def main(args):
# =====================================
# Load config
# =====================================
with open(os.path.join(args.output_dir, 'config.json')) as f:
config = json.load(f)
args.__dict__.update(config)
# =====================================
# Preparation
# =====================================
data_file = os.path.join(RAW_DATA_DIR, "ComputerVision", "dSprites",
"dsprites_ndarray_co1sh3sc6or40x32y32_64x64.npz")
# It is already in the range [0, 1]
with np.load(data_file, encoding="latin1") as f:
x_train = f['imgs']
x_train = np.expand_dims(x_train.astype(np.float32), axis=-1)
# =====================================
# Instantiate models
# =====================================
if args.enc_dec_model == "1Konny":
encoder = Encoder_1Konny(args.z_dim, stochastic=True)
decoder = Decoder_1Konny()
disc_z = DiscriminatorZ_1Konny()
else:
raise ValueError("Do not support enc_dec_model='{}'!".format(
args.enc_dec_model))
model = AAE([64, 64, 1],
args.z_dim,
encoder=encoder,
decoder=decoder,
discriminator_z=disc_z,
rec_x_mode=args.rec_x_mode,
stochastic_z=args.stochastic_z,
use_gp0_z=True,
gp0_z_mode=args.gp0_z_mode)
loss_coeff_dict = {
'rec_x': args.rec_x_coeff,
'G_loss_z1_gen': args.G_loss_z1_gen_coeff,
'D_loss_z1_gen': args.D_loss_z1_gen_coeff,
'gp0_z': args.gp0_z_coeff,
}
model.build(loss_coeff_dict)
SimpleParamPrinter.print_all_params_list()
# =====================================
# TF Graph Handler
asset_dir = make_dir_if_not_exist(os.path.join(args.output_dir, "asset"))
img_eval = remove_dir_if_exist(os.path.join(asset_dir, "img_eval"),
ask_4_permission=False)
img_eval = make_dir_if_not_exist(img_eval)
img_x_rec = make_dir_if_not_exist(os.path.join(img_eval, "x_rec"))
img_z_rand_2_traversal = make_dir_if_not_exist(
os.path.join(img_eval, "z_rand_2_traversal"))
img_z_cond_all_traversal = make_dir_if_not_exist(
os.path.join(img_eval, "z_cond_all_traversal"))
img_z_cond_1_traversal = make_dir_if_not_exist(
os.path.join(img_eval, "z_cond_1_traversal"))
img_z_corr = make_dir_if_not_exist(os.path.join(img_eval, "z_corr"))
img_z_dist = make_dir_if_not_exist(os.path.join(img_eval, "z_dist"))
img_z_stat_dist = make_dir_if_not_exist(
os.path.join(img_eval, "z_stat_dist"))
img_rec_error_dist = make_dir_if_not_exist(
os.path.join(img_eval, "rec_error_dist"))
model_dir = make_dir_if_not_exist(os.path.join(args.output_dir,
"model_tf"))
train_helper = SimpleTrainHelper(log_dir=None, save_dir=model_dir)
# =====================================
# =====================================
# Training Loop
# =====================================
config_proto = tf.ConfigProto(allow_soft_placement=True)
config_proto.gpu_options.allow_growth = True
config_proto.gpu_options.per_process_gpu_memory_fraction = 0.9
sess = tf.Session(config=config_proto)
# Load model
train_helper.load(sess, load_step=args.load_step)
#'''
# Reconstruction
# ======================================= #
seed = 389
x = x_train[np.arange(seed, seed + 64)]
img_file = os.path.join(img_x_rec, 'x_rec_train.png')
model.reconstruct_images(img_file,
sess,
x,
block_shape=[8, 8],
batch_size=-1,
dec_output_2_img_func=binary_float_to_uint8)
# ======================================= #
# z random/conditional traversal
# ======================================= #
# Plot z cont with z cont
z_zero = np.zeros([args.z_dim], dtype=np.float32)
z_rand = np.random.randn(args.z_dim)
z_start, z_stop = -4, 4
num_points = 8
for i in range(args.z_dim):
for j in range(i + 1, args.z_dim):
print("Plot random 2 comps z traverse with {} and {} components!".
format(i, j))
img_file = os.path.join(img_z_rand_2_traversal,
'z[{},{},zero].png'.format(i, j))
model.rand_2_latents_traverse(
img_file,
sess,
default_z=z_zero,
z_comp1=i,
start1=z_start,
stop1=z_stop,
num_points1=num_points,
z_comp2=j,
start2=z_start,
stop2=z_stop,
num_points2=num_points,
batch_size=args.batch_size,
dec_output_2_img_func=binary_float_to_uint8)
img_file = os.path.join(img_z_rand_2_traversal,
'z[{},{},rand].png'.format(i, j))
model.rand_2_latents_traverse(
img_file,
sess,
default_z=z_rand,
z_comp1=i,
start1=z_start,
stop1=z_stop,
num_points1=num_points,
z_comp2=j,
start2=z_stop,
stop2=z_stop,
num_points2=num_points,
batch_size=args.batch_size,
dec_output_2_img_func=binary_float_to_uint8)
seed = 389
z_start, z_stop = -4, 4
num_itpl_points = 8
for n in range(seed, seed + 30):
print("Plot conditional all comps z traverse with test sample {}!".
format(n))
x = x_train[n]
img_file = os.path.join(img_z_cond_all_traversal,
'x_train{}.png'.format(n))
model.cond_all_latents_traverse(
img_file,
sess,
x,
start=z_start,
stop=z_stop,
num_itpl_points=num_itpl_points,
batch_size=args.batch_size,
dec_output_2_img_func=binary_float_to_uint8)
seed = 64
z_start, z_stop = -4, 4
num_itpl_points = 8
print("Plot conditional 1 comp z traverse!")
for i in range(args.z_dim):
x = x_train[seed:seed + 64]
img_file = os.path.join(
img_z_cond_1_traversal,
'x_train[{},{}]_z{}.png'.format(seed, seed + 64, i))
model.cond_1_latent_traverse(
img_file,
sess,
x,
z_comp=i,
start=z_start,
stop=z_stop,
num_itpl_points=num_itpl_points,
batch_size=args.batch_size,
dec_output_2_img_func=binary_float_to_uint8)
# ======================================= #
# '''
# z correlation matrix
# ======================================= #
data = x_train
all_z = []
for batch_ids in iterate_data(len(data), args.batch_size, shuffle=False):
x = data[batch_ids]
z = model.encode(sess, x)
assert len(
z.shape) == 2 and z.shape[1] == args.z_dim, "z.shape: {}".format(
z.shape)
all_z.append(z)
all_z = np.concatenate(all_z, axis=0)
print("Start plotting!")
plot_corrmat_with_histogram(os.path.join(img_z_corr, "corr_mat.png"),
all_z)
plot_comp_dist(os.path.join(img_z_dist, 'z_{}'), all_z, x_lim=(-5, 5))
print("Done!")
# ======================================= #
# '''
# z gaussian stddev
# ======================================= #
print("\nPlot z mean and stddev!")
data = x_train
all_z_mean = []
all_z_stddev = []
for batch_ids in iterate_data(len(data), args.batch_size, shuffle=False):
x = data[batch_ids]
z_mean, z_stddev = sess.run(model.get_output(['z_mean', 'z_stddev']),
feed_dict={
model.is_train: False,
model.x_ph: x
})
all_z_mean.append(z_mean)
all_z_stddev.append(z_stddev)
all_z_mean = np.concatenate(all_z_mean, axis=0)
all_z_stddev = np.concatenate(all_z_stddev, axis=0)
plot_comp_dist(os.path.join(img_z_stat_dist, 'z_mean_{}.png'),
all_z_mean,
x_lim=(-5, 5))
plot_comp_dist(os.path.join(img_z_stat_dist, 'z_stddev_{}.png'),
all_z_stddev,
x_lim=(0, 3))
# ======================================= #
# '''
# Decoder sensitivity
# ======================================= #
z_start = -3
z_stop = 3
for i in range(args.z_dim):
print("\nPlot rec error distribution for z component {}!".format(i))
all_z1 = np.array(all_z, copy=True, dtype=np.float32)
all_z2 = np.array(all_z, copy=True, dtype=np.float32)
all_z1[:, i] = z_start
all_z2[:, i] = z_stop
all_x_rec1 = []
all_x_rec2 = []
for batch_ids in iterate_data(len(x_train),
args.batch_size,
shuffle=False):
z1 = all_z1[batch_ids]
z2 = all_z2[batch_ids]
x1 = model.decode(sess, z1)
x2 = model.decode(sess, z2)
all_x_rec1.append(x1)
all_x_rec2.append(x2)
all_x_rec1 = np.concatenate(all_x_rec1, axis=0)
all_x_rec2 = np.concatenate(all_x_rec2, axis=0)
rec_errors = np.sum(np.reshape((all_x_rec1 - all_x_rec2)**2,
[len(x_train), 28 * 28]),
axis=1)
plot_comp_dist(
os.path.join(
img_rec_error_dist,
'rec_error[zi={},{},{}].png'.format(i, z_start, z_stop)),
rec_errors)
def main(args):
# =====================================
# Load config
# =====================================
with open(join(args.output_dir, 'config.json')) as f:
config = json.load(f)
args.__dict__.update(config)
# =====================================
# Dataset
# =====================================
celebA_loader = TFCelebAWithAttrLoader(root_dir=args.celebA_root_dir)
img_height, img_width = args.celebA_resize_size, args.celebA_resize_size
celebA_loader.build_transformation_flow_tf(
*celebA_loader.get_transform_fns("1Konny",
resize_size=args.celebA_resize_size))
# =====================================
# Instantiate model
# =====================================
if args.activation == "relu":
activation = tf.nn.relu
elif args.activation == "leaky_relu":
activation = tf.nn.leaky_relu
else:
raise ValueError("Do not support '{}' activation!".format(
args.activation))
if args.enc_dec_model == "1Konny":
# assert args.z_dim == 65, "For 1Konny, z_dim must be 65. Found {}!".format(args.z_dim)
encoder = Encoder_1Konny(args.z_dim,
stochastic=True,
activation=activation)
decoder = Decoder_1Konny([img_height, img_width, 3],
activation=activation,
output_activation=tf.nn.sigmoid)
disc_z = DiscriminatorZ_1Konny()
else:
raise ValueError("Do not support encoder/decoder model '{}'!".format(
args.enc_dec_model))
model = AAE([img_height, img_width, 3],
args.z_dim,
encoder=encoder,
decoder=decoder,
discriminator_z=disc_z,
rec_x_mode=args.rec_x_mode,
stochastic_z=args.stochastic_z,
use_gp0_z=True,
gp0_z_mode=args.gp0_z_mode)
loss_coeff_dict = {
'rec_x': args.rec_x_coeff,
'G_loss_z1_gen': args.G_loss_z1_gen_coeff,
'D_loss_z1_gen': args.D_loss_z1_gen_coeff,
'gp0_z': args.gp0_z_coeff,
}
model.build(loss_coeff_dict)
SimpleParamPrinter.print_all_params_tf_slim()
# =====================================
# Load model
# =====================================
config_proto = tf.ConfigProto(allow_soft_placement=True)
config_proto.gpu_options.allow_growth = True
config_proto.gpu_options.per_process_gpu_memory_fraction = 0.9
sess = tf.Session(config=config_proto)
model_dir = make_dir_if_not_exist(join(args.output_dir, "model_tf"))
train_helper = SimpleTrainHelper(log_dir=None, save_dir=model_dir)
# Load model
train_helper.load(sess, load_step=args.load_step)
# =====================================
# Experiments
# save_dir = remove_dir_if_exist(join(args.save_dir, "AAE_{}".format(args.run)), ask_4_permission=False)
# save_dir = make_dir_if_not_exist(save_dir)
save_dir = make_dir_if_not_exist(
join(args.save_dir, "AAE_{}".format(args.run)))
# =====================================
np.set_printoptions(threshold=np.nan,
linewidth=1000,
precision=3,
suppress=True)
num_bins = args.num_bins
bin_limits = tuple([float(s) for s in args.bin_limits.split(";")])
data_proportion = args.data_proportion
num_data = int(data_proportion * celebA_loader.num_train_data)
eps = 1e-8
# file
f = open(join(
save_dir, 'log[bins={},bin_limits={},data={}].txt'.format(
num_bins, bin_limits, data_proportion)),
mode='w')
# print function
print_ = functools.partial(print_both, file=f)
'''
if attr_type == 0:
attr_names = celebA_loader.attributes
elif attr_type == 1:
attr_names = ['Male', 'Black_Hair', 'Blond_Hair', 'Straight_Hair', 'Wavy_Hair', 'Bald',
'Oval_Face', 'Big_Nose', 'Chubby', 'Double_Chin', 'Goatee', 'No_Beard',
'Mouth_Slightly_Open', 'Smiling',
'Eyeglasses', 'Pale_Skin']
else:
raise ValueError("Only support factor_type=0 or 1!")
