def __init__(self, data_path, year='2012', cache=None, **kargs):
with FileLock('voc.lock', timeout=option('download.lock.timeout', 4 * 60, type=int)):
train_dataset = torchvision.datasets.VOCSegmentation(
root=data_path, year=year, image_set='train', download=True,
transforms=UserTransform())
with FileLock('voc.lock', timeout=option('download.lock.timeout', 4 * 60, type=int)):
test_dataset = torchvision.datasets.VOCSegmentation(
root=data_path, year=year, image_set='val', download=True,
transforms=UserTransform())
dataset = DatasetPaddingWrapper(
torch.utils.data.ConcatDataset([train_dataset, test_dataset]))
if cache:
dataset = DatasetCache(dataset, cache)
if 'train_size' not in kargs:
kargs['train_size'] = len(train_dataset)
if 'valid_size' not in kargs:
kargs['valid_size'] = len(test_dataset)//2
if 'test_size' not in kargs:
kargs['test_size'] = len(test_dataset)//2 + len(test_dataset)%2
super(PascalVOC, self).__init__(
dataset,
**kargs,
)
def __init__(self,
uri,
database,
id,
experiment=None,
hpo_allowed=True,
work_allowed=True,
log_capture=False):
super(TrialWorker, self).__init__(uri, database, experiment, id,
WORK_QUEUE, RESULT_QUEUE)
self.namespaced = experiment is not None
self.client.capture = log_capture
if work_allowed:
self.new_handler(WORK_ITEM, self.run_trial)
if hpo_allowed:
self.new_handler(HPO_ITEM, self.run_hpo)
self.new_handler(WORKER_JOIN, self.ignore_message)
self.timeout = option('worker.timeout', 5 * 60, type=int)
self.max_retry = option('worker.max_retry', 3, type=int)
self.backoff = dict()
# Disable shutting down when receiving shut down
if experiment is None:
info(f'Disabling message shutdown because {experiment}')
self.dispatcher[SHUTDOWN] = lambda *args, **kwargs: print(
'ignoring shutdown signal')
def __init__(self, data_path):
transformations = [
transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))]
train_transform = [
to_pil_image,
transforms.RandomCrop(32, padding=4),
transforms.RandomHorizontalFlip(),
transforms.ToTensor()] + transformations
transformations = dict(
train=transforms.Compose(train_transform),
valid=transforms.Compose(transformations),
test=transforms.Compose(transformations))
with FileLock('cifar100.lock', timeout=option('download.lock.timeout', 4 * 60, type=int)):
train_dataset = datasets.CIFAR100(root=data_path, train=True, download=True, transform=transforms.ToTensor())
with FileLock('cifar100.lock', timeout=option('download.lock.timeout', 4 * 60, type=int)):
test_dataset = datasets.CIFAR100(root=data_path, train=False, download=True, transform=transforms.ToTensor())
super(CIFAR100, self).__init__(
torch.utils.data.ConcatDataset([train_dataset, test_dataset]),
test_size=len(test_dataset),
transforms=transformations
)
def __init__(self,
data_path,
transform=True,
transform_seed=0,
cache=None):
transformations = [
transforms.Normalize((0.4914, 0.4822, 0.4465),
(0.2023, 0.1994, 0.2010))
]
rng = numpy.random.RandomState(transform_seed)
if transform:
train_transform = [
to_pil_image,
RandomCrop(32, padding=4, seed=rng.randint(2**30)),
RandomHorizontalFlip(seed=rng.randint(2**30)),
transforms.ToTensor()
] + transformations
else:
train_transform = transformations
transformations = dict(train=Compose(train_transform),
valid=Compose(transformations),
test=Compose(transformations))
with FileLock('cifar10.lock',
timeout=option('download.lock.timeout', 4 * 60,
type=int)):
train_dataset = datasets.CIFAR10(root=data_path,
train=True,
download=True,
