(X, w, subsample=(2, 2), border_mode=(2, 2))
if args.db1:
h0 += b.dimshuffle('x', 0, 'x', 'x')
h1 = lrelu(h0)
h1 = dropout(h1, args.dropout)
h1 = dnn_conv(h1, w2, subsample=(2, 2), border_mode=(2, 2))
if args.dbn:
h1 = batchnorm(h1, g=g2, b=b2)
else:
h1 += b2.dimshuffle('x', 0, 'x', 'x')
h2 = lrelu(h1)
h2 = dropout(h2, args.dropout)
h2 = dnn_conv(h2, w3, subsample=(2, 2), border_mode=(2, 2))
if args.dbn:
h2 = batchnorm(h2, g=g3, b=b3)
else:
h2 += b3.dimshuffle('x', 0, 'x', 'x')
h3 = lrelu(h2)
h3 = dropout(h3, args.dropout)
h3 = dnn_conv(h3, w4, subsample=(2, 2), border_mode=(2, 2))
if args.dbn:
h3 = batchnorm(h3, g=g4, b=b4)
else:
h3 += b4.dimshuffle('x', 0, 'x', 'x')
h4 = lrelu(h3)
h4 = dropout(h4, args.dropout)
h4 = T.flatten(h4, 2)
y = sigmoid(T.dot(h4, wy))
y1 = sigmoid(T.dot(h4, wy1))
return y, y1
def discrim(X, w, b, w2, g2, b2, w3, g3, b3, w4, g4, b4, wy, wy1):
h0 = dnn_conv(X, w, subsample=(2, 2), border_mode=(2, 2))
if args.db1:
h0 += b.dimshuffle('x', 0, 'x', 'x')
h1 = lrelu(h0)
h1 = dropout(h1, args.dropout)
h1 = dnn_conv(h1, w2, subsample=(2, 2), border_mode=(2, 2))
if args.dbn:
h1 = batchnorm(h1, g=g2, b=b2)
else:
h1 += b2.dimshuffle('x', 0, 'x', 'x')
h2 = lrelu(h1)
h2 = dropout(h2, args.dropout)
h2 = dnn_conv(h2, w3, subsample=(2, 2), border_mode=(2, 2))
if args.dbn:
h2 = batchnorm(h2, g=g3, b=b3)
else:
h2 += b3.dimshuffle('x', 0, 'x', 'x')
h3 = lrelu(h2)
h3 = dropout(h3, args.dropout)
h3 = dnn_conv(h3, w4, subsample=(2, 2), border_mode=(2, 2))
if args.dbn:
h3 = batchnorm(h3, g=g4, b=b4)
else:
h3 += b4.dimshuffle('x', 0, 'x', 'x')
h4 = lrelu(h3)
h4 = dropout(h4, args.dropout)
h4 = T.flatten(h4, 2)
y = sigmoid(T.dot(h4, wy))
y1 = sigmoid(T.dot(h4, wy1))
return y, y1
def discrim(X, w, w2, g2, b2, w3, g3, b3, wy, by):
h0 = dropout(relu(dnn_conv(X, w, subsample=(2, 2), border_mode=(2, 2))), p=0.5)
h1 = dropout(relu(batchnorm(dnn_conv(h0, w2, subsample=(2, 2), border_mode=(2, 2)), g=g2, b=b2)), p=0.5)
h2 = dropout(relu(batchnorm(dnn_conv(h1, w3, subsample=(2, 2), border_mode=(2, 2)), g=g3, b=b3)), p=0.5)
h2 = T.flatten(h2, 2)
y = -relu(T.dot(h2, wy)+by)
return y
def discrim(X, w, w2, g2, b2, w3, g3, b3, wy, wa):
h0 = dropout(relu(dnn_conv(X, w, subsample=(2, 2), border_mode=(2, 2))), p=0.5)
h1 = dropout(relu(batchnorm(dnn_conv(h0, w2, subsample=(2, 2), border_mode=(2, 2)), g=g2, b=b2)), p=0.5)
h2 = dropout(relu(batchnorm(dnn_conv(h1, w3, subsample=(2, 2), border_mode=(2, 2)), g=g3, b=b3)), p=0.5)
h2 = T.flatten(h2, 2)
y = square(T.dot(h2, wy))
y = T.dot(T.log(1+y), T.exp(wa))
return y
def conv_encoder(X, w1, w2, w4, b4, w_mu, b_mu):
h1 = conv_and_pool(X, w1, s=2)
h1 = dropout(h1, 0.3)
h2 = conv_and_pool(h1, w2, s=2)
h2 = dropout(h2, 0.3)
h3 = T.flatten(h2, 2)
h4 = tanh((T.dot(h3, w4) + b4))
h4 = dropout(h4, 0.3)
z = T.dot(h4, w_mu) + b_mu
return z
def discrim(X):
current_input = dropout(X, 0.3)
### encoder ###
cv1 = relu(
dnn_conv(current_input, aew1, subsample=(1, 1), border_mode=(1, 1)))
cv2 = relu(
batchnorm(dnn_conv(cv1, aew2, subsample=(4, 4), border_mode=(2, 2)),
g=aeg2,
b=aeb2))
cv3 = relu(
batchnorm(dnn_conv(cv2, aew3, subsample=(1, 1), border_mode=(1, 1)),
g=aeg3,
b=aeb3))
cv4 = relu(
batchnorm(dnn_conv(cv3, aew4, subsample=(4, 4), border_mode=(2, 2)),
g=aeg4,
b=aeb4))
cv5 = relu(
batchnorm(dnn_conv(cv4, aew5, subsample=(1, 1), border_mode=(1, 1)),
g=aeg5,
b=aeb5))
cv6 = relu(