'''
print_("num_bins: {}".format(num_bins))
print_("bin_limits: {}".format(bin_limits))
print_("data_proportion: {}".format(data_proportion))
# Compute bins
# ================================= #
print_("")
print_("bin_limits: {}".format(bin_limits))
assert len(bin_limits) == 2 and bin_limits[0] < bin_limits[
1], "bin_limits={}".format(bin_limits)
bins = np.linspace(bin_limits[0],
bin_limits[1],
num_bins + 1,
endpoint=True)
print_("bins: {}".format(bins))
assert len(bins) == num_bins + 1
bin_widths = [bins[b] - bins[b - 1] for b in range(1, len(bins))]
print_("bin_widths: {}".format(bin_widths))
assert len(bin_widths
) == num_bins, "len(bin_widths)={} while num_bins={}!".format(
len(bin_widths), num_bins)
assert np.all(np.greater(bin_widths,
0)), "bin_widths: {}".format(bin_widths)
bin_centers = [(bins[b] + bins[b - 1]) * 0.5 for b in range(1, len(bins))]
print_("bin_centers: {}".format(bin_centers))
assert len(bin_centers
) == num_bins, "len(bin_centers)={} while num_bins={}!".format(
len(bin_centers), num_bins)
# ================================= #
# Compute representations
# ================================= #
z_data_attr_file = join(save_dir,
"z_data[data={}].npz".format(data_proportion))
if not exists(z_data_attr_file):
all_z_mean = []
all_z_stddev = []
all_attrs = []
print("")
print("Compute all_z_mean, all_z_stddev and all_attrs!")
count = 0
for batch_ids in iterate_data(num_data,
10 * args.batch_size,
shuffle=False):
x = celebA_loader.sample_images_from_dataset(
sess, 'train', batch_ids)
attrs = celebA_loader.sample_attrs_from_dataset('train', batch_ids)
assert attrs.shape[1] == celebA_loader.num_attributes
z_mean, z_stddev = sess.run(model.get_output(
['z_mean', 'z_stddev']),
feed_dict={
model.is_train: False,
model.x_ph: x
})
all_z_mean.append(z_mean)
all_z_stddev.append(z_stddev)
all_attrs.append(attrs)
count += len(batch_ids)
print("\rProcessed {} samples!".format(count), end="")
print()
all_z_mean = np.concatenate(all_z_mean, axis=0)
all_z_stddev = np.concatenate(all_z_stddev, axis=0)
all_attrs = np.concatenate(all_attrs, axis=0)
np.savez_compressed(z_data_attr_file,
all_z_mean=all_z_mean,
all_z_stddev=all_z_stddev,
all_attrs=all_attrs)
else:
print("{} exists. Load data from file!".format(z_data_attr_file))
with np.load(z_data_attr_file, "r") as f:
all_z_mean = f['all_z_mean']
all_z_stddev = f['all_z_stddev']
all_attrs = f['all_attrs']
print_("")
print_("all_z_mean.shape: {}".format(all_z_mean.shape))
print_("all_z_stddev.shape: {}".format(all_z_stddev.shape))
print_("all_attrs.shape: {}".format(all_attrs.shape))
# ================================= #
# Compute the probability mass function for ground truth factors
# ================================= #
num_attrs = all_attrs.shape[1]
assert all_attrs.dtype == np.bool
all_attrs = all_attrs.astype(np.int32)
# (num_samples, num_attrs, 2) # The first component is 1 and the last component is 0
all_Q_y_cond_x = np.stack([all_attrs, 1 - all_attrs], axis=-1)
# ================================= #
# Compute Q(zi|x)
# Compute I(zi, yk)
# ================================= #
Q_z_y = np.zeros([args.z_dim, num_attrs, num_bins, 2], dtype=np.float32)
MI_z_y = np.zeros([args.z_dim, num_attrs], dtype=np.float32)
H_z_y = np.zeros([args.z_dim, num_attrs], dtype=np.float32)
H_z_4_diff_y = np.zeros([args.z_dim, num_attrs], dtype=np.float32)
H_y_4_diff_z = np.zeros([num_attrs, args.z_dim], dtype=np.float32)
for i in range(args.z_dim):
print_("")
print_("Compute all_Q_z{}_cond_x!".format(i))
# Q_s_cond_x
all_Q_s_cond_x = []
for batch_ids in iterate_data(len(all_z_mean),
500,
shuffle=False,
include_remaining=True):
# (batch_size, num_bins)
q_s_cond_x = normal_density(
np.expand_dims(bin_centers, axis=0),
mean=np.expand_dims(all_z_mean[batch_ids, i], axis=-1),
stddev=np.expand_dims(all_z_stddev[batch_ids, i], axis=-1))
# (batch_size, num_bins)
max_q_s_cond_x = np.max(q_s_cond_x, axis=-1)
# print("\nmax_q_s_cond_x: {}".format(np.sort(max_q_s_cond_x)))
# (batch_size, num_bins)
deter_s_cond_x = at_bin(all_z_mean[batch_ids, i],
bins).astype(np.float32)
# (batch_size, num_bins)
Q_s_cond_x = q_s_cond_x * np.expand_dims(bin_widths, axis=0)
Q_s_cond_x = Q_s_cond_x / np.maximum(
np.sum(Q_s_cond_x, axis=1, keepdims=True), eps)
# print("sort(sum(Q_s_cond_x)) (before): {}".format(np.sort(np.sum(Q_s_cond_x, axis=-1))))
Q_s_cond_x = np.where(
np.expand_dims(np.less(max_q_s_cond_x, 1e-5), axis=-1),
deter_s_cond_x, Q_s_cond_x)
# print("sort(sum(Q_s_cond_x)) (after): {}".format(np.sort(np.sum(Q_s_cond_x, axis=-1))))
all_Q_s_cond_x.append(Q_s_cond_x)
# (num_samples, num_bins)
all_Q_s_cond_x = np.concatenate(all_Q_s_cond_x, axis=0)
assert np.all(all_Q_s_cond_x >= 0), "'all_Q_s_cond_x' contains negative values. " \
"sorted_all_Q_s_cond_x[:30]:\n{}!".format(
np.sort(all_Q_s_cond_x[:30], axis=None))
assert len(all_Q_s_cond_x) == len(
all_attrs), "all_Q_s_cond_x.shape={}, all_attrs.shape={}".format(
all_Q_s_cond_x.shape, all_attrs.shape)
# I(z, y)
for k in range(num_attrs):
# Compute Q(zi, yk)
# -------------------------------- #
# (z_dim, 2)
Q_zi_yk = np.matmul(np.transpose(all_Q_s_cond_x, axes=[1, 0]),
all_Q_y_cond_x[:, k, :])
Q_zi_yk = Q_zi_yk / len(all_Q_y_cond_x)
Q_zi_yk = Q_zi_yk / np.maximum(np.sum(Q_zi_yk), eps)
assert np.all(Q_zi_yk >= 0), "'Q_zi_yk' contains negative values. " \
"sorted_Q_zi_yk[:10]:\n{}!".format(np.sort(Q_zi_yk, axis=None))
log_Q_zi_yk = np.log(np.clip(Q_zi_yk, eps, 1 - eps))
Q_z_y[i, k] = Q_zi_yk
print_("sum(Q_zi_yk): {}".format(np.sum(Q_zi_yk)))
# -------------------------------- #
# Compute Q_z
# -------------------------------- #
Q_zi = np.sum(Q_zi_yk, axis=1)
log_Q_zi = np.log(np.clip(Q_zi, eps, 1 - eps))
print_("sum(Q_z{}): {}".format(i, np.sum(Q_zi)))
print_("Q_z{}: {}".format(i, Q_zi))
# -------------------------------- #
# Compute Q_y
# -------------------------------- #
Q_yk = np.sum(Q_zi_yk, axis=0)
log_Q_yk = np.log(np.clip(Q_yk, eps, 1 - eps))
print_("sum(Q_y{}): {}".format(k, np.sum(Q_yk)))
print_("Q_y{}: {}".format(k, np.sum(Q_yk)))
# -------------------------------- #
MI_zi_yk = Q_zi_yk * (log_Q_zi_yk - np.expand_dims(
log_Q_zi, axis=-1) - np.expand_dims(log_Q_yk, axis=0))
MI_zi_yk = np.sum(MI_zi_yk)
H_zi_yk = -np.sum(Q_zi_yk * log_Q_zi_yk)
H_zi = -np.sum(Q_zi * log_Q_zi)
H_yk = -np.sum(Q_yk * log_Q_yk)
MI_z_y[i, k] = MI_zi_yk
H_z_y[i, k] = H_zi_yk
H_z_4_diff_y[i, k] = H_zi
H_y_4_diff_z[k, i] = H_yk
# ================================= #
print_("")
print_("MI_z_y:\n{}".format(MI_z_y))
print_("H_z_y:\n{}".format(H_z_y))
print_("H_z_4_diff_y:\n{}".format(H_z_4_diff_y))
print_("H_y_4_diff_z:\n{}".format(H_y_4_diff_z))
# Compute metric
# ================================= #
# Sorted in decreasing order
MI_ids_sorted = np.argsort(MI_z_y, axis=0)[::-1]
MI_sorted = np.take_along_axis(MI_z_y, MI_ids_sorted, axis=0)
MI_gap_y = np.divide(MI_sorted[0, :] - MI_sorted[1, :], H_y_4_diff_z[:, 0])
MIG = np.mean(MI_gap_y)
print_("")
print_("MI_sorted: {}".format(MI_sorted))
print_("MI_ids_sorted: {}".format(MI_ids_sorted))
print_("MI_gap_y: {}".format(MI_gap_y))
print_("MIG: {}".format(MIG))
results = {
'Q_z_y': Q_z_y,
'MI_z_y': MI_z_y,
'H_z_y': H_z_y,
'H_z_4_diff_y': H_z_4_diff_y,
'H_y_4_diff_z': H_y_4_diff_z,
'MI_sorted': MI_sorted,
'MI_ids_sorted': MI_ids_sorted,
'MI_gap_y': MI_gap_y,
'MIG': MIG,
}
result_file = join(
save_dir, 'results[bins={},bin_limits={},data={}].npz'.format(
num_bins, bin_limits, data_proportion))
np.savez_compressed(result_file, **results)
# ================================= #
f.close()
def main(args):
# =====================================
# Load config
# =====================================
with open(join(args.output_dir, 'config.json')) as f:
