def __init__(self):
self.data_directory = os.path.join(FLAGS.working_directory, "MNIST")
if not os.path.exists(self.data_directory):
os.makedirs(self.data_directory)
self.save_path = FLAGS.working_directory + '/save.ckpt'
self.mnist = read_data_set("/tmp/vae/converted_java.npy")
self.input_tensor = tf.placeholder(tf.float32, [FLAGS.batch_size, 28 * 28])
with pt.defaults_scope(activation_fn=tf.nn.elu,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True):
with pt.defaults_scope(phase=pt.Phase.train):
with tf.variable_scope("model") as scope:
self.output_tensor, self.mean, self.stddev = decoder(encoder(self.input_tensor))
with pt.defaults_scope(phase=pt.Phase.test):
with tf.variable_scope("model", reuse=True) as scope:
self.sampled_tensor, _, _ = decoder()
self.vae_loss = get_vae_cost(self.mean, self.stddev)
self.rec_loss = get_reconstruction_cost(self.output_tensor, self.input_tensor)
self.loss = self.vae_loss + self.rec_loss
self.optimizer = tf.train.AdamOptimizer(FLAGS.learning_rate, epsilon=1.0)
self.train = pt.apply_optimizer(self.optimizer, losses=[self.loss])
self.init = tf.initialize_all_variables()
self.saver = tf.train.Saver()
def init_opt(self):
self.build_placeholder()
with pt.defaults_scope(phase=pt.Phase.train):
with tf.variable_scope("g_net"):
# ####get output from G network################################
c, kl_loss = self.sample_encoded_context(self.embeddings)
z = tf.random_normal([self.batch_size, cfg.Z_DIM])
self.log_vars.append(("hist_c", c))
self.log_vars.append(("hist_z", z))
fake_images = self.model.get_generator(tf.concat(1, [c, z]))
# ####get discriminator_loss and generator_loss ###################
discriminator_loss, generator_loss =\
self.compute_losses(self.images,
self.wrong_images,
fake_images,
self.embeddings)
generator_loss += kl_loss
self.log_vars.append(("g_loss_kl_loss", kl_loss))
self.log_vars.append(("g_loss", generator_loss))
self.log_vars.append(("d_loss", discriminator_loss))
# #######Total loss for build optimizers###########################
self.prepare_trainer(generator_loss, discriminator_loss)
# #######define self.g_sum, self.d_sum,....########################
self.define_summaries()
with pt.defaults_scope(phase=pt.Phase.test):
with tf.variable_scope("g_net", reuse=True):
self.sampler()
self.visualization(cfg.TRAIN.NUM_COPY)
print("success")
def init_opt(self):
self.build_placeholder()
with pt.defaults_scope(phase=pt.Phase.train):
with tf.variable_scope("g_net"):
# ####get output from G network################################
c, kl_loss = self.sample_encoded_context(self.embeddings)
z = tf.random_normal([self.batch_size, cfg.Z_DIM])
self.log_vars.append(("hist_c", c))
self.log_vars.append(("hist_z", z))
fake_images = self.model.get_generator(tf.concat(1, [c, z]))
# ####get discriminator_loss and generator_loss ###################
discriminator_loss, generator_loss =\
self.compute_losses(self.images,
self.wrong_images,
fake_images,
self.embeddings)
generator_loss += kl_loss
self.log_vars.append(("g_loss_kl_loss", kl_loss))
self.log_vars.append(("g_loss", generator_loss))
self.log_vars.append(("d_loss", discriminator_loss))
# #######Total loss for build optimizers###########################
self.prepare_trainer(generator_loss, discriminator_loss)
# #######define self.g_sum, self.d_sum,....########################
self.define_summaries()
with pt.defaults_scope(phase=pt.Phase.test):
with tf.variable_scope("g_net", reuse=True):
self.sampler()
self.visualization(cfg.TRAIN.NUM_COPY)
print("success")
def testNestedDefaultScope(self):
pretty_tensor_class._defaults['l2loss'] = 0
with prettytensor.defaults_scope(l2loss=0.001):
self.assertEqual(0.001, pretty_tensor_class._defaults['l2loss'])
with prettytensor.defaults_scope(l2loss=5):
self.assertEqual(5, pretty_tensor_class._defaults['l2loss'])
self.assertEqual(0.001, pretty_tensor_class._defaults['l2loss'])
self.assertEqual(0, pretty_tensor_class._defaults['l2loss'])
def testNestedDefaultScope(self):
pretty_tensor_class._defaults['l2loss'] = 0
with prettytensor.defaults_scope(l2loss=0.001):
self.assertEqual(0.001, pretty_tensor_class._defaults['l2loss'])
with prettytensor.defaults_scope(l2loss=5):
self.assertEqual(5, pretty_tensor_class._defaults['l2loss'])
self.assertEqual(0.001, pretty_tensor_class._defaults['l2loss'])
self.assertEqual(0, pretty_tensor_class._defaults['l2loss'])
def build_model(self):
with tf.device('/cpu:0'):
tf.reset_default_graph()
self._current_step = tf.Variable(0, trainable=False, name='global_step')
self._step = tf.assign(self._current_step, self._current_step + 1)
with pt.defaults_scope(activation_fn=self._activation.func):
with pt.defaults_scope(phase=pt.Phase.train):
with tf.variable_scope(self.encoder_scope):
self._build_encoder()
with tf.variable_scope(self.decoder_scope):
self._build_decoder()
def build_model(self):
tf.reset_default_graph()
self._batch_shape = inp.get_batch_shape(FLAGS.batch_size, FLAGS.input_path)
self._current_step = tf.Variable(0, trainable=False, name='global_step')
self._step = tf.assign(self._current_step, self._current_step + 1)
with pt.defaults_scope(activation_fn=self._activation.func):
with pt.defaults_scope(phase=pt.Phase.train):
with tf.variable_scope(self.encoder_scope):
self._build_encoder()
with tf.variable_scope(self.decoder_scope):
self._build_decoder()
def init_opt(self):
self.build_placeholder()
with tf.variable_scope("g_net"):
with pt.defaults_scope(phase=pt.Phase.train):
# ####get output from G network################################
# c, kl_loss = self.sample_encoded_context(self.conditions)
#c_text = self.model.generate_text_condition(self.embeddings)
#c, c_vector = self.model.generate_condition(self.conditions)
c_text = self.embeddings