batchnorm(dnn_conv(cv5, aew6, subsample=(4, 4), border_mode=(0, 0)),
g=aeg6,
b=aeb6))
### decoder ###
dv6 = relu(
batchnorm(deconv(cv6, aew6, subsample=(4, 4), border_mode=(0, 0)),
g=aeg6t,
b=aeb6t))
dv5 = relu(
batchnorm(deconv(dv6, aew5, subsample=(1, 1), border_mode=(1, 1)),
g=aeg5t,
b=aeb5t))
dv4 = relu(
batchnorm(deconv(dv5, aew4, subsample=(4, 4), border_mode=(2, 2)),
g=aeg4t,
b=aeb4t))
dv3 = relu(
batchnorm(deconv(dv4, aew3, subsample=(1, 1), border_mode=(1, 1)),
g=aeg3t,
b=aeb3t))
dv2 = relu(
batchnorm(deconv(dv3, aew2, subsample=(4, 4), border_mode=(2, 2)),
g=aeg2t,
b=aeb2t))
dv1 = tanh(deconv(dv2, aew1, subsample=(1, 1), border_mode=(1, 1)))
rX = dv1
mse = T.sqrt(T.sum(T.abs_(T.flatten(X - rX, 2)), axis=1)) + T.sqrt(
T.sum(T.flatten((X - rX)**2, 2), axis=1)) # L1 and L2 loss
return T.flatten(cv6, 2), rX, mse
dz_logpzx = T.grad(T.sum(logpxz), z) - z
tensor_grad_z = T.reshape(dz_logpzx, (-1, num_z, nz))
# notice we multiply 100 on dxkxy
vgd_grad_tensor = (T.batched_dot(Kxy, tensor_grad_z) + 100 * dxkxy) / T.tile(\
T.mean(Kxy, axis=2).dimshuffle(0, 1, 'x'), (1, 1, nz))
return vgd_grad_tensor
X = T.tensor4('X')
num_z = T.iscalar('num_z')
# for generatiing image functions
func_x_corrupt = dropout(X, p=drop_p)
func_x_corrupt =T.clip(func_x_corrupt, 1e-6, 1 - 1e-6)
func_z = conv_encoder(func_x_corrupt, *enc_params)
func_res_x, _ = conv_decoder(X, func_z, *dec_params)
# functions for svgd training
x_repeated = T.repeat(X, num_z, axis=0)
x_dropout = dropout(x_repeated, p=drop_p)
x_corrupt = T.clip(x_dropout, 1e-6, 1- 1e-6)
z = conv_encoder(x_corrupt, *enc_params)
reconstructed_x, logpxz = conv_decoder(x_repeated, z, *dec_params)
z_vgd_grad = 0. - _vgd_gradient(z, num_z, logpxz)
def discrim(X, Y):
def classifier(H, Y):
p_y_given_x = T.nnet.softmax(T.dot(H, logistic_w) + logistic_b)
neg_lik = -T.sum(T.mul(T.log(p_y_given_x), Y), axis=1)
return neg_lik, p_y_given_x
current_input = dropout(X, 0.2)
### encoder ###
cv1 = relu(
dnn_conv(current_input, aew1, subsample=(1, 1), border_mode=(1, 1)))
cv2 = relu(
batchnorm(dnn_conv(cv1, aew2, subsample=(2, 2), border_mode=(0, 0)),
g=aeg2,
b=aeb2))
cv3 = relu(
batchnorm(dnn_conv(cv2, aew3, subsample=(1, 1), border_mode=(1, 1)),
g=aeg3,
b=aeb3))
cv4 = relu(
batchnorm(dnn_conv(cv3, aew4, subsample=(4, 4), border_mode=(0, 0)),
g=aeg4,
b=aeb4))
cv5 = relu(
batchnorm(dnn_conv(cv4, aew5, subsample=(1, 1), border_mode=(1, 1)),
g=aeg5,
b=aeb5))
cv6 = relu(
batchnorm(dnn_conv(cv5, aew6, subsample=(4, 4), border_mode=(0, 0)),
g=aeg6,
b=aeb6))
### decoder ###
dv6 = relu(
batchnorm(deconv(cv6, aew6, subsample=(4, 4), border_mode=(0, 0)),
g=aeg6t,
b=aeb6t))
dv5 = relu(
batchnorm(deconv(dv6, aew5, subsample=(1, 1), border_mode=(1, 1)),
g=aeg5t,
b=aeb5t))
dv4 = relu(
batchnorm(deconv(dv5, aew4, subsample=(4, 4), border_mode=(0, 0)),
g=aeg4t,
b=aeb4t))
dv3 = relu(
batchnorm(deconv(dv4, aew3, subsample=(1, 1), border_mode=(1, 1)),
g=aeg3t,
b=aeb3t))
dv2 = relu(
batchnorm(deconv(dv3, aew2, subsample=(2, 2), border_mode=(0, 0)),
g=aeg2t,
b=aeb2t))
dv1 = tanh(deconv(dv2, aew1, subsample=(1, 1), border_mode=(1, 1)))
hidden = T.flatten(cv6, 2)
rX = dv1
mse = T.sqrt(T.sum(T.flatten((X - rX)**2, 2), axis=1))
#mse = T.sqrt(T.sum(T.abs_(T.flatten(X-rX, 2)),axis=1)) + T.sqrt(T.sum(T.flatten((X-rX)**2, 2), axis=1))
neg_lik, p_y_given_x = classifier(hidden, Y)
return hidden, p_y_given_x, rX, mse, neg_lik