config = json.load(f)
args.__dict__.update(config)
# =====================================
# Dataset
# =====================================
data_file = join(RAW_DATA_DIR, "ComputerVision", "dSprites",
"dsprites_ndarray_co1sh3sc6or40x32y32_64x64.npz")
# It is already in the range [0, 1]
with np.load(data_file, encoding="latin1") as f:
x_train = f['imgs']
# 3 shape * 6 scale * 40 rotation * 32 pos X * 32 pos Y
y_train = f['latents_classes'][:, 1:]
x_train = np.expand_dims(x_train.astype(np.float32), axis=-1)
num_train = len(x_train)
print("num_train: {}".format(num_train))
# =====================================
# Instantiate model
# =====================================
if args.enc_dec_model == "1Konny":
encoder = Encoder_1Konny(args.z_dim, stochastic=True)
decoder = Decoder_1Konny()
disc_z = DiscriminatorZ_1Konny()
else:
raise ValueError("Do not support enc_dec_model='{}'!".format(args.enc_dec_model))
model = AAE([64, 64, 1], args.z_dim,
encoder=encoder, decoder=decoder,
discriminator_z=disc_z,
rec_x_mode=args.rec_x_mode,
stochastic_z=args.stochastic_z,
use_gp0_z=True, gp0_z_mode=args.gp0_z_mode)
loss_coeff_dict = {
'rec_x': args.rec_x_coeff,
'G_loss_z1_gen': args.G_loss_z1_gen_coeff,
'D_loss_z1_gen': args.D_loss_z1_gen_coeff,
'gp0_z': args.gp0_z_coeff,
}
model.build(loss_coeff_dict)
SimpleParamPrinter.print_all_params_tf_slim()
# =====================================
# Load model
# =====================================
config_proto = tf.ConfigProto(allow_soft_placement=True)
config_proto.gpu_options.allow_growth = True
config_proto.gpu_options.per_process_gpu_memory_fraction = 0.9
sess = tf.Session(config=config_proto)
model_dir = make_dir_if_not_exist(join(args.output_dir, "model_tf"))
train_helper = SimpleTrainHelper(log_dir=None, save_dir=model_dir)
# Load model
train_helper.load(sess, load_step=args.load_step)
# =====================================
# Experiments
save_dir = make_dir_if_not_exist(join(args.save_dir, "{}_{}".format(args.enc_dec_model, args.run)))
np.set_printoptions(threshold=np.nan, linewidth=1000, precision=5, suppress=True)
# =====================================
# Compute representations
# ================================= #
z_data_file = join(save_dir, "z_data.npz")
if not exists(z_data_file):
all_z_mean = []
all_z_stddev = []
print("")
print("Compute all_z_mean, all_z_stddev!")
count = 0
for batch_ids in iterate_data(num_train, 10 * args.batch_size, shuffle=False):
x = x_train[batch_ids]
z_samples, z_mean, z_stddev = sess.run(
model.get_output(['z1_gen', 'z_mean', 'z_stddev']),
feed_dict={model.is_train: False, model.x_ph: x})
all_z_mean.append(z_mean)
all_z_stddev.append(z_stddev)
count += len(batch_ids)
print("\rProcessed {} samples!".format(count), end="")
print()
all_z_mean = np.concatenate(all_z_mean, axis=0)
all_z_stddev = np.concatenate(all_z_stddev, axis=0)
np.savez_compressed(z_data_file, all_z_mean=all_z_mean, all_z_stddev=all_z_stddev)
else:
print("{} exists. Load data from file!".format(z_data_file))
with np.load(z_data_file, "r") as f:
all_z_mean = f['all_z_mean']
all_z_stddev = f['all_z_stddev']
# ================================= #
if args.gpu_support == 'cupy':
print("Use cupy instead of numpy!")
results = estimate_JEMMIG_cupy(all_z_mean, all_z_stddev, y=y_train,
num_samples=args.num_samples,
batch_size=args.batch, gpu=args.gpu_id)
else:
raise NotImplementedError("There is no numpy support since it is too slow!")
result_file = join(save_dir, "results[num_samples={}].npz".format(args.num_samples))
np.savez_compressed(result_file, **results)
f.close()
def main(args):
# =====================================
# Load config
# =====================================
with open(join(args.output_dir, 'config.json')) as f:
config = json.load(f)
args.__dict__.update(config)
# =====================================
# Dataset
# =====================================
data_file = join(RAW_DATA_DIR, "ComputerVision", "dSprites",
"dsprites_ndarray_co1sh3sc6or40x32y32_64x64.npz")
# It is already in the range [0, 1]
with np.load(data_file, encoding="latin1") as f:
x_train = f['imgs']
# 3 shape * 6 scale * 40 rotation * 32 pos X * 32 pos Y
y_train = f['latents_classes']
x_train = np.expand_dims(x_train.astype(np.float32), axis=-1)
num_train = len(x_train)
print("num_train: {}".format(num_train))
print("y_train[:10]: {}".format(y_train[:10]))
# =====================================
# Instantiate model
# =====================================
if args.enc_dec_model == "1Konny":
encoder = Encoder_1Konny(args.z_dim, stochastic=True)
decoder = Decoder_1Konny()
disc_z = DiscriminatorZ_1Konny()
else:
raise ValueError("Do not support enc_dec_model='{}'!".format(
args.enc_dec_model))
model = AAE([64, 64, 1],
args.z_dim,
encoder=encoder,
decoder=decoder,
discriminator_z=disc_z,
rec_x_mode=args.rec_x_mode,
stochastic_z=args.stochastic_z,
use_gp0_z=True,
gp0_z_mode=args.gp0_z_mode)
loss_coeff_dict = {
'rec_x': args.rec_x_coeff,
'G_loss_z1_gen': args.G_loss_z1_gen_coeff,
'D_loss_z1_gen': args.D_loss_z1_gen_coeff,
'gp0_z': args.gp0_z_coeff,
}
model.build(loss_coeff_dict)
SimpleParamPrinter.print_all_params_tf_slim()
# =====================================
# Load model
# =====================================
config_proto = tf.ConfigProto(allow_soft_placement=True)
config_proto.gpu_options.allow_growth = True
config_proto.gpu_options.per_process_gpu_memory_fraction = 0.9
sess = tf.Session(config=config_proto)
model_dir = make_dir_if_not_exist(join(args.output_dir, "model_tf"))
train_helper = SimpleTrainHelper(log_dir=None, save_dir=model_dir)
# Load model
train_helper.load(sess, load_step=args.load_step)
# =====================================
# Experiments
save_dir = make_dir_if_not_exist(
join(args.save_dir, "{}_{}".format(args.enc_dec_model, args.run)))
# =====================================
np.set_printoptions(threshold=np.nan,
linewidth=1000,
precision=5,
suppress=True)
num_bins = args.num_bins
bin_limits = tuple([float(s) for s in args.bin_limits.split(";")])
data_proportion = args.data_proportion
num_data = int(data_proportion * num_train)
assert num_data == num_train, "For dSprites, you must use all data!"
eps = 1e-8
# file
f = open(join(
save_dir, 'log[bins={},bin_limits={},data={}].txt'.format(
num_bins, bin_limits, data_proportion)),
mode='w')
# print function
print_ = functools.partial(print_both, file=f)
print_("num_bins: {}".format(num_bins))
print_("bin_limits: {}".format(bin_limits))
print_("data_proportion: {}".format(data_proportion))
# Compute bins
# ================================= #
print_("")
print_("bin_limits: {}".format(bin_limits))
assert len(bin_limits) == 2 and bin_limits[0] < bin_limits[
1], "bin_limits={}".format(bin_limits)
bins = np.linspace(bin_limits[0],
bin_limits[1],
num_bins + 1,
endpoint=True)
print_("bins: {}".format(bins))
assert len(bins) == num_bins + 1
bin_widths = [bins[b] - bins[b - 1] for b in range(1, len(bins))]
print_("bin_widths: {}".format(bin_widths))
assert len(bin_widths
) == num_bins, "len(bin_widths)={} while num_bins={}!".format(
len(bin_widths), num_bins)
assert np.all(np.greater(bin_widths,
0)), "bin_widths: {}".format(bin_widths)
bin_centers = [(bins[b] + bins[b - 1]) * 0.5 for b in range(1, len(bins))]
print_("bin_centers: {}".format(bin_centers))
assert len(bin_centers
) == num_bins, "len(bin_centers)={} while num_bins={}!".format(
len(bin_centers), num_bins)
# ================================= #
# Compute representations
# ================================= #
z_data_file = join(save_dir, "z_data[data={}].npz".format(data_proportion))
if not exists(z_data_file):
all_z_mean = []
all_z_stddev = []
print("")
print("Compute all_z_mean, all_z_stddev and all_attrs!")