c_mask = self.conditions
z = tf.random_normal([self.batch_size, cfg.Z_DIM])
self.log_vars.append(("hist_c", c_text))
self.log_vars.append(("hist_z", z))
#G_input = tf.concat(1, [c, c_text])
#G_input = tf.concat(1, [G_input, z])
# print('#######################')
# print('c_text, c_mask shape is:', c_text, c_mask)
# print('#########################')
G_input = self.model.generate_condition(
tf.concat(1, [c_text, z]), c_mask)
# update by zhaoyang
self.debug_g_input = G_input
###################
fake_images = self.model.get_generator(G_input)
# update by kristy
self.debug_fake_images = fake_images
# ####get discriminator_loss and generator_loss ###################
discriminator_loss, generator_loss =\
self.compute_losses(self.images,
self.wrong_images,
fake_images,
self.embeddings,
self.conditions)
#generator_loss += kl_loss
#self.log_vars.append(("g_loss_kl_loss", kl_loss))
self.log_vars.append(("g_loss", generator_loss))
self.log_vars.append(("d_loss", discriminator_loss))
# #######Total loss for build optimizers###########################
self.prepare_trainer(generator_loss, discriminator_loss)
# #######define self.g_sum, self.d_sum,....########################
self.define_summaries()
with pt.defaults_scope(phase=pt.Phase.test):
#with tf.variable_scope("g_net", reuse=True):
self.sampler()
self.visualization(cfg.TRAIN.NUM_COPY)
print("success")
def init_opt(self):
self.build_placeholder()
with pt.defaults_scope(phase=pt.Phase.train):
# ####get output from G network####################################
with tf.variable_scope("g_net"):
c, kl_loss = self.sample_encoded_context(self.embeddings)
z = tf.random_normal([self.batch_size, cfg.Z_DIM])
self.log_vars.append(("hist_c", c))
self.log_vars.append(("hist_z", z))
fake_images = self.model.get_generator(
tf.concat(axis=1, values=[c, z]))
# ####get discriminator_loss and generator_loss ###################
discriminator_loss, generator_loss =\
self.compute_losses(self.images,
self.wrong_images,
fake_images,
self.embeddings,
self.style_indices, #but we don't need to use style indices for discriminator loss
flag='lr')
generator_loss += kl_loss
self.log_vars.append(("g_loss_kl_loss", kl_loss))
self.log_vars.append(("g_loss", generator_loss))
self.log_vars.append(("d_loss", discriminator_loss))
# #### For hr_g and hr_d #########################################
with tf.variable_scope("hr_g_net"):
hr_c, hr_kl_loss = self.sample_encoded_context(self.embeddings)
self.log_vars.append(("hist_hr_c", hr_c))
hr_fake_images = self.model.hr_get_generator(fake_images, hr_c)
# get losses
hr_discriminator_loss, hr_generator_loss =\
self.compute_losses(self.hr_images,
self.hr_wrong_images,
hr_fake_images,
self.embeddings,
self.style_indices,
flag='hr')
hr_generator_loss += hr_kl_loss
self.log_vars.append(("hr_g_loss", hr_generator_loss))
self.log_vars.append(("hr_d_loss", hr_discriminator_loss))
# #######define self.g_sum, self.d_sum,....########################
self.prepare_trainer(discriminator_loss, generator_loss,
hr_discriminator_loss, hr_generator_loss)
self.define_summaries()
with pt.defaults_scope(phase=pt.Phase.test):
self.sampler()
self.visualization(cfg.TRAIN.NUM_COPY)
print("success")
def build_model(self):
tf.reset_default_graph()
self._batch_shape = inp.get_batch_shape(FLAGS.batch_size,
FLAGS.input_path)
self._current_step = tf.Variable(0,
trainable=False,
name='global_step')
self._step = tf.assign(self._current_step, self._current_step + 1)
with pt.defaults_scope(activation_fn=self._activation.func):
with pt.defaults_scope(phase=pt.Phase.train):
with tf.variable_scope(self.encoder_scope):
self._build_encoder()
with tf.variable_scope(self.decoder_scope):
self._build_decoder()
def calc_pc():
'''Calculate the prior probabilities of each dimension based on counts in a binary dataset
data: N x M matrix of 1, -1
returns pc: M x 1 vector of p(c=1)
'''
data_directory = os.path.join(FLAGS.working_directory, "celebA")
private_tensor = tf.placeholder(tf.float32, [FLAGS.batch_size, FLAGS.private_size])
attrs = np.loadtxt(FLAGS.working_directory + FLAGS.attrs_directory + 'list_attr_celeba.txt', skiprows=2, usecols=range(1,FLAGS.output_size + FLAGS.private_size+1))
def get_feed(batch_no, test_phase):
#xs = dvib.read_imgs(batch_no, test_phase)
ys = dvib.read_attrs(attrs, batch_no, test_phase)
#xs = xs/PX_MAX
#ys = ys * PX_MAX / 2
return {private_tensor: ys[:, FLAGS.output_size:]}
with pt.defaults_scope(activation_fn=tf.nn.relu,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True):
with pt.defaults_scope(phase=pt.Phase.train):
with tf.variable_scope("prior") as scope:
# private data is in {-1, 1}
p_c = tf.reduce_mean((private_tensor+1.)/2., axis=0)
#pdb.set_trace()
init = tf.global_variables_initializer()
# Config session for memory
config = tf.ConfigProto()
#config.gpu_options.allow_growth = True
#config.gpu_options.per_process_gpu_memory_fraction = 0.8
config.log_device_placement=False
sess = tf.Session()
sess.run(init)
# calculating prior p_c
widgets = ["Calculating priors |", Percentage(), Bar(), ETA()]
pbar = ProgressBar(maxval = FLAGS.updates_per_epoch, widgets=widgets)
pbar.start()
p_cv = 0
for i in range(FLAGS.updates_per_epoch):
pbar.update(i)
feeds = get_feed(i, False)
p_cv += sess.run(p_c, feeds)
p_cv /= FLAGS.updates_per_epoch
print("prior p_c")
print(p_cv)
sess.close()
return p_cv
def inference_io(self, reuse):
with tf.variable_scope(self.name, reuse=reuse), pt.defaults_scope(
summary_collections=['INFERENCE_SUMMARIES']):
inf_input = tf.placeholder(tf.int32, [])
inf_logits = self.create(
pt.wrap(inf_input).reshape([1, 1]), pt.Phase.infer)
return inf_input, inf_logits
def create(self, input_placeholder, phase):
"""Creates a 2 layer LSTM model with dropout.
