def main():
# parse the arguments
arg_parser = ArgumentParser()
spt.register_config_arguments(config, arg_parser)
arg_parser.parse_args(sys.argv[1:])
# print the config
print_with_title('Configurations', pformat(config.to_dict()), after='\n')
# open the result object and prepare for result directories
results = MLResults(config.result_dir)
results.save_config(config) # save experiment settings for review
results.make_dirs('plotting', exist_ok=True)
results.make_dirs('train_summary', exist_ok=True)
# input placeholders
input_x = tf.placeholder(dtype=tf.int32,
shape=(None, config.x_dim),
name='input_x')
learning_rate = spt.AnnealingVariable('learning_rate', config.initial_lr,
config.lr_anneal_factor)
# build the posterior flow
with tf.variable_scope('posterior_flow'):
flows = []
for i in range(config.n_flows):
flows.append(spt.layers.ActNorm())
flows.append(
spt.layers.CouplingLayer(tf.make_template(
'coupling',
coupling_layer_shift_and_scale,
create_scope_now_=True),
scale_type='exp'))
flows.append(spt.layers.InvertibleDense())
posterior_flow = spt.layers.SequentialFlow(flows=flows)
# derive the initialization op
with tf.name_scope('initialization'), \
arg_scope([spt.layers.act_norm], initializing=True):
init_q_net = q_net(input_x, posterior_flow)
init_chain = init_q_net.chain(p_net,
latent_axis=0,
observed={'x': input_x})
init_loss = tf.reduce_mean(init_chain.vi.training.sgvb())
# derive the loss and lower-bound for training
with tf.name_scope('training'):
train_q_net = q_net(input_x, posterior_flow)
train_chain = train_q_net.chain(p_net,
latent_axis=0,
observed={'x': input_x})
vae_loss = tf.reduce_mean(train_chain.vi.training.sgvb())
loss = vae_loss + tf.losses.get_regularization_loss()
# derive the nll and logits output for testing
with tf.name_scope('testing'):
test_q_net = q_net(input_x, posterior_flow, n_z=config.test_n_z)
test_chain = test_q_net.chain(p_net,
latent_axis=0,
observed={'x': input_x})
test_nll = -tf.reduce_mean(test_chain.vi.evaluation.is_loglikelihood())
test_lb = tf.reduce_mean(test_chain.vi.lower_bound.elbo())
# derive the optimizer
with tf.name_scope('optimizing'):
optimizer = tf.train.AdamOptimizer(learning_rate)
params = tf.trainable_variables()
grads = optimizer.compute_gradients(loss, var_list=params)
with tf.control_dependencies(tf.get_collection(
tf.GraphKeys.UPDATE_OPS)):
train_op = optimizer.apply_gradients(grads)
# derive the plotting function
with tf.name_scope('plotting'):
plot_p_net = p_net(n_z=100)
x_plots = tf.reshape(bernoulli_as_pixel(plot_p_net['x']), (-1, 28, 28))
def plot_samples(loop):
with loop.timeit('plot_time'):
images = session.run(x_plots)
save_images_collection(images=images,
filename='plotting/{}.png'.format(
loop.epoch),
grid_size=(10, 10))
# prepare for training and testing data
(x_train, y_train), (x_test, y_test) = spt.datasets.load_mnist()
train_flow = bernoulli_flow(x_train,
config.batch_size,
shuffle=True,
skip_incomplete=True)
test_flow = bernoulli_flow(x_test, config.test_batch_size, sample_now=True)
with spt.utils.create_session().as_default() as session, \
train_flow.threaded(5) as train_flow:
# initialize the network
spt.utils.ensure_variables_initialized()
for [batch_x] in train_flow:
print('Network initialization loss: {:.6g}'.format(
session.run(init_loss, {input_x: batch_x})))
print('')
break
# train the network
with spt.TrainLoop(params,
var_groups=['p_net', 'q_net', 'posterior_flow'],
max_epoch=config.max_epoch,
max_step=config.max_step,
summary_dir=(results.system_path('train_summary')
if config.write_summary else None),
summary_graph=tf.get_default_graph(),
early_stopping=False) as loop:
trainer = spt.Trainer(loop,
train_op, [input_x],
train_flow,
metrics={'loss': loss})
trainer.anneal_after(learning_rate,
epochs=config.lr_anneal_epoch_freq,
steps=config.lr_anneal_step_freq)
evaluator = spt.Evaluator(loop,
metrics={
'test_nll': test_nll,
'test_lb': test_lb
},
inputs=[input_x],
data_flow=test_flow,
time_metric_name='test_time')
evaluator.after_run.add_hook(
lambda: results.update_metrics(evaluator.last_metrics_dict))
trainer.evaluate_after_epochs(evaluator, freq=10)
trainer.evaluate_after_epochs(functools.partial(
plot_samples, loop),
freq=10)
trainer.log_after_epochs(freq=1)
trainer.run()
# print the final metrics and close the results object
print_with_title('Results', results.format_metrics(), before='\n')
results.close()
def main():
# parse the arguments
arg_parser = ArgumentParser()
spt.register_config_arguments(config, arg_parser)
arg_parser.parse_args(sys.argv[1:])
# print the config
print_with_title('Configurations', pformat(config.to_dict()), after='\n')
# open the result object and prepare for result directories
results = MLResults(config.result_dir)
results.save_config(config) # save experiment settings for review
results.make_dirs('train_summary', exist_ok=True)
# input placeholders
input_x = tf.placeholder(dtype=tf.float32,
shape=(None, ) + config.x_shape,
name='input_x')
input_y = tf.placeholder(dtype=tf.int32, shape=[None], name='input_y')
is_training = tf.placeholder(dtype=tf.bool, shape=(), name='is_training')
learning_rate = spt.AnnealingVariable('learning_rate', config.initial_lr,
config.lr_anneal_factor)
multi_gpu = MultiGPU()
# build the model
grads = []
losses = []
y_list = []
acc_list = []
batch_size = spt.utils.get_batch_size(input_x)
params = None
optimizer = tf.train.AdamOptimizer(learning_rate)
for dev, pre_build, [dev_input_x, dev_input_y
] in multi_gpu.data_parallel(batch_size,