count = 0
for batch_ids in iterate_data(num_data,
10 * args.batch_size,
shuffle=False):
x = x_train[batch_ids]
z_mean, z_stddev = sess.run(model.get_output(
['z_mean', 'z_stddev']),
feed_dict={
model.is_train: False,
model.x_ph: x
})
all_z_mean.append(z_mean)
all_z_stddev.append(z_stddev)
count += len(batch_ids)
print("\rProcessed {} samples!".format(count), end="")
print()
all_z_mean = np.concatenate(all_z_mean, axis=0)
all_z_stddev = np.concatenate(all_z_stddev, axis=0)
np.savez_compressed(z_data_file,
all_z_mean=all_z_mean,
all_z_stddev=all_z_stddev)
else:
print("{} exists. Load data from file!".format(z_data_file))
with np.load(z_data_file, "r") as f:
all_z_mean = f['all_z_mean']
all_z_stddev = f['all_z_stddev']
# ================================= #
print_("")
all_Q_z_cond_x = []
for i in range(args.z_dim):
print_("\nCompute all_Q_z{}_cond_x!".format(i))
all_Q_s_cond_x = []
for batch_ids in iterate_data(len(all_z_mean),
500,
shuffle=False,
include_remaining=True):
# (batch_size, num_bins)
q_s_cond_x = normal_density(
np.expand_dims(bin_centers, axis=0),
mean=np.expand_dims(all_z_mean[batch_ids, i], axis=-1),
stddev=np.expand_dims(all_z_stddev[batch_ids, i], axis=-1))
# (batch_size, num_bins)
max_q_s_cond_x = np.max(q_s_cond_x, axis=-1)
# print("\nmax_q_s_cond_x: {}".format(np.sort(max_q_s_cond_x)))
# (batch_size, num_bins)
deter_s_cond_x = at_bin(all_z_mean[batch_ids, i],
bins).astype(np.float32)
# (batch_size, num_bins)
Q_s_cond_x = q_s_cond_x * np.expand_dims(bin_widths, axis=0)
Q_s_cond_x = Q_s_cond_x / np.maximum(
np.sum(Q_s_cond_x, axis=1, keepdims=True), eps)
# print("sort(sum(Q_s_cond_x)) (before): {}".format(np.sort(np.sum(Q_s_cond_x, axis=-1))))
Q_s_cond_x = np.where(
np.expand_dims(np.less(max_q_s_cond_x, 1e-5), axis=-1),
deter_s_cond_x, Q_s_cond_x)
# print("sort(sum(Q_s_cond_x)) (after): {}".format(np.sort(np.sum(Q_s_cond_x, axis=-1))))
all_Q_s_cond_x.append(Q_s_cond_x)
# (num_samples, num_bins)
all_Q_s_cond_x = np.concatenate(all_Q_s_cond_x, axis=0)
assert np.all(all_Q_s_cond_x >= 0), "'all_Q_s_cond_x' contains negative values. " \
"sorted_all_Q_s_cond_x[:30]:\n{}!".format(np.sort(all_Q_s_cond_x[:30], axis=None))
assert len(all_Q_s_cond_x) == num_train
all_Q_z_cond_x.append(all_Q_s_cond_x)
# (z_dim, num_samples, num_bins)
all_Q_z_cond_x = np.asarray(all_Q_z_cond_x, dtype=np.float32)
print_("all_Q_z_cond_x.shape: {}".format(all_Q_z_cond_x.shape))
print_("sum(all_Q_z_cond_x)[:, :10]:\n{}".format(
np.sum(all_Q_z_cond_x, axis=-1)[:, :10]))
# (z_dim, num_bins)
Q_z = np.mean(all_Q_z_cond_x, axis=1)
log_Q_z = np.log(np.clip(Q_z, eps, 1 - eps))
print_("Q_z.shape: {}".format(Q_z.shape))
print_("sum(Q_z): {}".format(np.sum(Q_z, axis=-1)))
# (z_dim, )
H_z = -np.sum(Q_z * log_Q_z, axis=-1)
# Factors
gt_factors = ['shape', 'scale', 'rotation', 'pos_x', 'pos_y']
gt_num_values = [3, 6, 40, 32, 32]
MI_z_y = np.zeros([args.z_dim, len(gt_factors)], dtype=np.float32)
H_z_y = np.zeros([args.z_dim, len(gt_factors)], dtype=np.float32)
ids_sorted = np.zeros([args.z_dim, len(gt_factors)], dtype=np.int32)
MI_z_y_sorted = np.zeros([args.z_dim, len(gt_factors)], dtype=np.float32)
H_z_y_sorted = np.zeros([args.z_dim, len(gt_factors)], dtype=np.float32)
H_y = []
RMIG = []
JEMMI = []
for k, (factor, num_values) in enumerate(zip(gt_factors, gt_num_values)):
print_("\n#" + "=" * 50 + "#")
print_("The {}-th gt factor '{}' has {} values!".format(
k, factor, num_values))
print_("")
# (num_samples, num_categories)
# NOTE: We must use k+1 to account for the 'color' attribute, which is always white
all_Q_yk_cond_x = one_hot(y_train[:, k + 1],
num_categories=num_values,
dtype=np.float32)
print_("all_Q_yk_cond_x.shape: {}".format(all_Q_yk_cond_x.shape))
# (num_categories)
Q_yk = np.mean(all_Q_yk_cond_x, axis=0)
log_Q_yk = np.log(np.clip(Q_yk, eps, 1 - eps))
print_("Q_yk.shape: {}".format(Q_yk.shape))
H_yk = -np.sum(Q_yk * log_Q_yk)
print_("H_yk: {}".format(H_yk))
H_y.append(H_yk)
Q_z_yk = np.zeros([args.z_dim, num_bins, num_values], dtype=np.float32)
# Compute I(zi, yk)
for i in range(args.z_dim):
print_("\n#" + "-" * 50 + "#")
all_Q_zi_cond_x = all_Q_z_cond_x[i]
assert len(all_Q_zi_cond_x) == len(all_Q_yk_cond_x) == num_train, \
"all_Q_zi_cond_x.shape: {}, all_Q_yk_cond_x.shape: {}".format(
all_Q_zi_cond_x.shape, all_Q_yk_cond_x.shape)
# (num_bins, num_categories)
Q_zi_yk = np.matmul(np.transpose(all_Q_zi_cond_x, axes=[1, 0]),
all_Q_yk_cond_x)
Q_zi_yk = Q_zi_yk / num_train
print_("np.sum(Q_zi_yk): {}".format(np.sum(Q_zi_yk)))
Q_zi_yk = Q_zi_yk / np.maximum(np.sum(Q_zi_yk), eps)
print_("np.sum(Q_zi_yk) (normalized): {}".format(np.sum(Q_zi_yk)))
assert np.all(Q_zi_yk >= 0), "'Q_zi_yk' contains negative values. " \
"sorted_Q_zi_yk[:10]:\n{}!".format(np.sort(Q_zi_yk, axis=None))
# (num_bins, num_categories)
log_Q_zi_yk = np.log(np.clip(Q_zi_yk, eps, 1 - eps))
print_("")
print_("Q_zi (default): {}".format(Q_z[i]))
print_("Q_zi (sum of Q_zi_yk over yk): {}".format(
np.sum(Q_zi_yk, axis=-1)))
print_("")
print_("Q_yk (default): {}".format(Q_yk))
print_("Q_yk (sum of Q_zi_yk over zi): {}".format(
np.sum(Q_zi_yk, axis=0)))
MI_zi_yk = Q_zi_yk * (log_Q_zi_yk - np.expand_dims(
log_Q_z[i], axis=-1) - np.expand_dims(log_Q_yk, axis=0))
MI_zi_yk = np.sum(MI_zi_yk)
H_zi_yk = -np.sum(Q_zi_yk * log_Q_zi_yk)
Q_z_yk[i] = Q_zi_yk
MI_z_y[i, k] = MI_zi_yk
H_z_y[i, k] = H_zi_yk
print_("#" + "-" * 50 + "#")
# Print statistics for all z
print_("")
print_("MI_z_yk:\n{}".format(MI_z_y[:, k]))
print_("H_z_yk:\n{}".format(H_z_y[:, k]))
print_("H_z:\n{}".format(H_z))
print_("H_yk:\n{}".format(H_yk))
# Compute RMIG and JEMMI
ids_yk_sorted = np.argsort(MI_z_y[:, k], axis=0)[::-1]
MI_z_yk_sorted = np.take_along_axis(MI_z_y[:, k],
ids_yk_sorted,
axis=0)
H_z_yk_sorted = np.take_along_axis(H_z_y[:, k], ids_yk_sorted, axis=0)
RMIG_yk = np.divide(MI_z_yk_sorted[0] - MI_z_yk_sorted[1], H_yk)
JEMMI_yk = np.divide(
H_z_yk_sorted[0] - MI_z_yk_sorted[0] + MI_z_yk_sorted[1],
H_yk + np.log(num_bins))
ids_sorted[:, k] = ids_yk_sorted
MI_z_y_sorted[:, k] = MI_z_yk_sorted
H_z_y_sorted[:, k] = H_z_yk_sorted
RMIG.append(RMIG_yk)
JEMMI.append(JEMMI_yk)
print_("")
print_("ids_sorted: {}".format(ids_sorted))
print_("MI_z_yk_sorted: {}".format(MI_z_yk_sorted))
print_("RMIG_yk: {}".format(RMIG_yk))
print_("JEMMI_yk: {}".format(JEMMI_yk))
z_yk_prob_file = join(
save_dir,
"z_yk_prob_4_{}[bins={},bin_limits={},data={}].npz".format(
factor, num_bins, bin_limits, data_proportion))
np.savez_compressed(z_yk_prob_file, Q_z_yk=Q_z_yk)
print_("#" + "=" * 50 + "#")
results = {
"MI_z_y": MI_z_y,
"H_z_y": H_z_y,
"ids_sorted": ids_sorted,
"MI_z_y_sorted": MI_z_y_sorted,
"H_z_y_sorted": H_z_y_sorted,
"H_z": H_z,
"H_y": np.asarray(H_y, dtype=np.float32),
"RMIG": np.asarray(RMIG, dtype=np.float32),
"JEMMI": np.asarray(JEMMI, dtype=np.float32),
}
result_file = join(
save_dir, "results[bins={},bin_limits={},data={}].npz".format(
num_bins, bin_limits, data_proportion))
np.savez_compressed(result_file, **results)
f.close()
def main(args):
# =====================================
# Load config
# =====================================
with open(join(args.output_dir, 'config.json')) as f:
config = json.load(f)
args.__dict__.update(config)
# =====================================
# Dataset
# =====================================
celebA_loader = TFCelebAWithAttrLoader(root_dir=args.celebA_root_dir)
img_height, img_width = args.celebA_resize_size, args.celebA_resize_size
celebA_loader.build_transformation_flow_tf(
*celebA_loader.get_transform_fns("1Konny", resize_size=args.celebA_resize_size))
# =====================================
# Instantiate model
# =====================================
if args.activation == "relu":
activation = tf.nn.relu
elif args.activation == "leaky_relu":
activation = tf.nn.leaky_relu
else:
raise ValueError("Do not support '{}' activation!".format(args.activation))
if args.enc_dec_model == "1Konny":
# assert args.z_dim == 65, "For 1Konny, z_dim must be 65. Found {}!".format(args.z_dim)
encoder = Encoder_1Konny(args.z_dim, stochastic=True, activation=activation)
decoder = Decoder_1Konny([img_height, img_width, 3], activation=activation,
output_activation=tf.nn.sigmoid)
disc_z = DiscriminatorZ_1Konny()
else:
raise ValueError("Do not support encoder/decoder model '{}'!".format(args.enc_dec_model))
model = AAE([img_height, img_width, 3], args.z_dim,
encoder=encoder, decoder=decoder,
discriminator_z=disc_z,
rec_x_mode=args.rec_x_mode,
stochastic_z=args.stochastic_z,
use_gp0_z=True, gp0_z_mode=args.gp0_z_mode)
loss_coeff_dict = {
'rec_x': args.rec_x_coeff,
'G_loss_z1_gen': args.G_loss_z1_gen_coeff,
'D_loss_z1_gen': args.D_loss_z1_gen_coeff,
'gp0_z': args.gp0_z_coeff,
}
model.build(loss_coeff_dict)
SimpleParamPrinter.print_all_params_tf_slim()
# =====================================
# Load model
# =====================================
config_proto = tf.ConfigProto(allow_soft_placement=True)
config_proto.gpu_options.allow_growth = True
config_proto.gpu_options.per_process_gpu_memory_fraction = 0.9
sess = tf.Session(config=config_proto)
model_dir = make_dir_if_not_exist(join(args.output_dir, "model_tf"))
train_helper = SimpleTrainHelper(log_dir=None, save_dir=model_dir)
# Load model
train_helper.load(sess, load_step=args.load_step)
# =====================================
# Experiments
# save_dir = remove_dir_if_exist(join(args.save_dir, "AAE_{}".format(args.run)), ask_4_permission=True)
# save_dir = make_dir_if_not_exist(save_dir)
save_dir = make_dir_if_not_exist(join(args.save_dir, "AAE_{}".format(args.run)))
# =====================================
np.set_printoptions(threshold=np.nan, linewidth=1000, precision=4, suppress=True)
num_bins = args.num_bins
bin_limits = tuple([float(s) for s in args.bin_limits.split(";")])
data_proportion = args.data_proportion
num_data = int(data_proportion * celebA_loader.num_train_data)
eps = 1e-8
# file
f = open(join(save_dir, 'log[bins={},bin_limits={},data={}].txt'.