Args:
input_placeholder: placeholder of timesteps x sequences
phase: Phase controls whether or not dropout is active. In
training mode we want to perform dropout, but in test we
want to disable it.
Returns: The logits layer.
"""
timesteps = input_placeholder.get_shape()[1].value
text_in = integerize.reshape_cleavable(input_placeholder)
with pt.defaults_scope(activation_fn=tf.nn.relu, l2loss=0.00001):
# The embedding lookup must be placed on a cpu.
with tf.device('/cpu:0'):
embedded = text_in.embedding_lookup(integerize.CHARS,
[self.embedding])
# Because the sequence LSTM expects each timestep to be its
# own Tensor, we need to cleave the sequence. Below we can
# build a stacked 2 layer LSTM by just chaining them together.
# You can stack as many layers as you want.
lstm = embedded.cleave_sequence(timesteps)
assert len(self.lstms)
for lstm_size in self.lstms:
lstm = lstm.sequence_lstm(lstm_size)
# The classifier is much more efficient if it runs across the entire
# dataset at once, so we want to squash (i.e. uncleave).
# Note: if phase is test, dropout is a noop.
return (lstm.squash_sequence().dropout(
keep_prob=0.8, phase=phase).fully_connected(integerize.CHARS,
activation_fn=None))
def network():
dim_0, dim_1, dim_2 = grid_size
gt = tf.placeholder(tf.float32, [dim_0, dim_1])
conflict_grids = tf.placeholder(tf.float32, [num_timesteps, dim_0, dim_1, dim_2])
mask = tf.placeholder(tf.float32, [dim_0, dim_1])
#poverty_grid = tf.placeholder(tf.float32, [1, dim_0, dim_1])
assert(num_timesteps > 1)
with tf.variable_scope("model") as scope:
with pt.defaults_scope(activation_fn=tf.nn.relu,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True):
enc_conflicts = network_conflict(conflict_grids)
rnn_output = network_rnn(enc_conflicts)
rnn_output = tf.reshape(rnn_output, [1, 64])
'''
with tf.variable_scope("model") as scope:
with pt.defaults_scope(activation_fn=tf.nn.relu,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True):
enc_poverty = network_poverty(poverty_grid)
feats = tf.concat(0, [mean_conflict, enc_poverty])
'''
feats = rnn_output
pred = fc_layers(feats, dim_0)
return conflict_grids, pred, gt, mask
def build_model(sess, image_shape, embedding_dim, batch_size):
model = CondALI(image_shape=image_shape)
embeddings = tf.placeholder(tf.float32, [batch_size, embedding_dim],
name='conditional_embeddings')
images = tf.placeholder(tf.float32, [batch_size] + image_shape,
name='real_images')
bottlenecks = prepare_bottlenecks(images)
with tf.variable_scope("e_net"):
#Add Cond_AUG to fake latents
fake_latents = model.get_encoder(bottlenecks)
with pt.defaults_scope(phase=pt.Phase.test):
with tf.variable_scope("g_net"):
latents = sample_conditionned_latent_variable(
embeddings, batch_size, model)
fake_latents = sample_conditionned_latent_variable(
fake_latents, batch_size, model)
fake_images = model.get_generator(latents)
fake_images_2 = model.get_generator(fake_latents)
ckt_path = cfg.TEST.PRETRAINED_MODEL
if ckt_path.find('.ckpt') != -1:
print("Reading model parameters from %s" % ckt_path)
saver = tf.train.Saver(tf.global_variables())
saver.restore(sess, ckt_path)
else:
print("Input a valid model path.")
return embeddings, fake_images, fake_images_2
def network():
dim_0, dim_1, dim_2 = grid_size
gt = tf.placeholder(tf.float32, [dim_0, dim_1])
conflict_grids = tf.placeholder(tf.float32, [num_timesteps, dim_0, dim_1, dim_2])
mask = tf.placeholder(tf.float32, [dim_0, dim_1])
#poverty_grid = tf.placeholder(tf.float32, [1, dim_0, dim_1])
assert(num_timesteps > 1)
with tf.variable_scope("model") as scope:
with pt.defaults_scope(activation_fn=tf.nn.relu,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True):
enc_conflicts = network_conflict(conflict_grids)
mean_conflict = tf.reduce_mean(enc_conflicts, 0)
mean_conflict = tf.reshape(mean_conflict, [1, 128])
'''
with tf.variable_scope("model") as scope:
with pt.defaults_scope(activation_fn=tf.nn.relu,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True):
enc_poverty = network_poverty(poverty_grid)
feats = tf.concat(0, [mean_conflict, enc_poverty])
'''
feats = mean_conflict
pred = fc_layers(feats, dim_0)
return conflict_grids, pred, gt, mask
def multilayer_fully_connected(images, labels):
images = pt.wrap(images)
with pt.defaults_scope(activation_fn=tf.nn.relu, l2loss=0.00001):
return (images
.fully_connected(100)
.fully_connected(100)
.softmax_classifier(10, labels))
def _make_encoder_template(self):
defaults_scope = {
'phase': pt.UnboundVariable('phase', default=pt.Phase.train),
'scale_after_normalization': True,
}
with pt.defaults_scope(**defaults_scope):
with tf.variable_scope("encoder"):
if self.network_type=="fully-connected":
z_dim = self.latent_dist.dist_flat_dim
self.encoder_template = (pt.template("x_in").
custom_fully_connected(1000).
batch_normalize().
apply(tf.nn.elu).
custom_fully_connected(1000).
batch_normalize().
apply(tf.nn.elu).
custom_fully_connected(z_dim))
elif self.network_type=="convolutional":
z_dim = self.latent_dist.dist_flat_dim
self.encoder_template = (pt.template("x_in").
reshape([-1] + list(self.image_shape)).
custom_conv2d(64, k_h=4, k_w=4).
apply(tf.nn.elu).
custom_conv2d(128, k_h=4, k_w=4).
batch_normalize().
apply(tf.nn.elu).
custom_fully_connected(1024).
batch_normalize().
apply(tf.nn.elu).
