def view_latent_vary(identifier, epoch, n_steps=6):
settings = json.load(open('./experiments/settings/' + identifier + '.txt', 'r'))
Z_sample = model.sample_Z(1, settings['seq_length'], settings['latent_dim'],
settings['use_time'])[0]
samples_dim = []
for dim in range(settings['latent_dim']):
Z_samples_dim = plotting.vary_latent_dimension(Z_sample, dim, n_steps)
samples_dim.append(model.sample_trained_model(settings, epoch, Z_samples_dim.shape[0], Z_samples_dim))
plotting.save_plot_vary_dimension(samples_dim, epoch, settings['identifier'] + '_varydim', n_dim=settings['latent_dim'])
return True
def view_fixed(identifier, epoch, n_samples=6, dim=None):
""" What happens when we give the same point at each time step? """
settings = json.load(open('./experiments/settings/' + identifier + '.txt', 'r'))
Z_samples = model.sample_Z(n_samples, settings['seq_length'], settings['latent_dim'],
settings['use_time'])
# now, propagate forward the value at time 0 (which time doesn't matter)
for i in range(1, settings['seq_length']):
if dim is None:
Z_samples[:, i, :] = Z_samples[:, 0, :]
else:
Z_samples[:, i, dim] = Z_samples[:, 0, dim]
# now generate
samples = model.sample_trained_model(settings, epoch, n_samples, Z_samples)
# now visualise
plotting.save_plot_sample(samples, epoch, identifier + '_fixed', n_samples)
return True
with tf.variable_scope("SIGMA_optimizer"):
sigma_solver = tf.train.RMSPropOptimizer(learning_rate=0.05).minimize(
-that, var_list=[sigma])
#sigma_solver = tf.train.AdamOptimizer().minimize(-that, var_list=[sigma])
#sigma_solver = tf.train.AdagradOptimizer(learning_rate=0.1).minimize(-that, var_list=[sigma])
sigma_opt_iter = 2000
sigma_opt_thresh = 0.001
sigma_opt_vars = [
var for var in tf.global_variables() if 'SIGMA_optimizer' in var.name
]
sess = tf.Session(config=tf.ConfigProto(allow_soft_placement=True,
log_device_placement=True))
sess.run(tf.global_variables_initializer())
vis_Z = model.sample_Z(batch_size, seq_length, latent_dim, use_time)
vis_C = model.sample_C(batch_size, cond_dim, max_val, one_hot)
# vis_C[:1] = np.arange(cond_dim)
vis_sample = sess.run(G_sample, feed_dict={Z: vis_Z, CG: vis_C})
vis_real_indices = np.random.choice(len(samples['vali']), size=6)
vis_real = np.float32(samples['vali'][vis_real_indices, :, :])
vis_real_labels = labels['vali'][vis_real_indices]
samps = vis_real
labs = vis_real_labels
plotting.save_mnist_plot_sample(samps.reshape(-1, seq_length**2, 1),
0,
identifier + '_real',
n_samples=6,
n_sigmas = 2
sigma = tf.get_variable(name='sigma', shape=n_sigmas, initializer=tf.constant_initializer(
value=np.power(heuristic_sigma_training, np.linspace(-1, 3, num=n_sigmas))))
mmd2, that = mix_rbf_mmd2_and_ratio(eval_real_PH, eval_sample_PH, sigma)
with tf.variable_scope("SIGMA_optimizer"):
sigma_solver = tf.train.RMSPropOptimizer(learning_rate=0.05).minimize(-that, var_list=[sigma])
# sigma_solver = tf.train.AdamOptimizer().minimize(-that, var_list=[sigma])
# sigma_solver = tf.train.AdagradOptimizer(learning_rate=0.1).minimize(-that, var_list=[sigma])
sigma_opt_iter = 2000
sigma_opt_thresh = 0.001
sigma_opt_vars = [var for var in tf.global_variables() if 'SIGMA_optimizer' in var.name]
sess = tf.Session()
sess.run(tf.global_variables_initializer())
vis_Z = model.sample_Z(batch_size, seq_length, latent_dim, use_time)
if CGAN:
vis_C = model.sample_C(batch_size, cond_dim, max_val, one_hot)
if 'eICU_task' in data:
vis_C = labels['train'][np.random.choice(labels['train'].shape[0], batch_size, replace=False), :]
vis_sample = sess.run(G_sample, feed_dict={Z: vis_Z, CG: vis_C})
else:
vis_sample = sess.run(G_sample, feed_dict={Z: vis_Z})
vis_C = None
vis_real_indices = np.random.choice(len(samples['vali']), size=6)
vis_real = np.float32(samples['vali'][vis_real_indices, :, :])
if not labels['vali'] is None:
vis_real_labels = labels['vali'][vis_real_indices]
else:
vis_real_labels = None