format(num_bins, bin_limits, data_proportion)), mode='w')
# print function
print_ = functools.partial(print_both, file=f)
print_("num_bins: {}".format(num_bins))
print_("bin_limits: {}".format(bin_limits))
print_("data_proportion: {}".format(data_proportion))
# Compute representations
# ================================= #
z_data_file = join(save_dir, "z_data[data={}].npz".format(data_proportion))
if not exists(z_data_file):
all_z_mean = []
all_z_stddev = []
print("")
print("Compute all_z_mean and all_z_stddev!")
count = 0
for batch_ids in iterate_data(num_data, 10 * args.batch_size, shuffle=False):
x = celebA_loader.sample_images_from_dataset(sess, 'train', batch_ids)
z_mean, z_stddev = sess.run(
model.get_output(['z_mean', 'z_stddev']),
feed_dict={model.is_train: False, model.x_ph: x})
all_z_mean.append(z_mean)
all_z_stddev.append(z_stddev)
count += len(batch_ids)
print("\rProcessed {} samples!".format(count), end="")
print()
all_z_mean = np.concatenate(all_z_mean, axis=0)
all_z_stddev = np.concatenate(all_z_stddev, axis=0)
np.savez_compressed(z_data_file, all_z_mean=all_z_mean, all_z_stddev=all_z_stddev)
else:
print("{} exists. Load data from file!".format(z_data_file))
with np.load(z_data_file, "r") as f:
all_z_mean = f['all_z_mean']
all_z_stddev = f['all_z_stddev']
print_("")
print_("all_z_mean.shape: {}".format(all_z_mean.shape))
print_("all_z_stddev.shape: {}".format(all_z_stddev.shape))
# ================================= #
# Compute bins
# ================================= #
print_("")
print_("bin_limits: {}".format(bin_limits))
assert len(bin_limits) == 2 and bin_limits[0] < bin_limits[1], "bin_limits={}".format(bin_limits)
bins = np.linspace(bin_limits[0], bin_limits[1], num_bins + 1, endpoint=True)
print_("bins: {}".format(bins))
assert len(bins) == num_bins + 1
bin_widths = [bins[b] - bins[b - 1] for b in range(1, len(bins))]
print_("bin_widths: {}".format(bin_widths))
assert len(bin_widths) == num_bins, "len(bin_widths)={} while num_bins={}!".format(len(bin_widths), num_bins)
assert np.all(np.greater(bin_widths, 0)), "bin_widths: {}".format(bin_widths)
bin_centers = [(bins[b] + bins[b - 1]) * 0.5 for b in range(1, len(bins))]
print_("bin_centers: {}".format(bin_centers))
assert len(bin_centers) == num_bins, "len(bin_centers)={} while num_bins={}!".format(len(bin_centers), num_bins)
# ================================= #
# Compute mutual information
# ================================= #
H_z = []
H_z_cond_x = []
MI_z_x = []
norm_MI_z_x = []
Q_z_cond_x = []
Q_z = []
for i in range(args.z_dim):
print_("")
print_("Compute I(z{}, x)!".format(i))
# Q_s_cond_x
all_Q_s_cond_x = []
for batch_ids in iterate_data(len(all_z_mean), 500, shuffle=False, include_remaining=True):
# (batch_size, num_bins)
q_s_cond_x = normal_density(np.expand_dims(bin_centers, axis=0),
mean=np.expand_dims(all_z_mean[batch_ids, i], axis=-1),
stddev=np.expand_dims(all_z_stddev[batch_ids, i], axis=-1))
# (batch_size, num_bins)
max_q_s_cond_x = np.max(q_s_cond_x, axis=-1)
# print("\nmax_q_s_cond_x: {}".format(np.sort(max_q_s_cond_x)))
# (batch_size, num_bins)
deter_s_cond_x = at_bin(all_z_mean[batch_ids, i], bins).astype(np.float32)
# (batch_size, num_bins)
Q_s_cond_x = q_s_cond_x * np.expand_dims(bin_widths, axis=0)
Q_s_cond_x = Q_s_cond_x / np.maximum(np.sum(Q_s_cond_x, axis=1, keepdims=True), eps)
# print("sort(sum(Q_s_cond_x)) (before): {}".format(np.sort(np.sum(Q_s_cond_x, axis=-1))))
Q_s_cond_x = np.where(np.expand_dims(np.less(max_q_s_cond_x, 1e-5), axis=-1),
deter_s_cond_x, Q_s_cond_x)
# print("sort(sum(Q_s_cond_x)) (after): {}".format(np.sort(np.sum(Q_s_cond_x, axis=-1))))
all_Q_s_cond_x.append(Q_s_cond_x)
all_Q_s_cond_x = np.concatenate(all_Q_s_cond_x, axis=0)
print_("sort(sum(all_Q_s_cond_x))[:10]: {}".format(
np.sort(np.sum(all_Q_s_cond_x, axis=-1), axis=0)[:100]))
assert np.all(all_Q_s_cond_x >= 0), "'all_Q_s_cond_x' contains negative values. " \
"sorted_all_Q_s_cond_x[:30]:\n{}!".format(np.sort(all_Q_s_cond_x[:30], axis=None))
Q_z_cond_x.append(all_Q_s_cond_x)
H_zi_cond_x = -np.mean(np.sum(all_Q_s_cond_x * np.log(np.maximum(all_Q_s_cond_x, eps)), axis=1), axis=0)
# Q_s
Q_s = np.mean(all_Q_s_cond_x, axis=0)
print_("Q_s: {}".format(Q_s))
print_("sum(Q_s): {}".format(sum(Q_s)))
assert np.all(Q_s >= 0), "'Q_s' contains negative values. " \
"sorted_Q_s[:10]:\n{}!".format(np.sort(Q_s, axis=None))
Q_s = Q_s / np.sum(Q_s, axis=0)
print_("sum(Q_s) (normalized): {}".format(sum(Q_s)))
Q_z.append(Q_s)
H_zi = -np.sum(Q_s * np.log(np.maximum(Q_s, eps)), axis=0)
MI_zi_x = H_zi - H_zi_cond_x
normalized_MI_zi_x = (1.0 * MI_zi_x) / (H_zi + eps)
print_("H_zi: {}".format(H_zi))
print_("H_zi_cond_x: {}".format(H_zi_cond_x))
print_("MI_zi_x: {}".format(MI_zi_x))
print_("normalized_MI_zi_x: {}".format(normalized_MI_zi_x))
H_z.append(H_zi)
H_z_cond_x.append(H_zi_cond_x)
MI_z_x.append(MI_zi_x)
norm_MI_z_x.append(normalized_MI_zi_x)
H_z = np.asarray(H_z, dtype=np.float32)
H_z_cond_x = np.asarray(H_z_cond_x, dtype=np.float32)
MI_z_x = np.asarray(MI_z_x, dtype=np.float32)
norm_MI_z_x = np.asarray(norm_MI_z_x, dtype=np.float32)
print_("")
print_("H_z: {}".format(H_z))
print_("H_z_cond_x: {}".format(H_z_cond_x))
print_("MI_z_x: {}".format(MI_z_x))
print_("norm_MI_z_x: {}".format(norm_MI_z_x))
sorted_z_comps = np.argsort(MI_z_x, axis=0)[::-1]
sorted_MI_z_x = np.take_along_axis(MI_z_x, sorted_z_comps, axis=0)
print_("sorted_MI_z_x: {}".format(sorted_MI_z_x))
print_("sorted_z_comps: {}".format(sorted_z_comps))
sorted_norm_z_comps = np.argsort(norm_MI_z_x, axis=0)[::-1]
sorted_norm_MI_z_x = np.take_along_axis(norm_MI_z_x, sorted_norm_z_comps, axis=0)
print_("sorted_norm_MI_z_x: {}".format(sorted_norm_MI_z_x))
print_("sorted_norm_z_comps: {}".format(sorted_norm_z_comps))
result_file = join(save_dir, 'results[bins={},bin_limits={},data={}].npz'.
format(num_bins, bin_limits, data_proportion))
np.savez_compressed(result_file,
H_z=H_z, H_z_cond_x=H_z_cond_x, MI_z_x=MI_z_x, norm_MI_z_x=norm_MI_z_x,
sorted_MI_z_x=sorted_MI_z_x, sorted_z_comps=sorted_z_comps,
sorted_norm_MI_z_x=sorted_norm_MI_z_x,
sorted_norm_z_comps=sorted_norm_z_comps)
Q_z_cond_x = np.asarray(Q_z_cond_x, dtype=np.float32)
Q_z = np.asarray(Q_z, dtype=np.float32)
z_prob_file = join(save_dir, 'z_prob[bins={},bin_limits={},data={}].npz'.