custom_fully_connected(z_dim))
def _make_decoder_template(self):
defaults_scope = {
'phase': pt.UnboundVariable('phase', default=pt.Phase.train),
'scale_after_normalization': True,
}
image_size = self.image_shape[0]
with pt.defaults_scope(**defaults_scope):
with tf.variable_scope("decoder"):
if self.network_type=="fully-connected":
self.decoder_template = (pt.template("z_in").
custom_fully_connected(1000).
apply(tf.nn.relu).
custom_fully_connected(1000).
batch_normalize().
apply(tf.nn.relu).
custom_fully_connected(self.image_dim))
elif self.network_type=="convolutional":
self.decoder_template = \
(pt.template("z_in").
custom_fully_connected(1024).
batch_normalize().
apply(tf.nn.relu).
custom_fully_connected(image_size/4 * image_size/4 * 128).
batch_normalize().
apply(tf.nn.relu).
reshape([-1, image_size/4, image_size/4, 128]).
custom_deconv2d([0, image_size/2, image_size/2, 64],
k_h=4, k_w=4).
batch_normalize().
apply(tf.nn.relu).
custom_deconv2d([0] + list(self.image_shape),
k_h=4, k_w=4).
flatten())
def image2feature(self, image_tensor):
if self.patch_feature_dim == 0:
return None
mid_tensor = (
pt.wrap(image_tensor).
conv2d(3, 32).
max_pool(2, 2)
).tensor # 64x64
hgd = [
{"type": "conv2d", "depth": 64},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 32 x 32
{"type": "conv2d", "depth": 128},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 16 x 16
{"type": "conv2d", "depth": 256},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 8 x 8
{"type": "conv2d", "depth": 512},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 4 x 4
{"type": "conv2d", "depth": 512},
]
with pt.defaults_scope(**self.pt_defaults_scope_value()):
feature_map = hourglass(
mid_tensor, hgd,
net_type=self.options["hourglass_type"] if "hourglass_type" in self.options else None
)
return feature_map
def build_model(sess, embedding_dim, batch_size):
model = CondGAN(
lr_imsize=cfg.TEST.LR_IMSIZE,
hr_lr_ratio=int(cfg.TEST.HR_IMSIZE/cfg.TEST.LR_IMSIZE))
embeddings = tf.placeholder(
tf.float32, [batch_size, embedding_dim],
name='conditional_embeddings')
with pt.defaults_scope(phase=pt.Phase.test):
with tf.variable_scope("g_net"):
c = sample_encoded_context(embeddings, model)
z = tf.random_normal([batch_size, cfg.Z_DIM])
fake_images = model.get_generator(tf.concat(1, [c, z]))
with tf.variable_scope("hr_g_net"):
hr_c = sample_encoded_context(embeddings, model)
hr_fake_images = model.hr_get_generator(fake_images, hr_c)
ckt_path = cfg.TEST.PRETRAINED_MODEL
if ckt_path.find('.ckpt') != -1:
print("Reading model parameters from %s" % ckt_path)
saver = tf.train.Saver(tf.all_variables())
saver.restore(sess, ckt_path)
else:
print("Input a valid model path.")
return embeddings, fake_images, hr_fake_images
def fc():
with tf.variable_scope('fc'):
with pt.defaults_scope(activation_fn=tf.nn.relu):
fc_seq = pt.wrap(x).sequential()
fc_seq.fully_connected(10, activation_fn=None)
fc_seq.softmax()
return tf.nn.softmax(fc_seq)
def main_network(images, training):
# Wrap the input images as a Pretty Tensor object.
x_pretty = pt.wrap(images)
# Pretty Tensor uses special numbers to distinguish between
# the training and testing phases.
if training:
phase = pt.Phase.train
else:
phase = pt.Phase.infer
# Create the convolutional neural network using Pretty Tensor.
# It is very similar to the previous tutorials, except
# the use of so-called batch-normalization in the first layer.
with pt.defaults_scope(activation_fn=tf.nn.relu, phase=phase):
y_pred, loss = x_pretty.\
conv2d(kernel=5, depth=64, name='layer_conv1', batch_normalize=True).\
max_pool(kernel=2, stride=2).\
conv2d(kernel=5, depth=64, name='layer_conv2').\
max_pool(kernel=2, stride=2).\
flatten().\
fully_connected(size=256, name='layer_fc1').\
fully_connected(size=128, name='layer_fc2').\
softmax_classifier(num_classes=num_classes, labels=y_true)
return y_pred, loss
def feature2image(self, feature_tensor):
output_channels = 3*self.recon_dist_param_num
hgd = [
{"type": "conv2d", "depth": 64, "decoder_depth": output_channels, "decoder_activation_fn": None},
{"type": "conv2d", "depth": 64, "decoder_depth": 32},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 40 x 40
{"type": "conv2d", "depth": 128, "decoder_depth": 64},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 20x20
{"type": "conv2d", "depth": 256},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 10x10
{"type": "conv2d", "depth": 512},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 5x5
{"type": "conv2d", "depth": 512},
]
with pt.defaults_scope(**self.pt_defaults_scope_value()):
output_tensor = hourglass(
feature_tensor, hgd,
net_type=self.options["hourglass_type"] if "hourglass_type" in self.options else None,
extra_highlevel_feature=None
)
return output_tensor
def posterior_net(self, data_tensor, cond_info_dict):
with pt.defaults_scope(phase=pt.Phase.test):
with tf.variable_scope(self._name, reuse=True) as scope:
condition_tensor = self.condition_subnet(cond_info_dict)
enc_outputs, enc_extra_outputs = self.encoding_subnet(
data_tensor, condition_tensor=condition_tensor)
reconstructed, dec_extra_outputs = self.decoding_subnet(
enc_outputs,
condition_tensor=condition_tensor,
extra_inputs=enc_extra_outputs['for_decoder'])
decoded_vis, decoded_param_tensor = self.decoded_vis_subnet(
reconstructed)
decoded_out = dict()
decoded_out["vis"] = decoded_vis
decoded_out["param"] = decoded_param_tensor
aux_out = dict()
aux_out[
"decoded"] = decoded_out # extracts "save" field in self.reconstructed_base_aux_out
aux_out["encoded"] = enc_extra_outputs["save"]
aux_out["data"] = data_tensor
latent_param_dict = dict(value=enc_outputs)
return latent_param_dict, aux_out
def mapping(self, x):
"""
Inference network to parameterize variational family. It takes
data x as input and outputs the variational parameters lambda.
lambda = phi(x)
"""
with pt.defaults_scope(activation_fn=tf.nn.elu,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True):
params = (pt.wrap(x).