transform=transforms.ToTensor())
with FileLock('cifar10.lock',
timeout=option('download.lock.timeout', 4 * 60,
type=int)):
test_dataset = datasets.CIFAR10(root=data_path,
train=False,
download=True,
transform=transforms.ToTensor())
super(CIFAR10, self).__init__(torch.utils.data.ConcatDataset(
[train_dataset, test_dataset]),
test_size=len(test_dataset),
transforms=transformations)
def __init__(self,
data_path,
mini=False,
train_size=None,
valid_size=None,
test_size=None,
input_shape=None,
target_shape=None,
**kwargs):
transformations = [transforms.Normalize((0.1307, ), (0.3081, ))]
if mini:
transformations.insert(0, minimize(7))
transform = transforms.Compose(transformations)
with FileLock('mnist.lock',
timeout=option('download.lock.timeout', 4 * 60,
type=int)):
train_dataset = datasets.MNIST(data_path,
train=True,
download=True,
transform=transforms.ToTensor())
with FileLock('mnist.lock',
timeout=option('download.lock.timeout', 4 * 60,
type=int)):
test_dataset = datasets.MNIST(data_path,
train=False,
download=True,
transform=transforms.ToTensor())
if test_size is None:
test_size = len(test_dataset)
super(MNIST, self).__init__(torch.utils.data.ConcatDataset(
[train_dataset, test_dataset]),
test_size=test_size,
train_size=train_size,
valid_size=valid_size,
transforms=transform,
input_shape=input_shape,
target_shape=target_shape)
def __init__(self, data_path):
with FileLock('SVHN.lock',
timeout=option('download.lock.timeout', 4 * 60,
type=int)):
train_dataset = datasets.SVHN(data_path,
split='train',
download=True,
transform=transforms.ToTensor())
with FileLock('SVHN.lock',
timeout=option('download.lock.timeout', 4 * 60,
type=int)):
test_dataset = datasets.SVHN(data_path,
split='test',
download=True,
transform=transforms.ToTensor())
super(SVHN, self).__init__(torch.utils.data.ConcatDataset(
[train_dataset, test_dataset]),
test_size=len(test_dataset))
def dashboard():
"""Dashboard entry point for Olympus user"""
from msgqueue.backends import new_monitor
parser = ArgumentParser()
parser.add_argument(
'--uri',
type=str,
default='mongo://127.0.0.1:27017',
help='URI pointing to the resource to connect to\n'
'Examples:\n'
' - mongodb instance: mongo://127.0.0.1:27017\n'
' - cockroach db instance cockroach://0.0.0.0:8123\n'
' - local archive: zip:/home/setepenre/work/olympus/data.zip\n')
parser.add_argument('--database',
type=str,
default='olympus',
help='Name of the database')
parser.add_argument('--storage',
type=str,
default=option('state.storage',
'/home/setepenre/zshare/tmp'),
help='FS path to storage')
args = parser.parse_args()
dash = Dashboard()
client = new_monitor(args.uri, args.database)
state_storage = StateStorage(folder=args.storage)
navbar = html.navbar(
Experiments='/experiment',
Studies='/study',
States='/state/browse',
Debug='/',
)
dash.add_page(MainPage(dash), header=navbar)
dash.add_page(StatusQueue(client), header=navbar)
dash.add_page(InspectQueue(client), header=navbar)
dash.add_page(ResultQueue(client), header=navbar)
dash.add_page(GanttQueue(client), header=navbar)
dash.add_page(SpaceQueue(client), header=navbar)
dash.add_page(FANVOAQueue(client), header=navbar)
dash.add_page(LogsQueue(client), header=navbar)
dash.add_page(MetricQueue(client), header=navbar)
dash.add_page(ExperimentOverview(client), header=navbar)
dash.add_page(StudyOverview(client), header=navbar)
dash.add_page(StateBrowser(state_storage), header=navbar)
dash.add_page(InspectModel(state_storage), header=navbar)