format(num_bins, bin_limits, data_proportion))
np.savez_compressed(z_prob_file, Q_z_cond_x=Q_z_cond_x, Q_z=Q_z)
def main(args):
# Load config
# ===================================== #
with open(join(args.output_dir, 'config.json')) as f:
config = json.load(f)
args.__dict__.update(config)
# ===================================== #
# Load dataset
# ===================================== #
data_file = join(RAW_DATA_DIR, "ComputerVision", "dSprites",
"dsprites_ndarray_co1sh3sc6or40x32y32_64x64.npz")
# It is already in the range [0, 1]
with np.load(data_file, encoding="latin1") as f:
x_train = f['imgs']
# 3 shape * 6 scale * 40 rotation * 32 pos X * 32 pos Y
y_train = f['latents_classes'][:, 1:]
x_train = np.expand_dims(x_train.astype(np.float32), axis=-1)
num_train = len(x_train)
print("num_train: {}".format(num_train))
# ===================================== #
# Build model
# ===================================== #
if args.enc_dec_model == "1Konny":
encoder = Encoder_1Konny(args.z_dim, stochastic=True)
decoder = Decoder_1Konny()
disc_z = DiscriminatorZ_1Konny()
else:
raise ValueError("Do not support enc_dec_model='{}'!".format(
args.enc_dec_model))
model = AAE([64, 64, 1],
args.z_dim,
encoder=encoder,
decoder=decoder,
discriminator_z=disc_z,
rec_x_mode=args.rec_x_mode,
stochastic_z=args.stochastic_z,
use_gp0_z=True,
gp0_z_mode=args.gp0_z_mode)
loss_coeff_dict = {
'rec_x': args.rec_x_coeff,
'G_loss_z1_gen': args.G_loss_z1_gen_coeff,
'D_loss_z1_gen': args.D_loss_z1_gen_coeff,
'gp0_z': args.gp0_z_coeff,
}
model.build(loss_coeff_dict)
SimpleParamPrinter.print_all_params_tf_slim()
# ===================================== #
# Initialize session
# ===================================== #
config_proto = tf.ConfigProto(allow_soft_placement=True)
config_proto.gpu_options.allow_growth = True
config_proto.gpu_options.per_process_gpu_memory_fraction = 0.9
sess = tf.Session(config=config_proto)
model_dir = make_dir_if_not_exist(join(args.output_dir, "model_tf"))
train_helper = SimpleTrainHelper(log_dir=None, save_dir=model_dir)
train_helper.load(sess, load_step=args.load_step)
# ===================================== #
# Experiments
# ===================================== #
save_dir = make_dir_if_not_exist(
join(args.save_dir, "{}_{}".format(args.enc_dec_model, args.run)))
np.set_printoptions(threshold=np.nan,
linewidth=1000,
precision=5,
suppress=True)
# ===================================== #
# Compute representations
# ===================================== #
z_data_file = join(save_dir, "z_data.npz")
if not exists(z_data_file):
all_z_mean = []
all_z_stddev = []
print("")
print("Compute all_z_mean, all_z_stddev!")
count = 0
for batch_ids in iterate_data(num_train,
10 * args.batch_size,
shuffle=False):
x = x_train[batch_ids]
z_samples, z_mean, z_stddev = sess.run(model.get_output(
['z1_gen', 'z_mean', 'z_stddev']),
feed_dict={
model.is_train: False,
model.x_ph: x
})
all_z_mean.append(z_mean)
all_z_stddev.append(z_stddev)
count += len(batch_ids)
print("\rProcessed {} samples!".format(count), end="")
print()
all_z_mean = np.concatenate(all_z_mean, axis=0)
all_z_stddev = np.concatenate(all_z_stddev, axis=0)
np.savez_compressed(z_data_file,
all_z_mean=all_z_mean,
all_z_stddev=all_z_stddev)
else:
print("{} exists. Load data from file!".format(z_data_file))
with np.load(z_data_file, "r") as f:
all_z_mean = f['all_z_mean']
all_z_stddev = f['all_z_stddev']
# ===================================== #
cont_mask = [False, True, True, True, True
] if args.continuous_only else None
if args.classifier == "LASSO":
results = compute_metrics_with_LASSO(latents=all_z_mean,
factors=y_train,
params={
'alpha': args.LASSO_alpha,
'max_iter': args.LASSO_iters
},
cont_mask=cont_mask)
result_file = join(
save_dir, "results[LASSO,{},alpha={},iters={}].npz".format(
"cont" if args.continuous_only else "all", args.LASSO_alpha,
args.LASSO_iters))
else:
results = compute_metrics_with_RandomForest(latents=all_z_mean,
factors=y_train,
params={
'n_estimators':
args.RF_trees,
'max_depth':
args.RF_depth
})
result_file = join(
save_dir, "results[RF,{},trees={},depth={}].npz".format(
"cont" if args.continuous_only else "all", args.RF_trees,
args.RF_depth))
np.savez_compressed(result_file, **results)
def main(args):
# =====================================
# Load config
# =====================================
with open(join(args.output_dir, 'config.json')) as f:
config = json.load(f)
args.__dict__.update(config)
# =====================================
# Dataset
# =====================================
data_file = join(RAW_DATA_DIR, "ComputerVision", "dSprites",
"dsprites_ndarray_co1sh3sc6or40x32y32_64x64.npz")
# It is already in the range [0, 1]
with np.load(data_file, encoding="latin1") as f:
x_train = f['imgs']
# 3 shape * 6 scale * 40 rotation * 32 pos X * 32 pos Y
y_train = f['latents_classes']
x_train = np.expand_dims(x_train.astype(np.float32), axis=-1)
num_train = len(x_train)
print("num_train: {}".format(num_train))
print("y_train[:10]: {}".format(y_train[:10]))
# =====================================
# Instantiate model
# =====================================
if args.enc_dec_model == "1Konny":
encoder = Encoder_1Konny(args.z_dim, stochastic=True)
decoder = Decoder_1Konny()
disc_z = DiscriminatorZ_1Konny()
else:
raise ValueError("Do not support enc_dec_model='{}'!".format(args.enc_dec_model))
model = AAE([64, 64, 1], args.z_dim,
encoder=encoder, decoder=decoder,
discriminator_z=disc_z,
rec_x_mode=args.rec_x_mode,
stochastic_z=args.stochastic_z,
use_gp0_z=True, gp0_z_mode=args.gp0_z_mode)
loss_coeff_dict = {
'rec_x': args.rec_x_coeff,
'G_loss_z1_gen': args.G_loss_z1_gen_coeff,
'D_loss_z1_gen': args.D_loss_z1_gen_coeff,
'gp0_z': args.gp0_z_coeff,
}
model.build(loss_coeff_dict)
SimpleParamPrinter.print_all_params_tf_slim()
# =====================================
# Load model
# =====================================
config_proto = tf.ConfigProto(allow_soft_placement=True)
config_proto.gpu_options.allow_growth = True
config_proto.gpu_options.per_process_gpu_memory_fraction = 0.9
sess = tf.Session(config=config_proto)
model_dir = make_dir_if_not_exist(join(args.output_dir, "model_tf"))
train_helper = SimpleTrainHelper(log_dir=None, save_dir=model_dir)
# Load model
train_helper.load(sess, load_step=args.load_step)
# =====================================
# Experiments
save_dir = make_dir_if_not_exist(join(args.save_dir, "{}_{}".format(args.enc_dec_model, args.run)))
# =====================================
np.set_printoptions(threshold=np.nan, linewidth=1000, precision=5, suppress=True)
num_bins = args.num_bins
bin_limits = tuple([float(s) for s in args.bin_limits.split(";")])
data_proportion = args.data_proportion
num_data = int(data_proportion * num_train)
assert num_data == num_train, "For dSprites, you must use all data!"
eps = 1e-8
# file
f = open(join(save_dir, 'log[bins={},bin_limits={},data={}].txt'.
format(num_bins, bin_limits, data_proportion)), mode='w')
# print function
print_ = functools.partial(print_both, file=f)
print_("num_bins: {}".format(num_bins))
print_("bin_limits: {}".format(bin_limits))
print_("data_proportion: {}".format(data_proportion))
# Compute bins
# ================================= #
print_("")
print_("bin_limits: {}".format(bin_limits))
assert len(bin_limits) == 2 and bin_limits[0] < bin_limits[1], "bin_limits={}".format(bin_limits)
bins = np.linspace(bin_limits[0], bin_limits[1], num_bins + 1, endpoint=True)
print_("bins: {}".format(bins))
assert len(bins) == num_bins + 1
bin_widths = [bins[b] - bins[b - 1] for b in range(1, len(bins))]
print_("bin_widths: {}".format(bin_widths))
assert len(bin_widths) == num_bins, "len(bin_widths)={} while num_bins={}!".format(len(bin_widths), num_bins)
assert np.all(np.greater(bin_widths, 0)), "bin_widths: {}".format(bin_widths)
bin_centers = [(bins[b] + bins[b - 1]) * 0.5 for b in range(1, len(bins))]
print_("bin_centers: {}".format(bin_centers))
assert len(bin_centers) == num_bins, "len(bin_centers)={} while num_bins={}!".format(len(bin_centers), num_bins)
# ================================= #
# Compute representations
# ================================= #
z_data_file = join(save_dir, "z_data[data={}].npz".format(data_proportion))
if not exists(z_data_file):
all_z_mean = []
all_z_stddev = []
print("")
print("Compute all_z_mean, all_z_stddev and all_attrs!")
