def genIt(name='bird'):
z = tf.random_normal((batch_size, rand_dim))
gen = generator(z)
with tf.Session() as sess:
sess.run(
tf.group(tf.global_variables_initializer(),
tf.sg_phase().assign(False)))
tf.sg_restore(sess,
tf.train.latest_checkpoint('asset/train/gan'),
category=['generator', 'discriminator'])
fake_features = []
for i in range(100):
fake_features.append(sess.run(gen))
np.save('../data/fake_' + name + '_negative.npy',
np.array(fake_features).reshape((-1, 4096)))
def trainIt():
data = prepareData()
x = data['train'][0]
# x = data['train']
z = tf.random_normal((batch_size, rand_dim))
gen = generator(z)
disc_real = discriminator(x)
disc_fake = discriminator(gen)
loss_d_r = disc_real.sg_mse(target=data['train'][1], name='disc_real')
# loss_d_r = disc_real.sg_mse(target = tf.ones(batch_size), name = 'disc_real')
loss_d_f = disc_fake.sg_mse(target=tf.zeros(batch_size), name='disc_fake')
loss_d = (loss_d_r + loss_d_f) / 2
loss_g = disc_fake.sg_mse(target=tf.ones(batch_size), name='gen')
# train_disc = tf.sg_optim(loss_d, lr=0.01, name = 'train_disc', category = 'discriminator') # discriminator train ops
train_disc = tf.sg_optim(loss_d_r,
lr=0.01,
name='train_disc',
category='discriminator')
train_gen = tf.sg_optim(loss_g, lr=0.01,
category='generator') # generator train ops
@tf.sg_train_func
def alt_train(sess, opt):
if sess.run(tf.sg_global_step()) % 1 == 0:
l_disc = sess.run([loss_d_r,
train_disc])[0] # training discriminator
else:
l_disc = sess.run(loss_d)
# l_gen = sess.run([loss_g, train_gen])[0] # training generator
# print np.mean(l_gen)
return np.mean(l_disc) #+ np.mean(l_gen)
alt_train(log_interval=10,
max_ep=25,
ep_size=(1100 + 690) / batch_size,
early_stop=False,
save_dir='asset/train/gan',
save_interval=10)
# target continuous variable # 1
target_cval_1 = tf.placeholder(dtype=tf.sg_floatx, shape=batch_size)
# target continuous variable # 2
target_cval_2 = tf.placeholder(dtype=tf.sg_floatx, shape=batch_size)
# category variables
z = (tf.ones(batch_size, dtype=tf.sg_intx) *
target_num).sg_one_hot(depth=cat_dim)
# continuous variables
z = z.sg_concat(
target=[target_cval_1.sg_expand_dims(),
target_cval_2.sg_expand_dims()])
# random seed = categorical variable + continuous variable + random normal
z = z.sg_concat(target=tf.random_normal((batch_size, rand_dim)))
# generator
gen = generator(z).sg_squeeze()
#
# run generator
#
def run_generator(num, x1, x2, fig_name='sample.png'):
with tf.Session() as sess:
tf.sg_init(sess)
# restore parameters
tf.sg_restore(sess,
x = data.train.image
y = data.train.label
# labels for discriminator
y_real = tf.ones(batch_size)
y_fake = tf.zeros(batch_size)
# discriminator labels ( half 1s, half 0s )
y_disc = tf.concat(0, [y, y * 0])
# categorical latent variable
z_cat = tf.multinomial(
tf.ones((batch_size, cat_dim), dtype=tf.sg_floatx) / cat_dim,
1).sg_squeeze().sg_int()
# continuous latent variable
z_con = tf.random_normal((batch_size, con_dim))
# random latent variable dimension
z_rand = tf.random_normal((batch_size, rand_dim))
# latent variable
z = tf.concat(1, [z_cat.sg_one_hot(depth=cat_dim), z_con, z_rand])
#
# Computational graph
#
# generator
gen = generator(z)
# add image summary
tf.sg_summary_image(x, name='real')
tf.sg_summary_image(gen, name='fake')
data = tf.sg_data.Mnist(batch_size=32)