return dash
def __init__(self, data_path):
with FileLock('FashionMNIST.lock',
timeout=option('download.lock.timeout', 4 * 60,
type=int)):
train_dataset = datasets.FashionMNIST(
data_path,
train=True,
download=True,
transform=transforms.ToTensor())
with FileLock('FashionMNIST.lock',
timeout=option('download.lock.timeout', 4 * 60,
type=int)):
test_dataset = datasets.FashionMNIST(
data_path,
train=False,
download=True,
transform=transforms.ToTensor())
super(FashionMNIST, self).__init__(torch.utils.data.ConcatDataset(
[train_dataset, test_dataset]),
test_size=len(test_dataset))
def build_dataset(data_path, timeout=10 * 60):
if all_hdf5_exists(data_path):
return
try:
with FileLock(os.path.join(data_path, DIRNAME + ".lock"), timeout=option('download.lock.timeout', timeout, type=int)):
download(data_path)
unzip(data_path)
create_hdf5(data_path)
except Timeout:
print("Another process holds the lock since more than {} seconds. "
"Will try to load the dataset.").format(timeout)
finally:
clean(data_path)
def __init__(self,
name=None,
dataset=None,
path=option('data.path', default='/tmp/olympus/data'),
**kwargs):
if dataset is not None:
self.dataset = dataset
elif name is not None:
dataset_ctor = registered_datasets.get(name)
if dataset_ctor is None:
raise RegisteredDatasetNotFound(name)
self.dataset = dataset_ctor(data_path=path, **kwargs)
else:
raise MissingArgument('Dataset or Name need to be set')
def __call__(self, input_size, output_size, attention_probs_dropout_prob,
hidden_dropout_prob):
cache_dir = option('model.cache', '/tmp/olympus/cache')
info('model cache folder: {}'.format(cache_dir))
config = BertConfig.from_pretrained('bert-base-uncased',
num_labels=2,
finetuning_task=self.task,
cache_dir=cache_dir)
config.attention_probs_dropout_prob = attention_probs_dropout_prob
config.hidden_dropout_prob = hidden_dropout_prob
model = BertWrapper.from_pretrained('bert-base-uncased',
from_tf=False,
config=config,
cache_dir=cache_dir)
return model
def __init__(self,
data_path,
transforms=None,
target_transforms=None,
download=True):
self.root = data_path
if download:
with FileLock('penndufan.lock',
timeout=option('download.lock.timeout',
4 * 60,
type=int)):
self.download()
self.transforms = transforms
self.target_transforms = target_transforms
# load all image files, sorting them to
# ensure that they are aligned
self.imgs = list(sorted(os.listdir(self.images_path)))
self.masks = list(sorted(os.listdir(self.masks_path)))
def __init__(self,
hpo,
rank,
uri,
experiment,
database=option('olympus.database', 'olympus')):
self.hpo = hpo
self.experiment = experiment
self.client = new_client(uri, database)
self.current_message = None
# check that HPO is not finished
state = self._fetch_final_state()
if state is not None:
raise ExperimentFinished(
f'Experiment `{experiment}` is finished, change the experiment name'
)
# first worker queue HPO
if rank == 0:
self._queue_hpo()
# broadcast that one worker is joining
self.client.push(RESULT_QUEUE, self.experiment, {}, mtype=WORKER_JOIN)
import torch
from olympus.datasets import SplitDataset, Dataset, DataLoader
from olympus.datasets.decorator.window import WindowedDataset
from olympus.metrics import Loss
from olympus.models import Model
from olympus.optimizers import Optimizer, known_optimizers
from olympus.tasks.finance import Finance, SharpeRatioCriterion
from olympus.utils import option, fetch_device, show_hyperparameter_space, parse_args
from olympus.observers import metric_logger, CheckPointer