count = 0
for batch_ids in iterate_data(num_data, 10 * args.batch_size, shuffle=False):
x = x_train[batch_ids]
z_mean, z_stddev = sess.run(
model.get_output(['z_mean', 'z_stddev']),
feed_dict={model.is_train: False, model.x_ph: x})
all_z_mean.append(z_mean)
all_z_stddev.append(z_stddev)
count += len(batch_ids)
print("\rProcessed {} samples!".format(count), end="")
print()
all_z_mean = np.concatenate(all_z_mean, axis=0)
all_z_stddev = np.concatenate(all_z_stddev, axis=0)
np.savez_compressed(z_data_file, all_z_mean=all_z_mean,
all_z_stddev=all_z_stddev)
else:
print("{} exists. Load data from file!".format(z_data_file))
with np.load(z_data_file, "r") as f:
all_z_mean = f['all_z_mean']
all_z_stddev = f['all_z_stddev']
# ================================= #
# Compute mutual information
# ================================= #
H_z = []
H_z_cond_x = []
MI_z_x = []
norm_MI_z_x = []
Q_z_cond_x = []
for i in range(args.z_dim):
print_("")
print_("Compute I(z{}, x)!".format(i))
# Q_s_cond_x
all_Q_s_cond_x = []
for batch_ids in iterate_data(len(all_z_mean), 500, shuffle=False, include_remaining=True):
# (batch_size, num_bins)
q_s_cond_x = normal_density(np.expand_dims(bin_centers, axis=0),
mean=np.expand_dims(all_z_mean[batch_ids, i], axis=-1),
stddev=np.expand_dims(all_z_stddev[batch_ids, i], axis=-1))
# (batch_size, num_bins)
max_q_s_cond_x = np.max(q_s_cond_x, axis=-1)
# print("\nmax_q_s_cond_x: {}".format(np.sort(max_q_s_cond_x)))
# (batch_size, num_bins)
deter_s_cond_x = at_bin(all_z_mean[batch_ids, i], bins).astype(np.float32)
# (batch_size, num_bins)
Q_s_cond_x = q_s_cond_x * np.expand_dims(bin_widths, axis=0)
Q_s_cond_x = Q_s_cond_x / np.maximum(np.sum(Q_s_cond_x, axis=1, keepdims=True), eps)
# print("sort(sum(Q_s_cond_x)) (before): {}".format(np.sort(np.sum(Q_s_cond_x, axis=-1))))
Q_s_cond_x = np.where(np.expand_dims(np.less(max_q_s_cond_x, 1e-5), axis=-1),
deter_s_cond_x, Q_s_cond_x)
# print("sort(sum(Q_s_cond_x)) (after): {}".format(np.sort(np.sum(Q_s_cond_x, axis=-1))))
all_Q_s_cond_x.append(Q_s_cond_x)
all_Q_s_cond_x = np.concatenate(all_Q_s_cond_x, axis=0)
print_("sort(sum(all_Q_s_cond_x))[:10]: {}".format(
np.sort(np.sum(all_Q_s_cond_x, axis=-1), axis=0)[:100]))
assert np.all(all_Q_s_cond_x >= 0), "'all_Q_s_cond_x' contains negative values. " \
"sorted_all_Q_s_cond_x[:30]:\n{}!".format(
np.sort(all_Q_s_cond_x[:30], axis=None))
Q_z_cond_x.append(all_Q_s_cond_x)
H_zi_cond_x = -np.mean(np.sum(all_Q_s_cond_x * np.log(np.maximum(all_Q_s_cond_x, eps)), axis=1), axis=0)
# Q_s
Q_s = np.mean(all_Q_s_cond_x, axis=0)
print_("Q_s: {}".format(Q_s))
print_("sum(Q_s): {}".format(sum(Q_s)))
assert np.all(Q_s >= 0), "'Q_s' contains negative values. " \
"sorted_Q_s[:10]:\n{}!".format(np.sort(Q_s, axis=None))
Q_s = Q_s / np.sum(Q_s, axis=0)
print_("sum(Q_s) (normalized): {}".format(sum(Q_s)))
H_zi = -np.sum(Q_s * np.log(np.maximum(Q_s, eps)), axis=0)
MI_zi_x = H_zi - H_zi_cond_x
normalized_MI_zi_x = (1.0 * MI_zi_x) / (H_zi + eps)
print_("H_zi: {}".format(H_zi))
print_("H_zi_cond_x: {}".format(H_zi_cond_x))
print_("MI_zi_x: {}".format(MI_zi_x))
print_("normalized_MI_zi_x: {}".format(normalized_MI_zi_x))
H_z.append(H_zi)
H_z_cond_x.append(H_zi_cond_x)
MI_z_x.append(MI_zi_x)
norm_MI_z_x.append(normalized_MI_zi_x)
H_z = np.asarray(H_z, dtype=np.float32)
H_z_cond_x = np.asarray(H_z_cond_x, dtype=np.float32)
MI_z_x = np.asarray(MI_z_x, dtype=np.float32)
norm_MI_z_x = np.asarray(norm_MI_z_x, dtype=np.float32)
print_("")
print_("H_z: {}".format(H_z))
print_("H_z_cond_x: {}".format(H_z_cond_x))
print_("MI_z_x: {}".format(MI_z_x))
print_("norm_MI_z_x: {}".format(norm_MI_z_x))
sorted_z_comps = np.argsort(MI_z_x, axis=0)[::-1]
sorted_MI_z_x = np.take_along_axis(MI_z_x, sorted_z_comps, axis=0)
print_("sorted_MI_z_x: {}".format(sorted_MI_z_x))
print_("sorted_z_comps: {}".format(sorted_z_comps))
sorted_norm_z_comps = np.argsort(norm_MI_z_x, axis=0)[::-1]
sorted_norm_MI_z_x = np.take_along_axis(norm_MI_z_x, sorted_norm_z_comps, axis=0)
print_("sorted_norm_MI_z_x: {}".format(sorted_norm_MI_z_x))
print_("sorted_norm_z_comps: {}".format(sorted_norm_z_comps))
result_file = join(save_dir, 'results[bins={},bin_limits={},data={}].npz'.
format(num_bins, bin_limits, data_proportion))
np.savez_compressed(result_file,
H_z=H_z, H_z_cond_x=H_z_cond_x, MI_z_x=MI_z_x, norm_MI_z_x=norm_MI_z_x,
sorted_MI_z_x=sorted_MI_z_x, sorted_z_comps=sorted_z_comps,
sorted_norm_MI_z_x=sorted_norm_MI_z_x,
sorted_norm_z_comps=sorted_norm_z_comps)
Q_z_cond_x = np.asarray(Q_z_cond_x, dtype=np.float32)
z_prob_file = join(save_dir, 'z_prob[bins={},bin_limits={},data={}].npz'.
format(num_bins, bin_limits, data_proportion))
np.savez_compressed(z_prob_file, Q_z_cond_x=Q_z_cond_x)
# ================================= #
f.close()
def main(args):
# =====================================
# Load config
# =====================================
with open(os.path.join(args.output_dir, 'config.json')) as f:
config = json.load(f)
args.__dict__.update(config)
# =====================================
# Preparation
# =====================================
celebA_loader = TFCelebALoader(root_dir=args.celebA_root_dir)
num_train = celebA_loader.num_train_data
num_test = celebA_loader.num_test_data
img_height, img_width = args.celebA_resize_size, args.celebA_resize_size
celebA_loader.build_transformation_flow_tf(
*celebA_loader.get_transform_fns("1Konny",
resize_size=args.celebA_resize_size))
# =====================================
# Instantiate models
# =====================================
# Only use activation for encoder and decoder
if args.activation == "relu":
activation = tf.nn.relu
elif args.activation == "leaky_relu":
activation = tf.nn.leaky_relu
else:
raise ValueError("Do not support '{}' activation!".format(
args.activation))
if args.enc_dec_model == "1Konny":
# assert args.z_dim == 65, "For 1Konny, z_dim must be 65. Found {}!".format(args.z_dim)
encoder = Encoder_1Konny(args.z_dim,
stochastic=True,
activation=activation)
decoder = Decoder_1Konny([img_height, img_width, 3],
activation=activation,
output_activation=tf.nn.sigmoid)
disc_z = DiscriminatorZ_1Konny()
else:
raise ValueError("Do not support encoder/decoder model '{}'!".format(
args.enc_dec_model))
model = AAE([img_height, img_width, 3],
args.z_dim,
encoder=encoder,
decoder=decoder,
discriminator_z=disc_z,
rec_x_mode=args.rec_x_mode,
stochastic_z=args.stochastic_z,
use_gp0_z=True,
gp0_z_mode=args.gp0_z_mode)
loss_coeff_dict = {
'rec_x': args.rec_x_coeff,
'G_loss_z1_gen': args.G_loss_z1_gen_coeff,
'D_loss_z1_gen': args.D_loss_z1_gen_coeff,
'gp0_z': args.gp0_z_coeff,
}
model.build(loss_coeff_dict)
SimpleParamPrinter.print_all_params_list()
# =====================================
# TF Graph Handler
asset_dir = make_dir_if_not_exist(os.path.join(args.output_dir, "asset"))
img_eval = remove_dir_if_exist(os.path.join(asset_dir, "img_eval"),
ask_4_permission=False)
img_eval = make_dir_if_not_exist(img_eval)
img_x_gen = make_dir_if_not_exist(os.path.join(img_eval, "x_gen"))
img_x_rec = make_dir_if_not_exist(os.path.join(img_eval, "x_rec"))
img_z_rand_2_traversal = make_dir_if_not_exist(
os.path.join(img_eval, "z_rand_2_traversal"))
img_z_cond_all_traversal = make_dir_if_not_exist(
os.path.join(img_eval, "z_cond_all_traversal"))
img_z_cond_1_traversal = make_dir_if_not_exist(
os.path.join(img_eval, "z_cond_1_traversal"))
img_z_corr = make_dir_if_not_exist(os.path.join(img_eval, "z_corr"))
img_z_dist = make_dir_if_not_exist(os.path.join(img_eval, "z_dist"))
img_z_stat_dist = make_dir_if_not_exist(
os.path.join(img_eval, "z_stat_dist"))
# img_rec_error_dist = make_dir_if_not_exist(os.path.join(img_eval, "rec_error_dist"))
model_dir = make_dir_if_not_exist(os.path.join(args.output_dir,
"model_tf"))
train_helper = SimpleTrainHelper(log_dir=None, save_dir=model_dir)
# =====================================
# =====================================
# Training Loop
# =====================================
config_proto = tf.ConfigProto(allow_soft_placement=True)
config_proto.gpu_options.allow_growth = True
config_proto.gpu_options.per_process_gpu_memory_fraction = 0.9
sess = tf.Session(config=config_proto)
# Load model
train_helper.load(sess, load_step=args.load_step)
# '''
# Generation
# ======================================= #
z = np.random.randn(64, args.z_dim)
img_file = os.path.join(img_x_gen, 'x_gen_test.png')
model.generate_images(img_file,
sess,
z,
block_shape=[8, 8],
batch_size=args.batch_size,
dec_output_2_img_func=binary_float_to_uint8)
# ======================================= #
# '''
# '''
# Reconstruction
# ======================================= #
seed = 389
x = celebA_loader.sample_images_from_dataset(sess, 'test',
list(range(seed, seed + 64)))
img_file = os.path.join(img_x_rec, 'x_rec_test.png')
model.reconstruct_images(img_file,
sess,
x,
block_shape=[8, 8],
batch_size=-1,
dec_output_2_img_func=binary_float_to_uint8)
# ======================================= #
# '''
# '''
# z random traversal
# ======================================= #
if args.z_dim <= 5:
print("z_dim = {}, perform random traversal!".format(args.z_dim))
# Plot z cont with z cont
z_zero = np.zeros([args.z_dim], dtype=np.float32)
z_rand = np.random.randn(args.z_dim)
z_start, z_stop = -4, 4
num_points = 8
for i in range(args.z_dim):
for j in range(i + 1, args.z_dim):
print(
"Plot random 2 comps z traverse with {} and {} components!"
.format(i, j))
img_file = os.path.join(img_z_rand_2_traversal,
'z[{},{},zero].png'.format(i, j))
model.rand_2_latents_traverse(
img_file,
sess,
default_z=z_zero,
z_comp1=i,
start1=z_start,
stop1=z_stop,
num_points1=num_points,
z_comp2=j,
start2=z_start,
stop2=z_stop,
num_points2=num_points,
batch_size=args.batch_size,
dec_output_2_img_func=binary_float_to_uint8)
img_file = os.path.join(img_z_rand_2_traversal,
'z[{},{},rand].png'.format(i, j))
model.rand_2_latents_traverse(
img_file,
sess,
default_z=z_rand,
z_comp1=i,
start1=z_start,
stop1=z_stop,
num_points1=num_points,
z_comp2=j,
start2=z_stop,
stop2=z_stop,
num_points2=num_points,
batch_size=args.batch_size,
dec_output_2_img_func=binary_float_to_uint8)
# ======================================= #
# '''
# z conditional traversal (all features + one feature)
# ======================================= #
seed = 389
num_samples = 30
data = celebA_loader.sample_images_from_dataset(
sess, 'train', list(range(seed, seed + num_samples)))
z_start, z_stop = -4, 4
num_itpl_points = 8
for n in range(num_samples):
print("Plot conditional all comps z traverse with test sample {}!".
format(n))
img_file = os.path.join(img_z_cond_all_traversal,
'x_train{}.png'.format(n))
model.cond_all_latents_traverse(
img_file,
sess,
data[n],
start=z_start,
stop=z_stop,
num_itpl_points=num_itpl_points,
batch_size=args.batch_size,
dec_output_2_img_func=binary_float_to_uint8)
z_start, z_stop = -4, 4
num_itpl_points = 8
for i in range(args.z_dim):
print("Plot conditional z traverse with comp {}!".format(i))
img_file = os.path.join(
img_z_cond_1_traversal,
'x_train[{},{}]_z{}.png'.format(seed, seed + num_samples, i))
model.cond_1_latent_traverse(
img_file,
sess,
data,
z_comp=i,
start=z_start,
stop=z_stop,
num_itpl_points=num_itpl_points,
batch_size=args.batch_size,
dec_output_2_img_func=binary_float_to_uint8)
# ======================================= #
# '''
# '''
# z correlation matrix
# ======================================= #
all_z = []
for batch_ids in iterate_data(num_train, args.batch_size, shuffle=False):
x = celebA_loader.sample_images_from_dataset(sess, 'train', batch_ids)
z = model.encode(sess, x)
assert len(
z.shape) == 2 and z.shape[1] == args.z_dim, "z.shape: {}".format(
z.shape)
all_z.append(z)
all_z = np.concatenate(all_z, axis=0)
print("Start plotting!")
plot_corrmat_with_histogram(os.path.join(img_z_corr, "corr_mat.png"),
all_z)
plot_comp_dist(os.path.join(img_z_dist, 'z_{}'), all_z, x_lim=(-5, 5))
print("Done!")
