def main(_):
FLAGS = create_parser("train") # pylint: disable=invalid-name
hparams = create_hparams("train", FLAGS)
train_spec = {
"run": RayModel,
"resources_per_trial": {
"cpu": FLAGS.cpu,
"gpu": FLAGS.gpu
},
"stop": {
"training_iteration": hparams.num_epochs,
},
"config": hparams.values(),
"local_dir": FLAGS.local_dir,
"checkpoint_freq": FLAGS.checkpoint_freq,
"checkpoint_at_end": FLAGS.checkpoint_at_end,
"num_samples": FLAGS.num_samples
}
if FLAGS.restore:
train_spec["restore"] = FLAGS.restore
ray.init()
run_experiments({FLAGS.name: train_spec})
def main(_):
FLAGS = create_parser("train") # pylint: disable=invalid-name # TODO
hparams = create_hparams("train", FLAGS) # TODO
train_spec = {
"run": RayModel,
"resources_per_trial": {
"cpu": FLAGS.cpu,
"gpu": FLAGS.gpu
},
"stop": {
"training_iteration": hparams.num_epochs,
},
"config": hparams.values(),
"local_dir": FLAGS.local_dir,
"checkpoint_freq": FLAGS.checkpoint_freq,
"num_samples": FLAGS.num_samples
}
if FLAGS.restore:
train_spec["restore"] = FLAGS.restore
ray.init(
webui_host='127.0.0.1',
# plasma_directory="/dev/shm/",
# memory=1024 * 1024 * 1024 * 25, # setting 25 GB for ray workers
# object_store_memory=1024 * 1024 * 1024 * 5, # setting 5 GB object store
# lru_evict=True
)
# copy code to local_dir
code_dir = os.path.join(os.path.abspath(os.getcwd()), 'pba')
dst_dir = os.path.join(FLAGS.local_dir, FLAGS.name, 'pba')
if os.path.exists(dst_dir):
shutil.rmtree(dst_dir) # remove old copy of code
shutil.copytree(code_dir, dst_dir)
run_experiments({FLAGS.name: train_spec})
ray.shutdown()
def main(_):
args = create_parser() # pylint: disable=invalid-name
hparams = create_hparams("train", args)
train_spec = {
"run": RayModel,
"resources_per_trial": {
"cpu": args.cpu,
"gpu": args.gpu
},
"stop": {
"training_iteration": hparams.num_epochs,
},
"config": hparams.values(),
"local_dir": args.local_dir,
"checkpoint_freq": args.checkpoint_freq,
"num_samples": 1
}
if args.restore:
train_spec["restore"] = args.restore
ray.init()
run_experiments({args.train_name: train_spec})
def main(_):
FLAGS = create_parser("search") # pylint: disable=invalid-name
hparams = create_hparams("search", FLAGS)
hparams_config = hparams.values()
train_spec = {
"run": RayModel,
"resources_per_trial": {
"cpu": FLAGS.cpu,
"gpu": FLAGS.gpu
},
"stop": {
"training_iteration": hparams.num_epochs,
},
"config": hparams_config,
"local_dir": FLAGS.local_dir,
"checkpoint_freq": FLAGS.checkpoint_freq,
"num_samples": FLAGS.num_samples
}
if FLAGS.restore:
train_spec["restore"] = FLAGS.restore
def explore(config):
"""Custom explore function.
Args:
config: dictionary containing ray config params.
Returns:
Copy of config with modified augmentation policy.
"""
new_params = []
if config["explore"] == "cifar10":
for i, param in enumerate(config["hp_policy"]):
if random.random() < 0.2:
if i % 2 == 0:
new_params.append(random.randint(0, 10))
else:
new_params.append(random.randint(0, 9))
else:
amt = np.random.choice([0, 1, 2, 3],
p=[0.25, 0.25, 0.25, 0.25])
# Cast np.int64 to int for py3 json
amt = int(amt)
if random.random() < 0.5:
new_params.append(max(0, param - amt))
else:
if i % 2 == 0:
new_params.append(min(10, param + amt))
else:
new_params.append(min(9, param + amt))
else:
raise ValueError()
config["hp_policy"] = new_params
return config
ray.init()
pbt = PopulationBasedTraining(
time_attr="training_iteration",
reward_attr="val_acc",
perturbation_interval=FLAGS.perturbation_interval,
custom_explore_fn=explore,
log_config=True)
run_experiments({FLAGS.name: train_spec},
scheduler=pbt,
reuse_actors=True,
verbose=True)
def main(_):
FLAGS = create_parser("search") # pylint: disable=invalid-name
hparams = create_hparams("search", FLAGS)
hparams_config = hparams.values()
train_spec = {
"run": RayModel,
"resources_per_trial": {
"cpu": FLAGS.cpu,
"gpu": FLAGS.gpu
},
"stop": {
"training_iteration": hparams.num_epochs,
},
"config": hparams_config,
"local_dir": FLAGS.local_dir,
"checkpoint_freq": FLAGS.checkpoint_freq,
"num_samples": FLAGS.num_samples
}
if FLAGS.restore:
train_spec["restore"] = FLAGS.restore
def explore(config):
"""
Custom explore function based on cifar10 from PBA paper
Args:
config: dictionary containing ray config params.
Returns:
Copy of config with modified augmentation policy.
"""
new_params = []
for i, param in enumerate(config["hp_policy"]):
if random.random() < 0.2:
if i % 2 == 0:
new_params.append(random.randint(0, 10))
else:
new_params.append(random.randint(0, 9))
else:
amt = np.random.choice([0, 1, 2, 3],
p=[0.25, 0.25, 0.25, 0.25])
# Cast np.int64 to int for py3 json
amt = int(amt)
if random.random() < 0.5:
new_params.append(max(0, param - amt))
else:
if i % 2 == 0:
new_params.append(min(10, param + amt))
else:
new_params.append(min(9, param + amt))
config["hp_policy"] = new_params
return config
ray.init(
webui_host='127.0.0.1',
# memory=1024 * 1024 * 1024 * 20, # setting 20 GB for ray workers
# object_store_memory=1024 * 1024 * 1024 * 30,
# lru_evict=True
)
# copy code to local_dir
code_dir = os.path.join(os.path.abspath(os.getcwd()), 'pba')
dst_dir = os.path.join(FLAGS.local_dir, FLAGS.name, 'pba')
if os.path.exists(dst_dir):
shutil.rmtree(dst_dir) # remove old copy of code
shutil.copytree(code_dir, dst_dir)
pbt = PopulationBasedTraining(
time_attr="training_iteration",
reward_attr='abs_rel_acc',
# metric="abs_rel",
# mode="min",
perturbation_interval=FLAGS.perturbation_interval,
custom_explore_fn=explore,
quantile_fraction=0.50,
log_config=True)
run_experiments({FLAGS.name: train_spec},
scheduler=pbt,
reuse_actors=True,
verbose=True)
ray.shutdown()