from olympus.utils.storage import StateStorage
DEFAULT_EXP_NAME = 'finance'
base = option('base_path', '/media/setepenre/local/')
def arguments():
parser = ArgumentParser(prog='finance',
description='Finance Baseline',
epilog=show_hyperparameter_space(),
formatter_class=RawDescriptionHelpFormatter)
parser.add_argument('--uri',
type=str,
default=None,
help='Resource to use to store metrics')
parser.add_argument('--database',
type=str,
import torch.nn.functional as F
from olympus.datasets import Dataset, SplitDataset, DataLoader
from olympus.optimizers import Optimizer, LRSchedule
from olympus.models import Model
from olympus.observers import ObserverList, ProgressView, Speed
from olympus.utils import fetch_device, option
epochs = 2
device = fetch_device()
base = option('base_path', '/tmp/olympus')
# Model
model = Model('resnet18', input_size=(1, 28, 28), output_size=(10, ))
# Optimizer
optimizer = Optimizer('sgd',
params=model.parameters(),
weight_decay=0.001,
lr=1e-5,
momentum=1e-5)
# Schedule
lr_schedule = LRSchedule('exponential', optimizer=optimizer, gamma=0.99)
data = Dataset('fake_mnist', path=f'{base}/data')
splits = SplitDataset(data, split_method='original')
# Dataloader
loader = DataLoader(splits, sampler_seed=1, batch_size=32)
from olympus.datasets import Dataset, SplitDataset, DataLoader
from olympus.utils import option, new_seed, get_seeds
from argparse import ArgumentParser
parser = ArgumentParser()
parser.add_argument('dataset', type=str, help='name of the dataset to load')
args = parser.parse_args()
# can be customized using OLYMPUS_BASE_PATH or Olympus configuration file if found
base = option('data.path', '/tmp/olympus')
# get the dataset
dataset = Dataset(args.dataset, path=f'{base}/data')
# How to split the dataset
splits = SplitDataset(dataset, split_method='original')
# DataLoader builder
loader = DataLoader(splits, sampler_seed=new_seed(sampler=1), batch_size=32)
# Train my model
for step, batch in enumerate(loader.train()):
print('\rTrain:', step, len(batch), end='')
print()
# Using a bigger batch size when gradient is not computed
for step, batch in enumerate(loader.valid(batch_size=1024)):
print('\rValid:', step, len(batch), end='')
print()
for step, batch in enumerate(loader.test(batch_size=1024)):
def main():
from sspace.space import compute_identity
args = arguments()
tickers = [
# 1 2 3 4 5 6 7 8 9 10
'MO',
'AEP',
'BA',
'BMY',
'CPB',
'CAT',
'CVX',
'KO',
'CL',
'COP', # 1
'ED',
'CVS',
'DHI',
'DHR',
'DRI',
'DE',
'D',
'DTE',
'ETN',
'EBAY', # 2
'F',
'BEN',
'HSY',
'HBAN',
'IBM',
'K',
'GIS',
'MSI',
'NSC',
'TXN'
]
start, end = '2000-01-01', '2019-05-10'
device = fetch_device()
task = finance_baseline(tickers, start, end, args.optimizer,
args.batch_size, device, args.window)
lr = 1e-8
uid = compute_identity(
dict(tickers=tickers,
start=start,
end=end,
window=args.window,
lr=lr,
epochs=args.epochs), 16)
if args.uri is not None:
logger = metric_logger(args.uri, args.database,
f'{DEFAULT_EXP_NAME}_{uid}')
task.metrics.append(logger)
if args.storage is not None:
storage = StateStorage(
folder=option('state.storage', '/home/setepenre/zshare/tmp'))
task.metrics.append(
CheckPointer(storage=storage,
time_buffer=5,
keep_best='validation_loss',
save_init=True))
optimizer = task.optimizer.defaults
optimizer['lr'] = lr
task.init(optimizer=optimizer, uid=uid)
task.fit(args.epochs)
stats = task.metrics.value()
print(stats)
return float(stats['validation_loss'])