reshape([FLAGS.n_data, 28, 28, 1]).
conv2d(5, 32, stride=2).
conv2d(5, 64, stride=2).
conv2d(5, 128, edges='VALID').
dropout(0.9).
flatten().
fully_connected(self.num_local_vars * 2, activation_fn=None)).tensor
# Return list of vectors where mean[i], stddev[i] are the
# parameters of the local variational factor for data point i.
mean = tf.reshape(params[:, :self.num_local_vars], [-1])
stddev = tf.reshape(tf.sqrt(tf.exp(params[:, self.num_local_vars:])), [-1])
return [mean, stddev]
def neural_network(x):
"""
Inference network to parameterize variational family. It takes
data as input and outputs the variational parameters.
loc, scale = neural_network(x)
"""
num_vars = 10
with pt.defaults_scope(activation_fn=tf.nn.elu,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True):
params = (pt.wrap(x).
reshape([N_DATA, 28, 28, 1]).
conv2d(5, 32, stride=2).
conv2d(5, 64, stride=2).
conv2d(5, 128, edges='VALID').
dropout(0.9).
flatten().
fully_connected(num_vars * 2, activation_fn=None)).tensor
# Return list of vectors where mean[i], stddev[i] are the
# parameters of the local variational factor for data point i.
loc = tf.reshape(params[:, :num_vars], [-1])
scale = tf.reshape(tf.sqrt(tf.exp(params[:, num_vars:])), [-1])
return [loc, scale]
def build_model(sess, embedding_dim, batch_size):
model = CondGAN(
lr_imsize=cfg.TEST.LR_IMSIZE,
hr_lr_ratio=int(cfg.TEST.HR_IMSIZE / cfg.TEST.LR_IMSIZE))
embeddings = tf.placeholder(
tf.float32, [batch_size, embedding_dim],
name='conditional_embeddings')
with pt.defaults_scope(phase=pt.Phase.test):
with tf.variable_scope("g_net"):
c = sample_encoded_context(embeddings, model)
z = tf.random_normal([batch_size, cfg.Z_DIM])
fake_images = model.get_generator(tf.concat(1, [c, z]))
with tf.variable_scope("hr_g_net"):
hr_c = sample_encoded_context(embeddings, model)
hr_fake_images = model.hr_get_generator(fake_images, hr_c)
ckt_path = cfg.TEST.PRETRAINED_MODEL
if ckt_path.find('.ckpt') != -1:
print("Reading model parameters from %s" % ckt_path)
saver = tf.train.Saver(tf.all_variables())
saver.restore(sess, ckt_path)
else:
print("Input a valid model path.")
return embeddings, fake_images, hr_fake_images
def inference(x):
"""
Run the models. Called inference because it does the same thing as tensorflow's cifar tutorial
"""
z_p = tf.random_normal((batch_size, hidden_size), 0,
1) # normal dist for GAN
eps = tf.random_normal((batch_size, hidden_size), 0,
1) # normal dist for VAE
with pt.defaults_scope(activation_fn=tf.nn.elu,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True):
with tf.variable_scope("enc"):
z_x_mean, z_x_log_sigma_sq = encoder(x) # get z from the input
with tf.variable_scope("gen"):
z_x = tf.add(z_x_mean,
tf.mul(tf.sqrt(tf.exp(z_x_log_sigma_sq)),
eps)) # grab our actual z
x_tilde = generator(z_x)
with tf.variable_scope("dis"):
_, l_x_tilde = discriminator(x_tilde)
with tf.variable_scope("gen", reuse=True):
x_p = generator(z_p)
with tf.variable_scope("dis", reuse=True):
d_x, l_x = discriminator(x) # positive examples
with tf.variable_scope("dis", reuse=True):
d_x_p, _ = discriminator(x_p)
return z_x_mean, z_x_log_sigma_sq, z_x, x_tilde, l_x_tilde, x_p, d_x, l_x, d_x_p, z_p
def mapping(self, x):
"""
lambda = phi(x)
"""
with pt.defaults_scope(
activation_fn=tf.nn.elu,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True,
):
params = (
pt.wrap(x)
.reshape([FLAGS.n_data, 28, 28, 1])
.conv2d(5, 32, stride=2)
.conv2d(5, 64, stride=2)
.conv2d(5, 128, edges="VALID")
.dropout(0.9)
.flatten()
.fully_connected(self.num_vars * 2, activation_fn=None)
).tensor
mean = params[:, : self.num_vars]
stddev = tf.sqrt(tf.exp(params[:, self.num_vars :]))
return [mean, stddev]
def testVariableCollections(self):
with prettytensor.defaults_scope(variable_collections=['a']):
self.MultiLayer()
self.assertTrue(tf.get_collection('a'))
self.assertEqual(tf.get_collection('a'),
tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES))
self.assertTrue(tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES))
def build_model(image_size, num_channels, num_classes):
x = tf.placeholder(tf.float32,
shape=[None, image_size * image_size],
name="x")
x_image = tf.reshape(x, [-1, image_size, image_size, num_channels])
y_true = tf.placeholder(tf.float32, shape=[None, 6], name="y_true")
y_true_cls = tf.argmax(y_true, axis=1)
# create wrapper tensor
x_pretty = pt.wrap(x_image)
with pt.defaults_scope(activation_fn=tf.nn.elu):
y_pred, loss = x_pretty. \
conv2d(5, 16, name='layer_conv1'). \
max_pool(2, 2). \
conv2d(3, 32, name='layer_conv2'). \
max_pool(2, 2). \
conv2d(3, 64, name= 'layer_conv3'). \
max_pool(2, 2).\
flatten(). \
fully_connected(128, name='layer_fc1'). \
fully_connected(32, name= 'layer_fc2'). \
softmax_classifier(num_classes=num_classes, labels=y_true)
optimizer = tf.train.AdamOptimizer(1e-4).minimize(loss)
y_pred_cls = tf.argmax(y_pred, axis=1)
prediction_accuracy = tf.reduce_mean(
tf.cast(tf.equal(y_true_cls, y_pred_cls), tf.float32))
return optimizer, x, y_true, prediction_accuracy
def main(argv=None):
input.init_dataset_constants()
num_images = GRID[0] * GRID[1]
FLAGS.batch_size = num_images
with tf.Graph().as_default():
g_template = model.generator_template()
z = tf.placeholder(tf.float32, shape=[FLAGS.batch_size, FLAGS.z_size])
#np.random.seed(1337) # generate same random numbers each time
noise = np.random.normal(size=(FLAGS.batch_size, FLAGS.z_size))
with pt.defaults_scope(phase=pt.Phase.test):
gen_images_op, _ = pt.construct_all(g_template, input=z)
sess = tf.Session()
init_variables(sess)
gen_images, = sess.run([gen_images_op], feed_dict={z: noise})
gen_images = (gen_images + 1) / 2
sess.close()
fig = plt.figure(1)
grid = ImageGrid(fig, 111, nrows_ncols=GRID, axes_pad=0.1)
for i in xrange(num_images):
im = gen_images[i]
axis = grid[i]
axis.axis('off')
axis.imshow(im)
plt.show()
fig.savefig('montage.png', dpi=100, bbox_inches='tight')
def create_model(text_in, timesteps, phase):
"""Creates a 2 layer LSTM model with dropout.
