def s3_get((bucket, source, destin)):
import boto
try:
print 'starting {}'.format(source)
conn = boto.connect_s3().get_bucket(bucket)
key = conn.get_key(source)
key.get_contents_to_filename(destin)
print 'finished {}'.format(source)
except:
rm_rf(destin)
raise
def s3_get((bucket, source, destin)):
import boto
try:
print 'starting {}'.format(source)
conn = boto.connect_s3().get_bucket(bucket)
key = conn.get_key(source)
key.get_contents_to_filename(destin)
print 'finished {}'.format(source)
except:
rm_rf(destin)
raise
def load_checkpoint(name=None, period_sec=5, debug=False):
'''
Grab last full checkpoint for profiling, or list available datasets.
'''
loom.store.require(name, ['samples.0.init', 'samples.0.shuffled'])
inputs, results = get_paths(name, 'checkpoints')
rm_rf(results['root'])
mkdir_p(results['root'])
with chdir(results['root']):
config = {'schedule': {'checkpoint_period_sec': period_sec}}
loom.config.config_dump(config, results['samples'][0]['config'])
# run first iteration
step = 0
mkdir_p(str(step))
kwargs = checkpoint_files(step, '_out')
print 'running checkpoint {}, tardis_iter 0'.format(step)
loom.runner.infer(
config_in=results['samples'][0]['config'],
rows_in=inputs['samples'][0]['shuffled'],
tares_in=inputs['ingest']['tares'],
model_in=inputs['samples'][0]['init'],
log_out=results['samples'][0]['infer_log'],
debug=debug,
**kwargs)
checkpoint = _load_checkpoint(step)
# find penultimate checkpoint
while not checkpoint.finished:
rm_rf(str(step - 3))
step += 1
print 'running checkpoint {}, tardis_iter {}'.format(
step,
checkpoint.tardis_iter)
kwargs = checkpoint_files(step - 1, '_in')
mkdir_p(str(step))
kwargs.update(checkpoint_files(step, '_out'))
loom.runner.infer(
config_in=results['samples'][0]['config'],
rows_in=inputs['samples'][0]['shuffled'],
tares_in=inputs['ingest']['tares'],
log_out=results['samples'][0]['infer_log'],
debug=debug,
**kwargs)
checkpoint = _load_checkpoint(step)
print 'final checkpoint {}, tardis_iter {}'.format(
step,
checkpoint.tardis_iter)
last_full = str(step - 2)
assert os.path.exists(last_full), 'too few checkpoints'
checkpoint = _load_checkpoint(step)
print 'saving checkpoint {}, tardis_iter {}'.format(
last_full,
checkpoint.tardis_iter)
for f in checkpoint_files(last_full).values():
shutil.move(f, results['root'])
for f in glob.glob(os.path.join(results['root'], '[0-9]*/')):
shutil.rmtree(f)
def clean(name):
'''
Clean out one dataset.
'''
rm_rf(loom.store.get_paths(name)['root'])
def load_checkpoint(name=None, period_sec=5, debug=False):
'''
Grab last full checkpoint for profiling, or list available datasets.
'''
if name is None:
list_options_and_exit(MODEL)
rows = ROWS.format(name)
model = MODEL.format(name)
assert os.path.exists(model), 'First load dataset'
assert os.path.exists(rows), 'First load dataset'
destin = CHECKPOINTS.format(name)
rm_rf(destin)
mkdir_p(os.path.dirname(destin))
def load_checkpoint(name):
checkpoint = loom.schema_pb2.Checkpoint()
with open_compressed(checkpoint_files(name)['checkpoint']) as f:
checkpoint.ParseFromString(f.read())
return checkpoint
with tempdir(cleanup_on_error=(not debug)):
config = {'schedule': {'checkpoint_period_sec': period_sec}}
config_in = os.path.abspath('config.pb.gz')
loom.config.config_dump(config, config_in)
# run first iteration
step = 0
mkdir_p(str(step))
kwargs = checkpoint_files(str(step), '_out')
print 'running checkpoint {}, tardis_iter 0'.format(step)
loom.runner.infer(
config_in=config_in,
rows_in=rows,
model_in=model,
debug=debug,
**kwargs)
checkpoint = load_checkpoint(step)
# find penultimate checkpoint
while not checkpoint.finished:
rm_rf(str(step - 3))
step += 1
print 'running checkpoint {}, tarids_iter {}'.format(
step,
checkpoint.tardis_iter)
kwargs = checkpoint_files(step - 1, '_in')
mkdir_p(str(step))
kwargs.update(checkpoint_files(step, '_out'))
loom.runner.infer(
config_in=config_in,
rows_in=rows,
debug=debug,
**kwargs)
checkpoint = load_checkpoint(step)
print 'final checkpoint {}, tardis_iter {}'.format(
step,
checkpoint.tardis_iter)
last_full = str(step - 2)
assert os.path.exists(last_full), 'too few checkpoints'
checkpoint = load_checkpoint(step)
print 'saving checkpoint {}, tardis_iter {}'.format(
last_full,
checkpoint.tardis_iter)
shutil.move(last_full, destin)
def clean(name):
'''
Clean out one dataset.
'''
rm_rf(loom.store.get_paths(name)['root'])