[input_x, input_y]):
with tf.device(dev), multi_gpu.maybe_name_scope(dev):
if pre_build:
_ = model(dev_input_x, is_training, channels_last=True)
else:
# derive the loss, output and accuracy
dev_logits = model(dev_input_x,
is_training=is_training,
channels_last=multi_gpu.channels_last(dev))
dev_cls_loss = tf.losses.sparse_softmax_cross_entropy(
dev_input_y, dev_logits)
dev_loss = dev_cls_loss + tf.losses.get_regularization_loss()
dev_y = spt.ops.softmax_classification_output(dev_logits)
dev_acc = spt.ops.classification_accuracy(dev_y, dev_input_y)
losses.append(dev_loss)
y_list.append(dev_y)
acc_list.append(dev_acc)
# derive the optimizer
params = tf.trainable_variables()
grads.append(
optimizer.compute_gradients(dev_loss, var_list=params))
# merge multi-gpu outputs and operations
[loss, acc] = multi_gpu.average([losses, acc_list], batch_size)
[y] = multi_gpu.concat([y_list])
train_op = multi_gpu.apply_grads(grads=multi_gpu.average_grads(grads),
optimizer=optimizer,
control_inputs=tf.get_collection(
tf.GraphKeys.UPDATE_OPS))
# prepare for training and testing data
(x_train, y_train), (x_test, y_test) = \
spt.datasets.load_cifar10(x_shape=config.x_shape, normalize_x=True)
train_flow = spt.DataFlow.arrays([x_train, y_train],
config.batch_size,
shuffle=True,
skip_incomplete=True)
test_flow = spt.DataFlow.arrays([x_test, y_test], config.test_batch_size)
with spt.utils.create_session().as_default():
# train the network
with spt.TrainLoop(params,
max_epoch=config.max_epoch,
max_step=config.max_step,
summary_dir=(results.system_path('train_summary')
if config.write_summary else None),
summary_graph=tf.get_default_graph(),
early_stopping=False) as loop:
trainer = spt.Trainer(loop,
train_op, [input_x, input_y],
train_flow,
feed_dict={is_training: True},
metrics={
'loss': loss,
'acc': acc
})
trainer.anneal_after(learning_rate,
epochs=config.lr_anneal_epoch_freq,
steps=config.lr_anneal_step_freq)
evaluator = spt.Evaluator(loop,
metrics={'test_acc': acc},
inputs=[input_x, input_y],
data_flow=test_flow,
feed_dict={is_training: False},
time_metric_name='test_time')
evaluator.after_run.add_hook(
lambda: results.update_metrics(evaluator.last_metrics_dict))
trainer.evaluate_after_epochs(evaluator, freq=5)
trainer.log_after_epochs(freq=1)
trainer.run()
# print the final metrics and close the results object
print_with_title('Results', results.format_metrics(), before='\n')
results.close()
def main():
# parse the arguments
arg_parser = ArgumentParser()
spt.register_config_arguments(config, arg_parser, title='Model options')
spt.register_config_arguments(spt.settings,
arg_parser,
prefix='tfsnippet',
title='TFSnippet options')
arg_parser.parse_args(sys.argv[1:])
# print the config
print_with_title('Configurations', pformat(config.to_dict()), after='\n')
# open the result object and prepare for result directories
results = MLResults(config.result_dir)
results.save_config(config) # save experiment settings for review
results.make_dirs('plotting', exist_ok=True)
results.make_dirs('train_summary', exist_ok=True)
# input placeholders
input_x = tf.placeholder(dtype=tf.int32,
shape=(None, config.x_dim),
name='input_x')
learning_rate = spt.AnnealingVariable('learning_rate', config.initial_lr,
config.lr_anneal_factor)
# derive the output for initialization
with tf.name_scope('initialization'), \
spt.utils.scoped_set_config(spt.settings, auto_histogram=False):
init_q_net = q_net(input_x, is_initializing=True)
init_chain = init_q_net.chain(p_net,
observed={'x': input_x},
is_initializing=True)
init_lb = tf.reduce_mean(init_chain.vi.lower_bound.elbo())
# derive the loss and lower-bound for training
with tf.name_scope('training'):
train_q_net = q_net(input_x)
train_chain = train_q_net.chain(p_net, observed={'x': input_x})
vae_loss = tf.reduce_mean(train_chain.vi.training.sgvb())
loss = vae_loss + tf.losses.get_regularization_loss()
# derive the nll and logits output for testing
with tf.name_scope('testing'):
test_q_net = q_net(input_x, n_z=config.test_n_z)
test_chain = test_q_net.chain(p_net,
latent_axis=0,
observed={'x': input_x})
test_nll = -tf.reduce_mean(test_chain.vi.evaluation.is_loglikelihood())
test_lb = tf.reduce_mean(test_chain.vi.lower_bound.elbo())
# derive the optimizer
with tf.name_scope('optimizing'):
optimizer = tf.train.AdamOptimizer(learning_rate)
params = tf.trainable_variables()
grads = optimizer.compute_gradients(loss, var_list=params)
with tf.control_dependencies(tf.get_collection(
tf.GraphKeys.UPDATE_OPS)):
train_op = optimizer.apply_gradients(grads)
# derive the plotting function
with tf.name_scope('plotting'):
plot_p_net = p_net(n_z=100)
x_plots = tf.reshape(bernoulli_as_pixel(plot_p_net['x']), (-1, 28, 28))
def plot_samples(loop):
with loop.timeit('plot_time'):
images = session.run(x_plots)
save_images_collection(images=images,
filename='plotting/{}.png'.format(
loop.epoch),
grid_size=(10, 10),
results=results)
# prepare for training and testing data
(x_train, y_train), (x_test, y_test) = \
spt.datasets.load_mnist(x_shape=[784])
train_flow = bernoulli_flow(x_train,
config.batch_size,
shuffle=True,
skip_incomplete=True)
test_flow = bernoulli_flow(x_test, config.test_batch_size, sample_now=True)
with spt.utils.create_session().as_default() as session, \
train_flow.threaded(5) as train_flow:
spt.utils.ensure_variables_initialized()
# initialize the network
for [x] in train_flow:
print('Network initialized, first-batch loss is {:.6g}.\n'.format(