Args:
text_in: The input text as ASCII ordinals in a Tensor.
timesteps: The number of timesteps in the sequence.
phase: Phase controls whether or not dropout is active. In training mode
we want to perform dropout, but in test we want to disable it.
Returns:
The logits.
"""
with pt.defaults_scope(activation_fn=tf.nn.relu, l2loss=0.00001):
# The embedding lookup must be placed on a cpu.
with tf.device('/cpu:0'):
embedded = text_in.embedding_lookup(CHARS, [EMBEDDING_SIZE])
# Because the sequence LSTM expects each timestep to be its own Tensor,
# we need to cleave the sequence.
# Below we can build a stacked 2 layer LSTM by just chaining them together.
# You can stack as many layers as you want.
lstm = (embedded
.cleave_sequence(timesteps)
.sequence_lstm(LOWER)
.sequence_lstm(UPPER))
# The classifier is much more efficient if it runs across the entire
# dataset at once, so we want to squash (i.e. uncleave).
# Note: if phase is test, dropout is a noop.
return (lstm.squash_sequence()
.dropout(keep_prob=0.8, phase=phase)
.fully_connected(CHARS, activation_fn=None))
def multilayer_fully_connected(images, labels):
images = pt.wrap(images)
with pt.defaults_scope(activation_fn=tf.nn.relu, l2loss=0.00001):
return (images.flatten().\
fully_connected(100).\
fully_connected(100).\
softmax_classifier(10, labels))
def init_op(self):
self.build_placeholder()
with pt.defaults_scope(phase=pt.Phase.train):
with tf.variable_scope("vae_mnist_model"):
vae_loss = self.compute_losses(self.input_images)
print("VAE losses computed")
self.prepare_trainer(loss=vae_loss)
def fc():
with tf.variable_scope('fc'):
with pt.defaults_scope(activation_fn=tf.nn.relu):
fc_seq = pt.wrap(x).sequential()
fc_seq.fully_connected(10, activation_fn=None)
fc_seq.softmax()
return tf.nn.softmax(fc_seq)
def inference(x224,x64):
z_p = tf.random_normal((batch_size, hidden_size), 0, 1)
eps = tf.random_normal((batch_size, hidden_size), 0, 1) # normal dist for VAE
with pt.defaults_scope(activation_fn=tf.nn.elu,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True):
with tf.variable_scope("enc"):
vgg_net = Vgg19('./vgg19.npy', codelen=hidden_size)
vgg_net.build(x224, beta_nima, train_model)
z_x_mean = vgg_net.fc9
z_x_log_sigma_sq = vgg_net.fc10
with tf.variable_scope("gen"):
z_x = tf.add(z_x_mean,
tf.multiply(tf.sqrt(tf.exp(z_x_log_sigma_sq)), eps)) # grab our actual z
x_tilde = generator(z_x)
# x_tilde = generator(z_x_mean)
with tf.variable_scope("dis"):
_, l_x_tilde = discriminator(x_tilde)
with tf.variable_scope("gen", reuse=True):
x_p = generator(z_p)
with tf.variable_scope("dis", reuse=True):
d_x, l_x = discriminator(x64)
with tf.variable_scope("dis", reuse=True):
d_x_p, _ = discriminator(x_p)
return z_x_mean,z_x_log_sigma_sq,x_tilde, l_x_tilde, z_x,x_p, d_x, l_x, d_x_p, z_p
def main_network(images, training):
# Wrap the input images as a Pretty Tensor object.
x_pretty = pt.wrap(images)
# Pretty Tensor uses special numbers to distinguish between
# the training and testing phases.
if training:
phase = pt.Phase.train
else:
phase = pt.Phase.infer
# CNN using Pretty Tensor.
#we can now quickly chain any number of layers to define neural networks
with pt.defaults_scope(activation_fn=tf.nn.relu, phase=phase):
y_pred, loss = x_pretty.\
conv2d(kernel=5, depth=64, name='layer_conv1', batch_normalize=True).\
max_pool(kernel=2, stride=2).\
conv2d(kernel=5, depth=64, name='layer_conv2').\
max_pool(kernel=2, stride=2).\
flatten().\
fully_connected(size=256, name='layer_fc1').\
fully_connected(size=128, name='layer_fc2').\
softmax_classifier(num_classes=num_classes, labels=y_true)
return y_pred, loss
def neural_network(x):
"""
Inference network to parameterize variational family. It takes
data as input and outputs the variational parameters.
loc, scale = neural_network(x)
"""
n_vars = 10
with pt.defaults_scope(activation_fn=tf.nn.elu,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True):
params = (pt.wrap(x).
reshape([N_MINIBATCH, 28, 28, 1]).
conv2d(5, 32, stride=2).
conv2d(5, 64, stride=2).
conv2d(5, 128, edges='VALID').
dropout(0.9).
flatten().
fully_connected(n_vars * 2, activation_fn=None)).tensor
# Return list of vectors where mean[i], stddev[i] are the
# parameters of the local variational factor for data point i.
loc = tf.reshape(params[:, :n_vars], [-1])
scale = tf.reshape(tf.sqrt(tf.exp(params[:, n_vars:])), [-1])
return [loc, scale]
def build_alexnet(ims, tr):
x_pretty = pt.wrap(ims)
if tr:
state = pt.Phase.train
else:
state = pt.Phase.infer
with pt.defaults_scope(activation_fn=tf.nn.relu, phase=state):
prediction, cost = x_pretty.\
conv2d(kernel=5, depth=64, name='conv1', batch_normalize=True).\
max_pool(kernel=2, stride=2).\
conv2d(kernel=5, depth=64, name='conv2', batch_normalize=True).\
max_pool(kernel=2, stride=2).\
conv2d(kernel=5, depth=64, name='conv3').\
conv2d(kernel=5, depth=64, name='conv4').\
conv2d(kernel=5, depth=64, name='conv5').\
flatten().\
fully_connected(size=256, name='fc1').\
fully_connected(size=128, name='fc2').\
fully_connected(size=64, name='fc3').\
softmax_classifier(num_classes=classes_of_image, labels=im_true_lb)
return prediction, cost
def create_model(text_in, timesteps, phase):
"""Creates a 2 layer LSTM model with dropout.