# input images
x = data.train.image
#
# Computational graph
#
# encoder network
with tf.sg_context(name='encoder', size=4, stride=2, act='relu'):
mu = (x.sg_conv(dim=64).sg_conv(dim=128).sg_flatten().sg_dense(
dim=1024).sg_dense(dim=num_dim, act='linear'))
# re-parameterization trick with random gaussian
z = mu + tf.random_normal(mu.get_shape())
# decoder network
with tf.sg_context(name='decoder', size=4, stride=2, act='relu'):
xx = (z.sg_dense(dim=1024).sg_dense(dim=7 * 7 * 128).sg_reshape(
shape=(-1, 7, 7, 128)).sg_upconv(dim=64).sg_upconv(dim=1,
act='sigmoid'))
# add image summary
tf.sg_summary_image(x, name='origin')
tf.sg_summary_image(xx, name='recon')
# loss
loss_recon = xx.sg_mse(target=x, name='recon').sg_mean(axis=[1, 2, 3])
loss_kld = tf.square(mu).sg_sum(axis=1) / (28 * 28)
tf.sg_summary_loss(loss_kld, name='kld')
reuse=reuse):
# generator network
res = (tensor.sg_dense(dim=1024, name='fc1').sg_dense(
dim=7 * 7 * 128,
name='fc2').sg_reshape(shape=(-1, 7, 7, 128)).sg_upconv(
dim=64, name='conv1').sg_upconv(dim=1,
act='sigmoid',
bn=False,
name='conv2'))
return res
# random normal seed
z = tf.random_normal((batch_size, rand_dim))
# generator
gen = generator(z).sg_squeeze()
#
# draw samples
#
with tf.Session() as sess:
tf.sg_init(sess)
# restore parameters
tf.sg_restore(sess,
tf.train.latest_checkpoint('asset/train/gan'),
# # inputs # # MNIST input tensor ( with QueueRunner ) data = tf.sg_data.Mnist(batch_size=32) # input images x = data.train.image # labels for discriminator y_real = tf.ones(batch_size) y_fake = tf.zeros(batch_size) # random gaussian seed z = tf.random_normal((data.batch_size, rand_dim)) # # Computational graph # # generator gen = generator(z) # add image summary tf.sg_summary_image(x, name='real') tf.sg_summary_image(gen, name='fake') # discriminator disc_real = discriminator(x) disc_fake = discriminator(gen)
# hyper parameters
#
batch_size = 100 # batch size
num_dim = 50 # latent dimension
#
# inputs
#
#
# Computational graph
#
# random gaussian seed
z = tf.random_normal((batch_size, num_dim))
# decoder network
with tf.sg_context(name='decoder', size=4, stride=2, act='relu'):
gen = (z.sg_dense(dim=1024).sg_dense(dim=7 * 7 * 128).sg_reshape(
shape=(-1, 7, 7,
128)).sg_upconv(dim=64).sg_upconv(dim=1,
act='sigmoid').sg_squeeze())
#
# draw samples
#
with tf.Session() as sess:
tf.sg_init(sess)
def t_get_indices(batchsize):
index = np.arange(batchsize)
np.random.shuffle(index)
return index
## Training Loop
sd = 1 / np.sqrt(num_features)
with tf.name_scope('input'):
X = tf.placeholder(tf.float32, [None, num_features], name="x_inp")
Y = tf.placeholder(tf.float32, [None, num_classes], name="y_inp")
W_1 = tf.Variable(
tf.random_normal([num_features, n_hidden_units_one], mean=0, stddev=sd))
b_1 = tf.Variable(tf.random_normal([n_hidden_units_one], mean=0, stddev=sd))
h_1 = tf.nn.tanh(tf.matmul(X, W_1) + b_1)
W_2 = tf.Variable(
tf.random_normal([n_hidden_units_one, n_hidden_units_two],
mean=0,
stddev=sd))
b_2 = tf.Variable(tf.random_normal([n_hidden_units_two], mean=0, stddev=sd))
h_2 = tf.nn.tanh(tf.matmul(h_1, W_2) + b_2)
W_3 = tf.Variable(
tf.random_normal([n_hidden_units_two, n_hidden_units_three],
mean=0,
stddev=sd))
b_3 = tf.Variable(tf.random_normal([n_hidden_units_three], mean=0, stddev=sd))