session.run(init_lb, feed_dict={input_x: x})))
break
# train the network
with spt.TrainLoop(params,
var_groups=['q_net', 'p_net'],
max_epoch=config.max_epoch,
max_step=config.max_step,
summary_dir=(results.system_path('train_summary')
if config.write_summary else None),
summary_graph=tf.get_default_graph(),
early_stopping=False) as loop:
trainer = spt.Trainer(loop,
train_op, [input_x],
train_flow,
metrics={'loss': loss},
summaries=tf.summary.merge_all(
spt.GraphKeys.AUTO_HISTOGRAM))
trainer.anneal_after(learning_rate,
epochs=config.lr_anneal_epoch_freq,
steps=config.lr_anneal_step_freq)
evaluator = spt.Evaluator(loop,
metrics={
'test_nll': test_nll,
'test_lb': test_lb
},
inputs=[input_x],
data_flow=test_flow,
time_metric_name='test_time')
evaluator.events.on(
spt.EventKeys.AFTER_EXECUTION,
lambda e: results.update_metrics(evaluator.last_metrics_dict))
trainer.evaluate_after_epochs(evaluator, freq=10)
trainer.evaluate_after_epochs(functools.partial(
plot_samples, loop),
freq=10)
trainer.log_after_epochs(freq=1)
trainer.run()
# print the final metrics and close the results object
print_with_title('Results', results.format_metrics(), before='\n')
results.close()
def main():
# parse the arguments
arg_parser = ArgumentParser()
spt.register_config_arguments(config, arg_parser)
arg_parser.parse_args(sys.argv[1:])
# print the config
print_with_title('Configurations', pformat(config.to_dict()), after='\n')
# open the result object and prepare for result directories
results = MLResults(config.result_dir)
results.save_config(config) # save experiment settings for review
results.make_dirs('plotting', exist_ok=True)
results.make_dirs('train_summary', exist_ok=True)
# input placeholders
input_x = tf.placeholder(dtype=tf.int32,
shape=(None, config.x_dim),
name='input_x')
is_training = tf.placeholder(dtype=tf.bool, shape=(), name='is_training')
learning_rate = spt.AnnealingVariable('learning_rate', config.initial_lr,
config.lr_anneal_factor)
multi_gpu = MultiGPU(disable_prebuild=False)
# build the model
grads = []
losses = []
test_nlls = []
test_lbs = []
batch_size = spt.utils.get_batch_size(input_x)
params = None
optimizer = tf.train.AdamOptimizer(learning_rate)
for dev, pre_build, [dev_input_x
] in multi_gpu.data_parallel(batch_size, [input_x]):
with tf.device(dev), multi_gpu.maybe_name_scope(dev):
if pre_build:
with arg_scope([p_net, q_net],
is_training=is_training,
channels_last=True):
_ = q_net(dev_input_x).chain(p_net,
observed={'x': dev_input_x})
else:
with arg_scope([p_net, q_net],
is_training=is_training,
channels_last=multi_gpu.channels_last(dev)):
# derive the loss and lower-bound for training
with tf.name_scope('training'):
train_q_net = q_net(dev_input_x)
train_chain = train_q_net.chain(
p_net, latent_axis=0, observed={'x': dev_input_x})
dev_vae_loss = tf.reduce_mean(
train_chain.vi.training.sgvb())
dev_loss = dev_vae_loss + \
tf.losses.get_regularization_loss()
losses.append(dev_loss)
# derive the nll and logits output for testing
with tf.name_scope('testing'):
test_q_net = q_net(dev_input_x, n_z=config.test_n_z)
test_chain = test_q_net.chain(
p_net, latent_axis=0, observed={'x': dev_input_x})
dev_test_nll = -tf.reduce_mean(
test_chain.vi.evaluation.is_loglikelihood())
dev_test_lb = tf.reduce_mean(
test_chain.vi.lower_bound.elbo())
test_nlls.append(dev_test_nll)
test_lbs.append(dev_test_lb)
# derive the optimizer
with tf.name_scope('optimizing'):
params = tf.trainable_variables()
grads.append(
optimizer.compute_gradients(dev_loss,
var_list=params))
# merge multi-gpu outputs and operations
with tf.name_scope('optimizing'):
[loss, test_lb, test_nll] = \
multi_gpu.average([losses, test_lbs, test_nlls], batch_size)
train_op = multi_gpu.apply_grads(grads=multi_gpu.average_grads(grads),
optimizer=optimizer,
control_inputs=tf.get_collection(
tf.GraphKeys.UPDATE_OPS))
# derive the plotting function
work_dev = multi_gpu.work_devices[0]
with tf.device(work_dev), tf.name_scope('plotting'):
plot_p_net = p_net(n_z=100,
is_training=is_training,
channels_last=multi_gpu.channels_last(work_dev))
x_plots = tf.reshape(bernoulli_as_pixel(plot_p_net['x']), (-1, 28, 28))
def plot_samples(loop):
with loop.timeit('plot_time'):
images = session.run(x_plots, feed_dict={is_training: False})
save_images_collection(images=images,
filename='plotting/{}.png'.format(
loop.epoch),
grid_size=(10, 10),
results=results)
# prepare for training and testing data
(x_train, y_train), (x_test, y_test) = spt.datasets.load_mnist()
train_flow = bernoulli_flow(x_train,
config.batch_size,
shuffle=True,
skip_incomplete=True)
test_flow = bernoulli_flow(x_test, config.test_batch_size, sample_now=True)
with spt.utils.create_session().as_default() as session, \
train_flow.threaded(5) as train_flow:
# train the network
with spt.TrainLoop(params,
var_groups=['q_net', 'p_net'],
max_epoch=config.max_epoch,
max_step=config.max_step,
summary_dir=(results.system_path('train_summary')
if config.write_summary else None),
summary_graph=tf.get_default_graph(),
early_stopping=False) as loop:
trainer = spt.Trainer(loop,
train_op, [input_x],
train_flow,
feed_dict={is_training: True},
metrics={'loss': loss})
trainer.anneal_after(learning_rate,
epochs=config.lr_anneal_epoch_freq,
steps=config.lr_anneal_step_freq)
evaluator = spt.Evaluator(loop,
metrics={
'test_nll': test_nll,
'test_lb': test_lb
},
inputs=[input_x],
data_flow=test_flow,
feed_dict={is_training: False},
time_metric_name='test_time')
evaluator.after_run.add_hook(