Args:
text_in: The input text as ASCII ordinals in a Tensor.
timesteps: The number of timesteps in the sequence.
phase: Phase controls whether or not dropout is active. In training mode
we want to perform dropout, but in test we want to disable it.
Returns:
The logits.
"""
with pt.defaults_scope(activation_fn=tf.nn.relu, l2loss=0.00001):
# The embedding lookup must be placed on a cpu.
with tf.device('/cpu:0'):
embedded = text_in.embedding_lookup(CHARS, [EMBEDDING_SIZE])
# Because the sequence LSTM expects each timestep to be its own Tensor,
# we need to cleave the sequence.
# Below we can build a stacked 2 layer LSTM by just chaining them together.
# You can stack as many layers as you want.
lstm = (embedded
.cleave_sequence(timesteps)
.sequence_lstm(LOWER)
.sequence_lstm(UPPER))
# The classifier is much more efficient if it runs across the entire
# dataset at once, so we want to squash (i.e. uncleave).
# Note: if phase is test, dropout is a noop.
return (lstm.squash_sequence()
.dropout(keep_prob=0.8, phase=phase)
.fully_connected(CHARS, activation_fn=None))
def getConv_features(images, training):
# Wrap the input images as a Pretty Tensor object.
x_pretty = pt.wrap(images)
# Pretty Tensor uses special numbers to distinguish between
# the training and testing phases.
if training:
phase = pt.Phase.train
else:
phase = pt.Phase.infer
# Create the convolutional neural network using Pretty Tensor.
# It is very similar to the previous tutorials, except
# the use of so-called batch-normalization in the first layer.
with pt.defaults_scope(activation_fn=tf.nn.relu, phase=phase):
p_input_flatten = x_pretty. \
conv2d(kernel=5, depth=64, name='layer_conv1_feature_extraction', batch_normalize=True). \
max_pool(kernel=2, stride=2). \
conv2d(kernel=5, depth=64, name='layer_conv2_feature_extraction'). \
max_pool(kernel=2, stride=2). \
flatten(). \
fully_connected(size=256, name='layer_fc1_feature_extraction')
return p_input_flatten
def testVariableCollections(self):
with prettytensor.defaults_scope(variable_collections=['a']):
self.MultiLayer()
self.assertTrue(tf.get_collection('a'))
self.assertEqual(
tf.get_collection('a'),
tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES))
self.assertTrue(tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES))
def output( self, inputs, phase = pt.Phase.train ): inputs = pt.wrap( inputs ) with pt.defaults_scope( phase = phase, activation_fn = self.nonlinearity, l2loss = self.l2loss ): for layer in self.hidden_layers: inputs = inputs.fully_connected( layer ) return inputs.fully_connected( self.dim_output, activation_fn = None )
def testUnboundVariableAsDefault(self):
"""The same unbound_var can be used multiple times in a graph."""
input_pt = self.Wrap(self.input)
with prettytensor.defaults_scope(
value=prettytensor.UnboundVariable('key')):
x = input_pt.ValidateMethod(self)
self.assertTrue(isinstance(x, pretty_tensor_class._DeferredLayer))
x.construct(key=KEY)
def testConvBatchNorm(self):
st = self.input_layer.sequential()
st.reshape([DIM_SAME, DIM_SAME, DIM_SAME, 1])
with prettytensor.defaults_scope(batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=False):
st.conv2d(3, 2)
self.assertEqual(
2, len(tf.get_collection(prettytensor.GraphKeys.UPDATE_OPS)))
def test_default_parameter_modifier(self):
called = set()
def parameter_modifier(var_name, variable, unused_phase):
called.add(var_name)
return variable
with prettytensor.defaults_scope(parameter_modifier=parameter_modifier):
st = self.input_layer.sequential()
st.flatten()
st.fully_connected(5)
self.assertEqual({'weights', 'bias'}, called)
def network():
gt = tf.placeholder(tf.float32, [conflict_grid_size[0], conflict_grid_size[1]])
conflict_grids = tf.placeholder(tf.float32, [num_timesteps,
conflict_grid_size[0],
conflict_grid_size[1],
conflict_grid_size[2]])
poverty_grid = tf.placeholder(tf.float32, [poverty_grid_size[0],
poverty_grid_size[1],
poverty_grid_size[2],
poverty_grid_size[3]])
climate_grids = tf.placeholder(tf.float32, [num_timesteps,
climate_grid_size[0],
climate_grid_size[1],
climate_grid_size[2]])
assert(num_timesteps > 1)
with tf.variable_scope("model") as scope:
with pt.defaults_scope(activation_fn=tf.nn.relu,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True):
enc_conflicts = network_conflict(conflict_grids)
enc_climate = network_climate(climate_grids)
enc_conflict_climate = tf.concat(1, [enc_conflicts, enc_climate])
rnn_output = network_rnn(enc_conflict_climate)
rnn_output = tf.reshape(rnn_output, [1, 128])
with tf.variable_scope("model") as scope:
with pt.defaults_scope(activation_fn=tf.nn.relu,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True):
enc_poverty = network_poverty(poverty_grid)
feats = tf.concat(1, [rnn_output, enc_poverty])
pred = fc_layers(feats, conflict_grid_size[0])
return conflict_grids, climate_grids, poverty_grid, pred, gt
def lenet5(images, labels):
images = pt.wrap(images)
with pt.defaults_scope(activation_fn=tf.nn.relu, l2loss=0.00001):
return (images
.reshape([-1, 28, 28, 1])
.conv2d(5, 20)
.max_pool(2, 2)
.conv2d(5, 50)
.max_pool(2, 2)
.flatten()
.fully_connected(500)
.softmax_classifier(10, labels))
def create_model(text_in, labels, timesteps, per_example_weights, phase=pt.Phase.train):
with pt.defaults_scope(phase=phase, l2loss=0.00001):
with tf.device('/cpu:0'):
embedded = text_in.embedding_lookup(CHARS, [EMBEDDING_SIZE])
lstm = (embedded
.cleave_sequence(timesteps)
.sequence_lstm(CHARS))
return (lstm
.squash_sequence()
.fully_connected(32, activation_fn=tf.nn.relu)
.dropout(0.7)
.softmax_classifier(SEXES, labels, per_example_weights=per_example_weights))
def cnn():
with tf.variable_scope('cnn'):
with pt.defaults_scope(activation_fn=tf.nn.relu):
x_reshape = tf.reshape(x, [-1, 28, 28, 1])
cnn_seq = pt.wrap(x_reshape).sequential()
cnn_seq.conv2d(7, 16)
cnn_seq.max_pool(2, 2)
cnn_seq.conv2d(7, 16)
cnn_seq.max_pool(2, 2)
cnn_seq.flatten()
cnn_seq.fully_connected(32, activation_fn=tf.nn.relu)
cnn_seq.fully_connected(10, activation_fn=None)
return tf.nn.softmax(cnn_seq)
def neural_network(self, z):
"""p = neural_network(z)"""
with pt.defaults_scope(activation_fn=tf.nn.elu,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True):
return (pt.wrap(z).
