def test_gan_utility_funcs(simple_gan: GAN):
xy_shp = simple_gan_z_shape[1:]
x = np.zeros(xy_shp, dtype=np.float32)
y = np.zeros(xy_shp, dtype=np.float32)
simple_gan.interpolate(x, y)
z_point = simple_gan.random_z_point()
neighbors = simple_gan.neighborhood(z_point, std=0.05)
diff = np.stack([neighbors[0]]*len(neighbors)) - neighbors
assert np.abs(diff).mean() < 0.1
def test_render_gan_generator():
nb_driver = 20
def driver(z):
return Dense(nb_driver)(z)
def tag3d_network_dense(x):
mask = sequential(
[Dense(16), Reshape((1, 4, 4)),
UpSampling2D((16, 16))])(x)
depth_map = sequential(
[Dense(16), Reshape((1, 4, 4)),
UpSampling2D((4, 4))])(x)
return mask, depth_map
def merge_mask(subsample):
def call(x):
if subsample:
x = MaxPooling2D(subsample)(x)
return Convolution2D(1, 3, 3, border_mode='same')(x)
return call
def light_generator(ins):
seq = sequential([Convolution2D(1, 3, 3,
border_mode='same')])(concat(ins))
return UpSampling2D((4, 4))(seq), UpSampling2D((4, 4))(seq), \
UpSampling2D((4, 4))(seq),
def offset_front(x):
return sequential(
[Dense(16), Reshape((1, 4, 4)),
UpSampling2D((4, 4))])(concat(x))
def offset_middle(x):
return UpSampling2D()(concat(x))
def offset_back(x):
feature_map = sequential([
UpSampling2D(),
])(concat(x))
return feature_map, Convolution2D(1, 3, 3,
border_mode='same')(feature_map)
def mask_post(x):
return sequential([Convolution2D(1, 3, 3,
border_mode='same')])(concat(x))
def mask_weight_blending(x):
return sequential([
Flatten(),
Dense(1),
])(x)
def discriminator_fn(x):
return gan_outputs(sequential([
Flatten(),
Dense(1),
])(concat(x)),
fake_for_gen=(0, 10),
fake_for_dis=(0, 10),
real=(10, 20))
gen = render_gan_generator(
mask_driver=driver,
tag_3d_model_network=tag3d_network_dense,
light_merge_mask16=merge_mask(None),
offset_merge_light16=merge_mask((4, 4)),
offset_merge_mask16=merge_mask(None),
offset_merge_mask32=merge_mask(None),
lighting_generator=light_generator,
offset_front=offset_front,
offset_middle=offset_middle,
offset_back=offset_back,
mask_weight_blending32=mask_weight_blending,
mask_weight_blending64=mask_weight_blending,
mask_postprocess=mask_post,
z_for_driver=(0, 10),
z_for_offset=(10, 20),
z_for_bits=(20, 32),
)
z_shape = (32, )
real_shape = (1, 64, 64)
z = Input(shape=z_shape, name='z')
fake = Input(shape=real_shape, name='fake')
real = Input(shape=real_shape, name='real')
generator = Container([z], gen([z]))
discriminator = Container([fake, real], discriminator_fn([fake, real]))
gan = GAN(generator, discriminator, z_shape, real_shape)
gan.build(Adam(), Adam(), gan_binary_crossentropy)
for l in gan.generator.layers:
print("{}: {}, {}".format(l.name, l.output_shape,
getattr(l, 'regularizers', [])))
bs = 10
z_in = np.random.sample((bs, ) + z_shape)
real_in = np.random.sample((bs, ) + real_shape)
gan.compile_generate()
gan.generate({'z': z_in})
fn = gan.compile_custom_layers(['fake', 'mask', 'mask_with_lighting'])
fn({'z': z_in, 'real': real_in})
def _build_gan(self):
self.generator_given_z.compile(self.generator_optimizer,
'binary_crossentropy')
self.discriminator.compile(self.discriminator_optimizer,
'binary_crossentropy')
self.gan = GAN(self.generator_given_z, self.discriminator)
def test_render_gan_generator():
nb_driver = 20
def driver(z):
return Dense(nb_driver)(z)
def tag3d_network_dense(x):
mask = sequential([
Dense(16),
Reshape((1, 4, 4)),
UpSampling2D((16, 16))
])(x)
depth_map = sequential([
Dense(16),
Reshape((1, 4, 4)),
UpSampling2D((4, 4))
])(x)
return mask, depth_map
def merge_mask(subsample):
def call(x):
if subsample:
x = MaxPooling2D(subsample)(x)
return Convolution2D(1, 3, 3, border_mode='same')(x)
return call
def light_generator(ins):
seq = sequential([
Convolution2D(1, 3, 3, border_mode='same')
])(concat(ins))
return UpSampling2D((4, 4))(seq), UpSampling2D((4, 4))(seq), \
UpSampling2D((4, 4))(seq),
def offset_front(x):
return sequential([
Dense(16),
Reshape((1, 4, 4)),
UpSampling2D((4, 4))
])(concat(x))
def offset_middle(x):
return UpSampling2D()(concat(x))
def offset_back(x):
feature_map = sequential([
UpSampling2D(),
])(concat(x))
return feature_map, Convolution2D(1, 3, 3,
border_mode='same')(feature_map)
def mask_post(x):
return sequential([
Convolution2D(1, 3, 3, border_mode='same')
])(concat(x))
def mask_weight_blending(x):
return sequential([
Flatten(),
Dense(1),
])(x)
def discriminator_fn(x):
return gan_outputs(sequential([
Flatten(),
Dense(1),
])(concat(x)), fake_for_gen=(0, 10), fake_for_dis=(0, 10),
real=(10, 20))
gen = render_gan_generator(
mask_driver=driver,
tag_3d_model_network=tag3d_network_dense,
light_merge_mask16=merge_mask(None),
offset_merge_light16=merge_mask((4, 4)),
offset_merge_mask16=merge_mask(None),
offset_merge_mask32=merge_mask(None),
lighting_generator=light_generator,
offset_front=offset_front,
offset_middle=offset_middle,
offset_back=offset_back,
mask_weight_blending32=mask_weight_blending,
mask_weight_blending64=mask_weight_blending,
mask_postprocess=mask_post,
z_for_driver=(0, 10),
z_for_offset=(10, 20),
z_for_bits=(20, 32),
)
z_shape = (32, )
real_shape = (1, 64, 64)
z = Input(shape=z_shape, name='z')
fake = Input(shape=real_shape, name='fake')
real = Input(shape=real_shape, name='real')
generator = Container([z], gen([z]))
discriminator = Container([fake, real], discriminator_fn([fake, real]))
gan = GAN(generator, discriminator, z_shape, real_shape)
gan.build(Adam(), Adam(), gan_binary_crossentropy)
for l in gan.generator.layers:
print("{}: {}, {}".format(
l.name, l.output_shape, getattr(l, 'regularizers', [])))
bs = 10
z_in = np.random.sample((bs,) + z_shape)
real_in = np.random.sample((bs,) + real_shape)
gan.compile_generate()
gan.generate({'z': z_in})
fn = gan.compile_custom_layers(['fake', 'mask', 'mask_with_lighting'])
fn({'z': z_in, 'real': real_in})