lambda: results.update_metrics(evaluator.last_metrics_dict))
trainer.evaluate_after_epochs(evaluator, freq=10)
trainer.evaluate_after_epochs(functools.partial(
plot_samples, loop),
freq=10)
trainer.log_after_epochs(freq=1)
trainer.run()
# print the final metrics and close the results object
print_with_title('Results', results.format_metrics(), before='\n')
results.close()
def main():
# parse the arguments
arg_parser = ArgumentParser()
spt.register_config_arguments(config, arg_parser, title='Model options')
spt.register_config_arguments(spt.settings,
arg_parser,
prefix='tfsnippet',
title='TFSnippet options')
arg_parser.parse_args(sys.argv[1:])
# print the config
print_with_title('Configurations', pformat(config.to_dict()), after='\n')
# open the result object and prepare for result directories
results = MLResults(config.result_dir)
results.save_config(config) # save experiment settings for review
results.make_dirs('plotting', exist_ok=True)
results.make_dirs('train_summary', exist_ok=True)
# input placeholders
input_x = tf.placeholder(dtype=tf.int32,
shape=(None, config.x_dim),
name='input_x')
learning_rate = spt.AnnealingVariable('learning_rate', config.initial_lr,
config.lr_anneal_factor)
# derive the loss and lower-bound for training
with tf.name_scope('training'):
train_q_net = q_net(input_x, n_samples=config.train_n_samples)
train_chain = train_q_net.chain(p_net,
latent_axis=0,
observed={'x': input_x})
if config.vi_algorithm == 'reinforce':
baseline = reinforce_baseline_net(input_x)
vae_loss = tf.reduce_mean(
train_chain.vi.training.reinforce(baseline=baseline))
else:
assert (config.vi_algorithm == 'vimco')
vae_loss = tf.reduce_mean(train_chain.vi.training.vimco())
loss = vae_loss + tf.losses.get_regularization_loss()
# derive the nll and logits output for testing
with tf.name_scope('testing'):
test_q_net = q_net(input_x, n_samples=config.test_n_samples)
test_chain = test_q_net.chain(p_net,
latent_axis=0,
observed={'x': input_x})
test_nll = -tf.reduce_mean(test_chain.vi.evaluation.is_loglikelihood())
# derive the classifier via q(y|x)
q_y_given_x = tf.argmax(test_q_net['y'].distribution.logits,
axis=-1,
name='q_y_given_x')
# derive the optimizer
with tf.name_scope('optimizing'):
optimizer = tf.train.AdamOptimizer(learning_rate)
params = tf.trainable_variables()
grads = optimizer.compute_gradients(loss, var_list=params)
with tf.control_dependencies(tf.get_collection(
tf.GraphKeys.UPDATE_OPS)):
train_op = optimizer.apply_gradients(grads)
# derive the plotting function
with tf.name_scope('plotting'):
plot_p_net = p_net(
observed={'y': tf.range(config.n_clusters, dtype=tf.int32)},
n_z=10)
x_plots = tf.reshape(
tf.transpose(bernoulli_as_pixel(plot_p_net['x']), (1, 0, 2)),
(-1, 28, 28))
def plot_samples(loop):
with loop.timeit('plot_time'):
images = session.run(x_plots)
save_images_collection(images=images,
filename='plotting/{}.png'.format(
loop.epoch),
grid_size=(config.n_clusters, 10),
results=results)
# derive the final un-supervised classifier
c_classifier = ClusteringClassifier(config.n_clusters, 10)
def train_classifier(loop):
df = bernoulli_flow(x_train,
config.batch_size,
shuffle=False,
skip_incomplete=False)
with loop.timeit('cls_train_time'):
[c_pred] = collect_outputs(
outputs=[q_y_given_x],
inputs=[input_x],
data_flow=df,
)
c_classifier.fit(c_pred, y_train)
print(c_classifier.describe())
def evaluate_classifier(loop):
with loop.timeit('cls_test_time'):
[c_pred] = collect_outputs(
outputs=[q_y_given_x],
inputs=[input_x],
data_flow=test_flow,
)
y_pred = c_classifier.predict(c_pred)
cls_metrics = {'test_acc': accuracy_score(y_test, y_pred)}
loop.collect_metrics(cls_metrics)
results.update_metrics(cls_metrics)
# prepare for training and testing data
(x_train, y_train), (x_test, y_test) = \
spt.datasets.load_mnist(x_shape=[784])
train_flow = bernoulli_flow(x_train,
config.batch_size,
shuffle=True,
skip_incomplete=True)
test_flow = bernoulli_flow(x_test, config.test_batch_size, sample_now=True)
with spt.utils.create_session().as_default() as session, \
train_flow.threaded(5) as train_flow:
# train the network
with spt.TrainLoop(
params,
var_groups=['p_net', 'q_net', 'gaussian_mixture_prior'],
max_epoch=config.max_epoch,
max_step=config.max_step,
summary_dir=(results.system_path('train_summary')
if config.write_summary else None),
summary_graph=tf.get_default_graph(),
early_stopping=False) as loop:
trainer = spt.Trainer(loop,
train_op, [input_x],
train_flow,
metrics={'loss': loss},
summaries=tf.summary.merge_all(
spt.GraphKeys.AUTO_HISTOGRAM))
trainer.anneal_after(learning_rate,
epochs=config.lr_anneal_epoch_freq,
steps=config.lr_anneal_step_freq)
evaluator = spt.Evaluator(loop,
metrics={'test_nll': test_nll},
inputs=[input_x],
data_flow=test_flow,
time_metric_name='test_time')
evaluator.events.on(
spt.EventKeys.AFTER_EXECUTION,
lambda e: results.update_metrics(evaluator.last_metrics_dict))
trainer.evaluate_after_epochs(evaluator, freq=10)
trainer.evaluate_after_epochs(functools.partial(
plot_samples, loop),
freq=10)
trainer.evaluate_after_epochs(functools.partial(
train_classifier, loop),
freq=10)
trainer.evaluate_after_epochs(functools.partial(
evaluate_classifier, loop),
freq=10)
trainer.log_after_epochs(freq=1)
trainer.run()
# print the final metrics and close the results object
with codecs.open('cluster_classifier.txt', 'wb', 'utf-8') as f:
f.write(c_classifier.describe())
print_with_title('Results', results.format_metrics(), before='\n')
results.close()
def main():