reshape([N_DATA, 1, 1, self.num_vars]).
deconv2d(3, 128, edges='VALID').
deconv2d(5, 64, edges='VALID').
deconv2d(5, 32, stride=2).
deconv2d(5, 1, stride=2, activation_fn=tf.nn.sigmoid).
flatten()).tensor
def testMethodRegistrationWithDefaults(self):
# pylint: disable=unused-variable,invalid-name
@prettytensor.Register(assign_defaults='funny_name')
def test_method3(_, funny_name='not none'):
return tf.constant(funny_name)
result = self.RunTensor(self.input_layer.test_method3())
self.assertEqual(b'not none', result)
result = self.RunTensor(self.input_layer.test_method3(funny_name='other'))
self.assertEqual(b'other', result)
with prettytensor.defaults_scope(funny_name='something'):
result = self.RunTensor(self.input_layer.test_method3())
self.assertEqual(b'something', result)
result = self.RunTensor(self.input_layer.test_method3(funny_name='other'))
self.assertEqual(b'other', result)
def generative_network(z):
"""Generative network to parameterize generative model. It takes
latent variables as input and outputs the likelihood parameters.
logits = neural_network(z)
"""
with pt.defaults_scope(activation_fn=tf.nn.elu,
batch_normalize=True,
scale_after_normalization=True):
return (pt.wrap(z).
reshape([M, 1, 1, d]).
deconv2d(3, 128, edges='VALID').
deconv2d(5, 64, edges='VALID').
deconv2d(5, 32, stride=2).
deconv2d(5, 1, stride=2, activation_fn=None).
flatten()).tensor
def lenet5(images, labels):
"""Creates a multi layer convolutional network.
The architecture is similar to that defined in LeNet 5.
Please change this to experiment with architectures.
Args:
images: The input images.
labels: The labels as dense one-hot vectors.
Returns:
A softmax result.
"""
images = pt.wrap(images)
with pt.defaults_scope(activation_fn=tf.nn.relu, l2loss=0.00001):
return (images.conv2d(5, 20).max_pool(2, 2).conv2d(5, 50).max_pool(2, 2)
.flatten().fully_connected(500).softmax_classifier(10, labels))
def network():
gt = tf.placeholder(tf.float32, 1)
input_tensor = tf.placeholder(tf.float32,
[num_timesteps, len_feats])
assert(num_timesteps > 1)
with tf.variable_scope("model") as scope:
with pt.defaults_scope(activation_fn=tf.nn.relu,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True):
rnn_feats = rnn(input_tensor) # dim = [batch_size, hidden]
rnn_feats = tf.reshape(rnn_feats, [batch_size, -1])
pred = fc_layers(rnn_feats)
return input_tensor, pred, gt
def testConvBatchNormArgumentOverride(self):
st = self.input_layer.sequential()
st.reshape([DIM_SAME, DIM_SAME, DIM_SAME, 1])
with prettytensor.defaults_scope(batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True):
st.conv2d(3, 2,
batch_normalize=prettytensor.BatchNormalizationArguments(
scale_after_normalization=False))
self.assertEqual(2,
len(tf.get_collection(prettytensor.GraphKeys.UPDATE_OPS)))
self.assertTrue(tf.get_collection(tf.GraphKeys.VARIABLES, '.*/beta'))
self.assertFalse(tf.get_collection(tf.GraphKeys.VARIABLES, '.*/gamma'))
self.assertTrue(tf.get_collection(
tf.GraphKeys.VARIABLES, '.*/moving_variance'))
self.assertTrue(tf.get_collection(tf.GraphKeys.VARIABLES, '.*/moving_mean'))
def multilayer_fully_connected(images, labels):
"""Creates a multi layer network of fully_connected layers.
Each layer is 100 neurons. Please change this to experiment with
architectures.
Args:
images: The input images.
labels: The labels as dense one-hot vectors.
Returns:
A softmax result.
"""
# Pretty Tensor is a thin wrapper on Tensors.
# Change this method to experiment with other architectures
images = pt.wrap(images)
with pt.defaults_scope(activation_fn=tf.nn.relu, l2loss=0.00001):
return (images.flatten().fully_connected(100).fully_connected(100)
.softmax_classifier(10, labels))
def network():
dim_0, dim_1, dim_2 = grid_size
gt = tf.placeholder(tf.float32, [dim_0, dim_1])
input_tensor = tf.placeholder(tf.float32, [num_timesteps, dim_0, dim_1, dim_2])
mask = tf.placeholder(tf.float32, [dim_0, dim_1])
assert(num_timesteps > 1)
with tf.variable_scope("model") as scope:
with pt.defaults_scope(activation_fn=tf.nn.relu,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True):
enc = network_grid(input_tensor)
rnn_feats = network_rnn(enc)
rnn_feats = tf.reshape(rnn_feats, [1, 64])
pred = fc_layers(rnn_feats, dim_0)
return input_tensor, pred, gt, mask