# ======================================= #
# '''
# '''
# z gaussian stddev
# ======================================= #
print("\nPlot z mean and stddev!")
all_z_mean = []
all_z_stddev = []
for batch_ids in iterate_data(num_train, args.batch_size, shuffle=False):
x = celebA_loader.sample_images_from_dataset(sess, 'train', batch_ids)
z_mean, z_stddev = sess.run(model.get_output(['z_mean', 'z_stddev']),
feed_dict={
model.is_train: False,
model.x_ph: x
})
all_z_mean.append(z_mean)
all_z_stddev.append(z_stddev)
all_z_mean = np.concatenate(all_z_mean, axis=0)
all_z_stddev = np.concatenate(all_z_stddev, axis=0)
plot_comp_dist(os.path.join(img_z_stat_dist, 'z_mean_{}.png'),
all_z_mean,
x_lim=(-5, 5))
plot_comp_dist(os.path.join(img_z_stat_dist, 'z_stddev_{}.png'),
all_z_stddev,
x_lim=(-0.5, 3))
def main(args):
# =====================================
# Preparation
# =====================================
data_file = os.path.join(RAW_DATA_DIR, "ComputerVision", "dSprites",
"dsprites_ndarray_co1sh3sc6or40x32y32_64x64.npz")
# It is already in the range [0, 1]
with np.load(data_file, encoding="latin1") as f:
x_train = f['imgs']
x_train = np.expand_dims(x_train.astype(np.float32), axis=-1)
num_train = len(x_train)
print("Number of training samples for dSprites: {}".format(num_train))
args.output_dir = os.path.join(args.output_dir, args.run)
if not os.path.exists(args.output_dir):
os.makedirs(args.output_dir)
else:
if args.force_rm_dir:
import shutil
shutil.rmtree(args.output_dir, ignore_errors=True)
print("Removed '{}'".format(args.output_dir))
else:
raise ValueError("Output directory '{}' existed. 'force_rm_dir' "
"must be set to True!".format(args.output_dir))
os.mkdir(args.output_dir)
save_args(os.path.join(args.output_dir, 'config.json'), args)
# pp.pprint(args.__dict__)
# =====================================
# Instantiate models
# =====================================
if args.enc_dec_model == "1Konny":
encoder = Encoder_1Konny(args.z_dim, stochastic=True)
decoder = Decoder_1Konny()
disc_z = DiscriminatorZ_1Konny()
else:
raise ValueError("Do not support enc_dec_model='{}'!".format(args.enc_dec_model))
model = AAE([64, 64, 1], args.z_dim,
encoder=encoder, decoder=decoder,
discriminator_z=disc_z,
rec_x_mode=args.rec_x_mode,
stochastic_z=args.stochastic_z,
use_gp0_z=True, gp0_z_mode=args.gp0_z_mode)
loss_coeff_dict = {
'rec_x': args.rec_x_coeff,
'G_loss_z1_gen': args.G_loss_z1_gen_coeff,
'D_loss_z1_gen': args.D_loss_z1_gen_coeff,
'gp0_z': args.gp0_z_coeff,
}
model.build(loss_coeff_dict)
SimpleParamPrinter.print_all_params_list()
loss = model.get_loss()
train_params = model.get_train_params()
opt_Dz = tf.train.AdamOptimizer(learning_rate=args.lr_Dz, beta1=args.beta1_Dz, beta2=args.beta2_Dz)
opt_AE = tf.train.AdamOptimizer(learning_rate=args.lr_AE, beta1=args.beta1_AE, beta2=args.beta2_AE)
with tf.control_dependencies(model.get_all_update_ops()):
train_op_Dz = opt_Dz.minimize(loss=loss['Dz_loss'], var_list=train_params['Dz_loss'])
train_op_D = train_op_Dz
train_op_AE = opt_AE.minimize(loss=loss['AE_loss'], var_list=train_params['AE_loss'])
# =====================================
# TF Graph Handler
asset_dir = make_dir_if_not_exist(os.path.join(args.output_dir, "asset"))
img_gen_dir = make_dir_if_not_exist(os.path.join(asset_dir, "img_gen"))
img_rec_dir = make_dir_if_not_exist(os.path.join(asset_dir, "img_rec"))
img_itpl_dir = make_dir_if_not_exist(os.path.join(asset_dir, "img_itpl"))
log_dir = make_dir_if_not_exist(os.path.join(args.output_dir, "log"))
train_log_file = os.path.join(log_dir, "train.log")
summary_dir = make_dir_if_not_exist(os.path.join(args.output_dir, "summary_tf"))
model_dir = make_dir_if_not_exist(os.path.join(args.output_dir, "model_tf"))
train_helper = SimpleTrainHelper(
log_dir=summary_dir,
save_dir=model_dir,
max_to_keep=3,
max_to_keep_best=1,
)
# =====================================
# =====================================
# Training Loop
# =====================================
config_proto = tf.ConfigProto(allow_soft_placement=True)
config_proto.gpu_options.allow_growth = True
config_proto.gpu_options.per_process_gpu_memory_fraction = 0.9
sess = tf.Session(config=config_proto)
train_helper.initialize(sess, init_variables=True, create_summary_writer=True)
Dz_fetch_keys = ['Dz_loss', 'D_loss_z0', 'D_loss_z1_gen',
'D_avg_prob_z0', 'D_avg_prob_z1_gen', 'gp0_z']
D_fetch_keys = Dz_fetch_keys
AE_fetch_keys = ['AE_loss', 'rec_x', 'G_loss_z1_gen']
global_step = 0
for epoch in range(args.epochs):
for batch_ids in iterate_data(num_train, args.batch_size, shuffle=True):
global_step += 1
x = x_train[batch_ids]
z = np.random.normal(size=[len(x), args.z_dim])
for i in range(args.Dz_steps):
_, Dm = sess.run([train_op_D, model.get_output(D_fetch_keys, as_dict=True)],
feed_dict={model.is_train: True, model.x_ph: x, model.z_ph: z})
for i in range(args.AE_steps):
_, AEm = sess.run([train_op_AE, model.get_output(AE_fetch_keys, as_dict=True)],
feed_dict={model.is_train: True, model.x_ph: x, model.z_ph: z})
if global_step % args.save_freq == 0:
train_helper.save(sess, global_step)
if global_step % args.log_freq == 0:
log_str = "\nEpoch {}/{}, Step {}, Dz_loss: {:.4f}, AE_loss: {:.4f}".format(
epoch, args.epochs, global_step, Dm['Dz_loss'], AEm['AE_loss']) + \
"\nrec_x: {:.4f}".format(AEm['rec_x']) + \
"\nD_loss_z0: {:.4f}, D_loss_z1_gen: {:.4f}, G_loss_z1_gen: {:.4f}".format(
Dm['D_loss_z0'], Dm['D_loss_z1_gen'], AEm['G_loss_z1_gen']) + \
"\nD_avg_prob_z0: {:.4f}, D_avg_prob_z1_gen: {:.4f}".format(
Dm['D_avg_prob_z0'], Dm['D_avg_prob_z1_gen']) + \
"\ngp0_z_coeff: {:.4f}, gp0_z: {:.4f}".format(args.gp0_z_coeff, Dm['gp0_z'])
print(log_str)
with open(train_log_file, "a") as f:
f.write(log_str)
f.write("\n")
f.close()
train_helper.add_summary(custom_tf_scalar_summary(
'AE_loss', AEm['AE_loss'], prefix='train'), global_step)
train_helper.add_summary(custom_tf_scalar_summary(
'rec_x', AEm['rec_x'], prefix='train'), global_step)
train_helper.add_summary(custom_tf_scalar_summary(
'G_loss_z1_gen', AEm['G_loss_z1_gen'], prefix='train'), global_step)
train_helper.add_summary(custom_tf_scalar_summary(
'D_loss_z0', Dm['D_loss_z0'], prefix='train'), global_step)
train_helper.add_summary(custom_tf_scalar_summary(
'D_loss_z1_gen', Dm['D_loss_z1_gen'], prefix='train'), global_step)
train_helper.add_summary(custom_tf_scalar_summary(
'D_prob_z0', Dm['D_avg_prob_z0'], prefix='train'), global_step)
train_helper.add_summary(custom_tf_scalar_summary(
'D_prob_z1_gen', Dm['D_avg_prob_z1_gen'], prefix='train'), global_step)
train_helper.add_summary(custom_tf_scalar_summary(
'gp0_z', Dm['gp0_z'], prefix='train'), global_step)
if global_step % args.viz_gen_freq == 0:
# Generate images
# ------------------------- #
z = np.random.normal(size=[64, args.z_dim])
img_file = os.path.join(img_gen_dir, 'step[%d]_gen_test.png' % global_step)
model.generate_images(img_file, sess, z, block_shape=[8, 8],
batch_size=args.batch_size,
dec_output_2_img_func=binary_float_to_uint8)
# ------------------------- #
if global_step % args.viz_rec_freq == 0:
# Reconstruct images
# ------------------------- #
x = x_train[np.random.choice(num_train, size=64, replace=False)]
img_file = os.path.join(img_rec_dir, 'step[%d]_rec_test.png' % global_step)
model.reconstruct_images(img_file, sess, x, block_shape=[8, 8],
batch_size=args.batch_size,
dec_output_2_img_func=binary_float_to_uint8)
# ------------------------- #
if global_step % args.viz_itpl_freq == 0:
# Interpolate images
# ------------------------- #
x1 = x_train[np.random.choice(num_train, size=12, replace=False)]
x2 = x_train[np.random.choice(num_train, size=12, replace=False)]
img_file = os.path.join(img_itpl_dir, 'step[%d]_itpl_test.png' % global_step)
model.interpolate_images(img_file, sess, x1, x2, num_itpl_points=12,
batch_on_row=True, batch_size=args.batch_size,
dec_output_2_img_func=binary_float_to_uint8)
# ------------------------- #
if epoch % 100 == 0:
train_helper.save_separately(sess, model_name="model_epoch{}".format(epoch),
global_step=global_step)
# Last save
train_helper.save(sess, global_step)