# parse the arguments
arg_parser = ArgumentParser()
spt.register_config_arguments(config, arg_parser, title='Model options')
spt.register_config_arguments(spt.settings,
arg_parser,
prefix='tfsnippet',
title='TFSnippet options')
arg_parser.parse_args(sys.argv[1:])
# print the config
print_with_title('Configurations', pformat(config.to_dict()), after='\n')
# open the result object and prepare for result directories
model_file = config.result_dir + "/" + os.path.basename(__file__).split(".py")[0] + "_" + \
str(config.noExp) + ".model"
dirName = os.path.basename(__file__).split(".py")[0] + "_" + str(
config.noExp)
results = MLResults(os.path.join(config.result_dir, dirName))
results.save_config(config) # save experiment settings
results.make_dirs('train_summary', exist_ok=True)
results.make_dirs('result_summary', exist_ok=True)
results.make_dirs('mid_summary', exist_ok=True)
# os.environ["CUDA_VISIBLE_DEVICES"] = config.GPU_number
# input placeholders
input_x = tf.placeholder(dtype=tf.float32,
shape=(None, ) + config.x_shape,
name='input_x')
learning_rate = spt.AnnealingVariable('learning_rate',
config.initial_lr,
config.lr_anneal_factor,
min_value=1e-6)
multi_gpu = MultiGPU(disable_prebuild=True)
# multi_gpu = MultiGPU()
# derive the training operation
gradses = []
grad_vars = []
train_losses = []
BATCH_SIZE = get_batch_size(input_x)
for dev, pre_build, [dev_input_x
] in multi_gpu.data_parallel(BATCH_SIZE, [input_x]):
with tf.device(dev), multi_gpu.maybe_name_scope(dev):
# derive the loss for initializing
with tf.name_scope('initialization'), \
arg_scope([p_net, q_net], is_initializing=True), \
spt.utils.scoped_set_config(spt.settings, auto_histogram=False):
init_q_net = q_net(dev_input_x, n_z=config.train_n_samples)
init_chain = init_q_net.chain(p_net,
latent_axis=0,
observed={'x': dev_input_x})
init_loss = tf.reduce_mean(init_chain.vi.training.vimco())
# derive the loss and lower-bound for training
with tf.name_scope('training'), \
arg_scope([p_net, q_net], is_training=True):
train_q_net = q_net(dev_input_x, n_z=config.train_n_samples)
train_chain = train_q_net.chain(p_net,
latent_axis=0,
observed={'x': dev_input_x})
train_loss = (tf.reduce_mean(train_chain.vi.training.vimco()) +
tf.losses.get_regularization_loss())
train_losses.append(train_loss)
# derive the logits output for testing
with tf.name_scope('testing'):
test_q_net = q_net(dev_input_x, n_z=config.test_n_z)
test_chain = test_q_net.chain(p_net,
latent_axis=0,
observed={'x': dev_input_x})
# log_prob of X and each univariate time series of X
log_prob = tf.reduce_mean(
test_chain.model['x'].distribution.log_prob(dev_input_x),
0)
log_prob_per_element = tf.reduce_sum(log_prob)
log_prob_per_element_univariate_TS = tf.reduce_sum(
log_prob, [0, 1, 3])
log_prob_per_element_univariate_TS_All = tf.reduce_sum(
log_prob, [1, 3])
# derive the optimizer
with tf.name_scope('optimizing'):
params = tf.trainable_variables()
optimizer = tf.train.AdamOptimizer(learning_rate)
grads = optimizer.compute_gradients(train_loss, params)
for grad, var in grads:
if grad is not None and var is not None:
if config.grad_clip_norm:
grad = tf.clip_by_norm(grad, config.grad_clip_norm)
if config.check_numerics:
grad = tf.check_numerics(
grad,
'gradient for {} has numeric issue'.format(
var.name))
grad_vars.append((grad, var))
gradses.append(grad_vars)
# merge multi-gpu outputs and operations
[train_loss] = multi_gpu.average([train_losses], BATCH_SIZE)
train_op = multi_gpu.apply_grads(grads=multi_gpu.average_grads(gradses),
optimizer=optimizer,
control_inputs=tf.get_collection(
tf.GraphKeys.UPDATE_OPS))
# sort the contribution of each univariate_TS of input
SORT_UNIVARIATE_TS_INPUT = tf.placeholder(dtype=tf.float32,
shape=(None, None),
name='SORT_UNIVARIATE_TS_INPUT')
SORT_UNIVARIATE_TS = tf.nn.top_k(SORT_UNIVARIATE_TS_INPUT,
k=config.metricNumber).indices + 1
# load the training and testing data
print("=" * 10 + "Shape of Input data" + "=" * 10)
x, time_indexs, x_test, time_indexs2 = load_matrix_allData(
config.dataReadformat, config.datapathForTrain, config.datapathForTest,
config.timeLength, config.metricNumber, "TrainFileNameList.txt",
"TestFileNameList.txt", results, config.norm)
x_test = x_test.reshape([-1, config.timeLength, config.metricNumber, 1])
print("Test:", x_test.shape)
if config.batchTest:
test_flow = DataFlow.arrays(
[x_test], config.test_batch_size) # DataFlow is iterator
del x_test
x_train, x_val = split_numpy_array(x, portion=config.VALID_PORTION)
x_train = x_train.reshape([-1, config.timeLength, config.metricNumber, 1])
x_val = x_val.reshape([-1, config.timeLength, config.metricNumber, 1])
train_flow = DataFlow.arrays([x_train],
config.batch_size,
shuffle=False,
skip_incomplete=True)
val_flow = DataFlow.arrays([x_val], config.test_batch_size)
print("Note:", config.x_dim,
", x_dim = size of datapoint = timeLength * metricNumber")
print("Input data shape:", x.shape, "Train data shape:", x_train.shape,
"Validation data shape:", x_val.shape)
del x_train, x_val, x
# training part
with spt.utils.create_session().as_default() as session:
spt.utils.ensure_variables_initialized()
saver = CheckpointSaver(tf.trainable_variables(), model_file)
if os.path.exists(model_file):
# load the parameters of trained model
saver.restore_latest()
else:
# initialize the network
while True:
breakFlag = 0
for [x] in train_flow:
INITLOSS = session.run(init_loss, feed_dict={input_x: x})
print('Network initialized, first-batch loss is {:.6g}.'.
