def plot_interpolation_generator():
# config
config = began.config
num_col = 10
num_generation = 20
batchsize = 2 * num_generation
base_z = began.sample_z(batchsize)
mix_z = np.zeros((num_col * num_generation, config.ndim_z),
dtype=np.float32)
for g in xrange(num_generation):
for i in xrange(num_col):
mix_z[g * num_col +
i] = base_z[2 * g] * (i / float(num_col)) + base_z[
2 * g + 1] * (1 - i / float(num_col))
x = began.generate_x_from_z(mix_z, test=True, as_numpy=True)
x = (x + 1.0) / 2.0
plot.tile_rgb_images(x.transpose(0, 2, 3, 1),
dir=args.plot_dir,
filename="interpolation_generator",
row=num_generation,
col=num_col)
def run_method_1(): # config discriminator_config = gan.config_discriminator generator_config = gan.config_generator num_col = 10 num_generation = 20 batchsize = 2 * num_generation base_z = gan.sample_z(batchsize) mix_z = np.zeros((num_col * num_generation, generator_config.ndim_input), dtype=np.float32) for g in xrange(num_generation): for i in xrange(num_col): mix_z[g * num_col + i] = base_z[2 * g] * (i / float(num_col)) + base_z[2 * g + 1] * (1 - i / float(num_col)) x_negative = gan.generate_x_from_z(mix_z, test=True, as_numpy=True) x_negative = (x_negative + 1.0) / 2.0 # optimize z # xp = gan.xp # x_fake = gan.generate_x_from_z(mix_z, test=True, as_numpy=False) # x_fake.unchain_backward() # for n in xrange(500): # discrimination_fake, _ = gan.discriminate(x_fake, test=True) # opt = F.sum(discrimination_fake) # print opt.data # opt.backward() # # gan.backprop_generator(-F.sum(discrimination_fake)) # x_fake = gan.to_variable(xp.clip(x_fake.data + x_fake.grad * 0.01, -1, 1)) # x_negative = gan.to_numpy(x_fake) # x_negative = (x_negative + 1.0) / 2.0 plot.tile_rgb_images(x_negative.transpose(0, 2, 3, 1), dir=args.plot_dir, filename="analogy_1", row=num_generation, col=num_col)
def plot_interpolation_discriminator():
# config
config = began.config
num_col = 10
num_generation = 20
batchsize = 2 * num_generation
base_h = np.random.uniform(-1, 1,
(batchsize, config.ndim_h)).astype(np.float32)
mix_h = np.zeros((num_col * num_generation, config.ndim_h),
dtype=np.float32)
for g in xrange(num_generation):
for i in xrange(num_col):
mix_h[g * num_col +
i] = base_h[2 * g] * (i / float(num_col)) + base_h[
2 * g + 1] * (1 - i / float(num_col))
x = began.decode(mix_h, test=True, as_numpy=True)
x = (x + 1.0) / 2.0
plot.tile_rgb_images(x.transpose(0, 2, 3, 1),
dir=args.plot_dir,
filename="interpolation_discriminator",
row=num_generation,
col=num_col)