def evaluate():
if len(sys.argv) < 4:
print(
"Usage: python3 evaluate.py [config suffix] [model name] [image files name1] [image files name2] ..."
)
exit(-1)
if len(sys.argv) == 4:
print(
" Note: Process a single image at a time may be inefficient - try multiple inputs)"
)
print("(TODO: batch processing when images have the same resolution)")
print()
print("Initializing...")
config_name = sys.argv[1]
import shutil
shutil.copy(
'models/%s/%s/scripts/config_%s.py' %
(config_name, sys.argv[2], config_name), 'config_tmp.py')
cfg = load_config('tmp')
cfg.name = sys.argv[1] + '/' + sys.argv[2]
net = GAN(cfg, restore=True)
net.restore(20000)
spec_files = sys.argv[3:]
print('processing files {}', spec_files)
net.eval(spec_files=spec_files, step_by_step=True)
def main(FLAGS):
if not os.path.isdir(FLAGS.data_dir):
os.makedirs(FLAGS.data_dir)
download_data(FLAGS.data_dir, FLAGS.train_data, FLAGS.test_data)
net = GAN(real_size,
z_size,
learning_rate,
alpha=FLAGS.alpha,
beta1=FLAGS.beta1)
'''--------Load data--------'''
train_data = loadmat(FLAGS.data_dir + '/' + FLAGS.train_data)
test_data = loadmat(FLAGS.data_dir + '/' + FLAGS.test_data)
dataset = preprocessor.Dataset(train_data, test_data)
'''--------Build net--------'''
saver = tf.train.Saver()
sample_z = np.random.uniform(-1, 1, size=(72, z_size))
samples, losses = [], []
steps = 0
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for e in range(FLAGS.epochs):
for x, y in dataset.batches(FLAGS.batch_size):
steps += 1
# Sample random noise for G
batch_z = np.random.uniform(-1,
1,
size=(FLAGS.batch_size, z_size))
# Run optimizers
_ = sess.run(net.d_opt,
feed_dict={
net.input_real: x,
net.input_z: batch_z
})
_ = sess.run(net.g_opt,
feed_dict={
net.input_z: batch_z,
net.input_real: x
})
if steps % FLAGS.print_every == 0:
# At the end of each epoch, get the losses and print them out
train_loss_d = net.d_loss.eval({
net.input_z: batch_z,
net.input_real: x
})
train_loss_g = net.g_loss.eval({net.input_z: batch_z})
print('Epoch {}/{}...'.format(e + 1, FLAGS.epochs),
'Discriminator Loss: {:.4f}'.format(train_loss_d),
'Generator loss: {:.4f}'.format(train_loss_g))
# Save losses to view after traning
losses.append((train_loss_d, train_loss_g))
if steps % FLAGS.show_every == 0:
gen_samples = sess.run(generator(net.input_z,
3,
reuse=True,
training=False),
feed_dict={net.input_z: sample_z})
samples.append(gen_samples)
_ = utils.view_samples(-1,
samples,
6,
12,
figsize=(FLAGS.h_figsize,
FLAGS.v_figsize))
plt.show()
saver.save(sess, './checkpoints/generator.ckpt')
with open('samples.pkl', 'wb') as f:
pkl.dump(samples, f)
fig, ax = plt.subplot()
losses = np.array(losses)
plt.plot(losses.T[0], label='Discriminator', alpha=0.5)
plt.plot(losses.T[1], label='Generator', alpha=0.5)
plt.title('Training Losses')
plt.legend()
plt.show()
def main():
config_name = sys.argv[1]
cfg = load_config(config_name)
cfg.name = sys.argv[1] + '/' + sys.argv[2]
net = GAN(cfg, mode=RESTORE_TRAIN)
net.train()
def main():
config_name = sys.argv[1]
cfg = load_config(config_name)
cfg.name = sys.argv[1] + '/' + sys.argv[2]
net = GAN(cfg, restore=False)
net.train()