format(INITLOSS))
if np.isnan(INITLOSS) or np.isinf(
INITLOSS) or INITLOSS > 10**5:
pass
else:
breakFlag = 1
break
if breakFlag:
break
# train the network
with train_flow.threaded(10) as train_flow:
with spt.TrainLoop(
params,
var_groups=['q_net', 'p_net'],
max_epoch=config.max_epoch,
max_step=config.max_step,
summary_dir=(results.system_path('train_summary')
if config.write_summary else None),
summary_graph=tf.get_default_graph(),
early_stopping=True) as loop:
trainer = spt.Trainer(loop,
train_op, [input_x],
train_flow,
metrics={'loss': train_loss},
summaries=tf.summary.merge_all(
spt.GraphKeys.AUTO_HISTOGRAM))
# anneal the learning rate
trainer.anneal_after(learning_rate,
epochs=config.lr_anneal_epoch_freq,
steps=config.lr_anneal_step_freq)
validator = spt.Validator(
loop,
train_loss,
[input_x],
val_flow,
)
trainer.evaluate_after_epochs(validator, freq=10)
trainer.log_after_epochs(freq=1)
trainer.run()
saver.save()
# save the training infomation
firWrite = True
num = 0
time0 = time.time()
for [x_train] in train_flow:
if config.savetrainDS:
# log prob of each metric of each instance
log_prob_per_element_univariate_TS_list_item_Train = (
session.run(log_prob_per_element_univariate_TS_All,
feed_dict={input_x: x_train}))
log_prob_per_element_univariate_TS_list_Train = log_prob_per_element_univariate_TS_list_item_Train
log_prob_per_element_list_Train = np.sum(np.array(
log_prob_per_element_univariate_TS_list_item_Train),
axis=1).tolist()
if firWrite:
save_file(
results.system_path("train_summary"),
"OutlierScores_metric.txt",
log_prob_per_element_univariate_TS_list_Train)
save_file(results.system_path("train_summary"),
"OutlierScores.txt",
log_prob_per_element_list_Train)
else:
save_file(
results.system_path("train_summary"),
"OutlierScores_metric.txt",
log_prob_per_element_univariate_TS_list_Train,
"\n", "a")
save_file(results.system_path("train_summary"),
"OutlierScores.txt",
log_prob_per_element_list_Train, "\n", "a")
firWrite = False
num += 1
if num % 1000 == 0:
print(
"-----Train %s >>>>>:Sum time of batch instances:%s" %
(num, float(time.time() - time0) / float(num)))
del train_flow, val_flow
# online test
time2 = time.time()
log_prob_per_element_list, log_prob_per_element_univariate_TS_list = [], []
if config.batchTest:
num = 0
for [x_test] in test_flow:
if config.savetestDS:
# log prob of each metric of each instance
log_prob_per_element_univariate_TS_list_item = (
session.run(log_prob_per_element_univariate_TS_All,
feed_dict={input_x: x_test}))
log_prob_per_element_univariate_TS_list += log_prob_per_element_univariate_TS_list_item.tolist(
)
log_prob_per_element_list += np.sum(
np.array(log_prob_per_element_univariate_TS_list_item),
axis=1).tolist()
num += 1
if num % 200 == 0:
print("-----Test %s >>>>>:Sum time of batch instances:%s" %
(num, float(time.time() - time2) / float(num)))
else:
num = 1
for batch_x in x_test:
if config.savetestTS:
log_prob_per_element_list_item = (session.run(
log_prob_per_element, feed_dict={input_x: [batch_x]}))
log_prob_per_element_list.append(
log_prob_per_element_list_item)
if config.savetestDS:
log_prob_per_element_univariate_TS_list_item = (
session.run(log_prob_per_element_univariate_TS,
feed_dict={input_x: [batch_x]}))
log_prob_per_element_univariate_TS_list.append(
log_prob_per_element_univariate_TS_list_item)
log_prob_per_element_list.append(
sum(log_prob_per_element_univariate_TS_list_item))
if num % 200 == 0:
print(
"-----Test>>>>>:%d, average time of each instance:%s" %
(num, float(time.time() - time2) / float(num)))
num += 1
# get the lable file name and its line cnt number
allLabelFileNameLineCntList = get_machineID(results, config.labelpath)
print("No of OutlierScores for all dataPoint:(%s):" %
len(log_prob_per_element_list))
if config.savetestDS:
save_file(
results.system_path("result_summary"),
"OutlierScores_metric.txt",
cat_List(allLabelFileNameLineCntList,
log_prob_per_element_univariate_TS_list))
save_file(
results.system_path("result_summary"), "OutlierScores.txt",
cat_List(allLabelFileNameLineCntList, log_prob_per_element_list))
if config.evaluation:
# Prepraration for the hitory two-metric results
twoMetricScore = read_file(results.system_path("train_summary"),
"OutlierScores_metric.txt")
ave_twoMetricScore = np.mean(np.array(twoMetricScore),
axis=0).tolist()
save_file(results.system_path("result_summary"), "PRF.txt",
["Average score of each univariate time series", "\n"],
",")
save_file(results.system_path("result_summary"), "PRF.txt",
ave_twoMetricScore + ["\n"], ",", "a")
save_file(results.system_path("result_summary"), "PRF.txt", [
"Threshold", "F", "Precision", "Recall", "TP", "FP", "FN", "\n"
], ",", "a")
# get the sorted item each metric by change score
twoMetricScoreList = cal_scoreChanges(
log_prob_per_element_list, ave_twoMetricScore,
log_prob_per_element_univariate_TS_list)
MetricResult = session.run(
SORT_UNIVARIATE_TS,
feed_dict={SORT_UNIVARIATE_TS_INPUT: twoMetricScoreList})
save_file(results.system_path("result_summary"),
"MetricResult.txt",
cat_List(allLabelFileNameLineCntList, MetricResult))
# POT evalution
POT_TH = pot_eval(
read_file(results.system_path("train_summary"),
"OutlierScores.txt", "float"), config.q,
config.level)
resultArray, outlierLabelfileNameLineCntList = cal_binaryResult(
log_prob_per_element_list, POT_TH, time_indexs2,
config.saveMetricInfo, allLabelFileNameLineCntList)
evaluate(results, config.labelpath, resultArray, time_indexs2,
POT_TH)
# print the final metrics and close the results object
print_with_title('Results', results.format_metrics(), before='\n')
results.close()
interpretation_hit_ratio(truth_filepath=config.interpret_filepath,
prediction_filepath=os.path.join(
config.result_dir, dirName, "result_summary",
"MetricResult.txt"))
def main():
# parse the arguments
arg_parser = ArgumentParser()
spt.register_config_arguments(config, arg_parser, title='Model options')
spt.register_config_arguments(spt.settings,
arg_parser,
prefix='tfsnippet',
title='TFSnippet options')
arg_parser.parse_args(sys.argv[1:])
# print the config
print_with_title('Configurations', pformat(config.to_dict()), after='\n')
# open the result object and prepare for result directories
results = MLResults(config.result_dir)
results.save_config(config) # save experiment settings for review
results.make_dirs('train_summary', exist_ok=True)
# input placeholders
input_x = tf.placeholder(dtype=tf.float32,
shape=(None, config.x_dim),
name='input_x')
input_y = tf.placeholder(dtype=tf.int32, shape=[None], name='input_y')
learning_rate = spt.AnnealingVariable('learning_rate', config.initial_lr,
config.lr_anneal_factor)
# derive the loss, output and accuracy
logits = model(input_x)
cls_loss = tf.losses.sparse_softmax_cross_entropy(input_y, logits)
loss = cls_loss + tf.losses.get_regularization_loss()
y = spt.ops.softmax_classification_output(logits)
acc = spt.ops.classification_accuracy(y, input_y)
# derive the optimizer
optimizer = tf.train.AdamOptimizer(learning_rate)
params = tf.trainable_variables()
grads = optimizer.compute_gradients(loss, var_list=params)
with tf.control_dependencies(tf.get_collection(tf.GraphKeys.UPDATE_OPS)):
train_op = optimizer.apply_gradients(grads)
# prepare for training and testing data
(x_train, y_train), (x_test, y_test) = \
spt.datasets.load_cifar10(x_shape=(config.x_dim,), normalize_x=True)
train_flow = spt.DataFlow.arrays([x_train, y_train],
config.batch_size,
shuffle=True,
skip_incomplete=True)
test_flow = spt.DataFlow.arrays([x_test, y_test], config.test_batch_size)
with spt.utils.create_session().as_default():
# train the network
with spt.TrainLoop(params,
max_epoch=config.max_epoch,
max_step=config.max_step,
summary_dir=(results.system_path('train_summary')
if config.write_summary else None),
summary_graph=tf.get_default_graph(),
early_stopping=False) as loop:
trainer = spt.Trainer(loop,
train_op, [input_x, input_y],
train_flow,
metrics={
'loss': loss,
'acc': acc
},
summaries=tf.summary.merge_all(
spt.GraphKeys.AUTO_HISTOGRAM))
trainer.anneal_after(learning_rate,
epochs=config.lr_anneal_epoch_freq,
steps=config.lr_anneal_step_freq)
evaluator = spt.Evaluator(loop,
metrics={'test_acc': acc},
inputs=[input_x, input_y],
data_flow=test_flow,
time_metric_name='test_time')
evaluator.events.on(
spt.EventKeys.AFTER_EXECUTION,
lambda e: results.update_metrics(evaluator.last_metrics_dict))
trainer.evaluate_after_epochs(evaluator, freq=5)
trainer.log_after_epochs(freq=1)
trainer.run()
# print the final metrics and close the results object
print_with_title('Results', results.format_metrics(), before='\n')
results.close()
def main(trainpath, normalpath, abnormalpath, outputpath):
if config.debug_level == -1:
spt.utils.set_assertion_enabled(False)
elif config.debug_level == 1:
spt.utils.set_check_numerics(True)
#spt.utils.set_assertion_enabled(False)
# print the config
print_with_title('Configurations', config.format_config(), after='\n')
# input and output file
train_file = trainpath
normal_file = normalpath
abnormal_file = abnormalpath
output_file = os.path.join('webankdata',
'{}_{}.csv'.format(config.flow_type or 'vae',
outputpath))
valid_file = os.path.join('webankdata',
'v{}_{}.csv'.format(config.flow_type or 'vae',
outputpath))
# you can change it by yourself
# read data
(x_train, y_train), (x_test, y_test), flows_test = \
get_data_vae(train_file, normal_file, abnormal_file)
config.x_dim = x_train.shape[1]
#config.z_dim = get_z_dim(x_train.shape[1])
all_len = x_train.shape[0]
print('origin data: %s' % all_len)
for i in range(30):
print(list(x_train[i]))
valid_rate = 0.1
x_train, x_valid = train_test_split(x_train, test_size=valid_rate)
# x_valid = x_train
print('%s for validation, %s for training v2' % (x_valid.shape[0], x_train.shape[0]))
print('%s for test' % x_test.shape[0])
print('x_dim: %s z_dim: %s' % (config.x_dim, config.z_dim))
# change it by yourself
# input placeholders
input_x = tf.placeholder(
dtype=tf.float32, shape=(None, config.x_dim), name='input_x')
learning_rate = spt.AnnealingVariable(
'learning_rate', config.initial_lr, config.lr_anneal_factor)
# build the posterior flow
if config.flow_type is None:
posterior_flow = None
elif config.flow_type == 'planar_nf':
posterior_flow = \
spt.layers.planar_normalizing_flows(config.n_planar_nf_layers)
else:
assert(config.flow_type == 'rnvp')
with tf.variable_scope('posterior_flow'):
flows = []
for i in range(config.n_rnvp_layers):
flows.append(spt.layers.ActNorm())
flows.append(spt.layers.CouplingLayer(
tf.make_template(
'coupling',
coupling_layer_shift_and_scale,
create_scope_now_=True
),
scale_type='sigmoid'
))
flows.append(spt.layers.InvertibleDense(strict_invertible=True))
posterior_flow = spt.layers.SequentialFlow(flows=flows)
# derive the initialization op
with tf.name_scope('initialization'), \
arg_scope([spt.layers.act_norm], initializing=True):
init_q_net = q_net(input_x, posterior_flow)
init_chain = init_q_net.chain(
p_net, latent_axis=0, observed={'x': input_x})
init_loss = tf.reduce_mean(init_chain.vi.training.sgvb())
# derive the loss and lower-bound for training
with tf.name_scope('training'):
train_q_net = q_net(input_x, posterior_flow)
train_chain = train_q_net.chain(
p_net, latent_axis=0, observed={'x': input_x})
vae_loss = tf.reduce_mean(train_chain.vi.training.sgvb())
loss = vae_loss + tf.losses.get_regularization_loss()
# derive the nll and logits output for testing
with tf.name_scope('testing'):
test_q_net = q_net(input_x, posterior_flow, n_z=config.test_n_z)
test_chain = test_q_net.chain(
p_net, latent_axis=0, observed={'x': input_x})
test_logp = test_chain.vi.evaluation.is_loglikelihood()
test_nll = -tf.reduce_mean(test_logp)
test_lb = tf.reduce_mean(test_chain.vi.lower_bound.elbo())
# derive the optimizer
with tf.name_scope('optimizing'):
optimizer = tf.train.AdamOptimizer(learning_rate)
params = tf.trainable_variables()
grads = optimizer.compute_gradients(loss, var_list=params)
cliped_grad = []
for grad, var in grads:
if grad is not None and var is not None:
if config.norm_clip is not None:
grad = tf.clip_by_norm(grad, config.norm_clip)
cliped_grad.append((grad, var))
with tf.control_dependencies(
tf.get_collection(tf.GraphKeys.UPDATE_OPS)):
train_op = optimizer.apply_gradients(cliped_grad)
train_flow = spt.DataFlow.arrays([x_train],
config.batch_size,
shuffle=True,
skip_incomplete=True)
valid_flow = spt.DataFlow.arrays([x_valid],
config.test_batch_size)
test_flow = spt.DataFlow.arrays([x_test],
config.test_batch_size)
# model_file
#model_name = ''
model_name = os.path.join(
'webankdata',
'md_{}_{}.model'.format(
config.flow_type or 'vae',
outputpath.split('.')[0]
)
)
with spt.utils.create_session().as_default() as session:
var_dict = spt.utils.get_variables_as_dict()
saver = spt.VariableSaver(var_dict, model_name)
#if os.path.exists(model_name):
if False:
print('%s exists' % model_name)
saver.restore()
else:
print('no model here, and start training')
# initialize the network
spt.utils.ensure_variables_initialized()
for [batch_x] in train_flow:
print('Network initialization loss: {:.6g}'.
format(session.run(init_loss, {input_x: batch_x})))
print('')
break
# train the network
with spt.TrainLoop(params,
var_groups=['p_net', 'q_net', 'posterior_flow'],
max_epoch=config.max_epoch,
max_step=config.max_step,
early_stopping=True,
valid_metric_name='valid_loss',
valid_metric_smaller_is_better=True) as loop:
trainer = spt.Trainer(
loop, train_op, [input_x], train_flow,
metrics={'loss': loss}
)
trainer.anneal_after(
learning_rate,
epochs=config.lr_anneal_epoch_freq,
steps=config.lr_anneal_step_freq
)
evaluator = spt.Evaluator(
loop,
metrics={'valid_loss': test_nll},
inputs=[input_x],
data_flow=valid_flow,
time_metric_name='valid_time'
)
trainer.evaluate_after_epochs(evaluator, freq=10)
trainer.log_after_epochs(freq=1)
trainer.run()
saver.save()
# get the answer
print('start testing')
start = time.time()
test_ans = collect_outputs([test_logp], [input_x], test_flow)[0] \
/ config.x_dim
end = time.time()
print("test time: ", end-start)
pd.DataFrame(
{'id': flows_test, 'label': y_test, 'score': test_ans}) \
.to_csv(output_file, index=False)
valid_ans = collect_outputs([test_logp], [input_x], valid_flow)[0] \
/ config.x_dim
pd.DataFrame({'score': valid_ans}).to_csv(valid_file, index=False)
