def config():
debug = False
batch_size = 6
train_dataset = "mix_2_spk_min_tr"
validate_dataset = "mix_2_spk_min_cv"
# Start with an empty dict to allow tracking by Sacred
trainer = {
"model": {
"factory": pt.models.bss.PermutationInvariantTrainingModel,
"dropout_input": 0.,
"dropout_hidden": 0.,
"dropout_linear": 0.
},
"storage_dir": None,
"optimizer": {
"factory": pt.optimizer.Adam,
"gradient_clipping": 1
},
"summary_trigger": (1000, "iteration"),
"stop_trigger": (300_000, "iteration"),
"loss_weights": {
"pit_ips_loss": 1.0,
"pit_mse_loss": 0.0,
}
}
pt.Trainer.get_config(trainer)
if trainer['storage_dir'] is None:
trainer['storage_dir'] = get_new_folder(path_template, mkdir=False)
ex.observers.append(
FileStorageObserver.create(Path(trainer['storage_dir']) / 'sacred'))
def test_fs_observer_equality(dir_obs):
basedir, obs = dir_obs
obs2 = FileStorageObserver.create(obs.basedir)
assert obs == obs2
assert not obs != obs2
assert not obs == "foo"
assert obs != "foo"
def test_fs_observer_equality(dir_obs):
basedir, obs = dir_obs
obs2 = FileStorageObserver.create(obs.basedir)
assert obs == obs2
assert not obs != obs2
assert not obs == 'foo'
assert obs != 'foo'
def test_fs_observer_resource_event_does_not_duplicate(dir_obs, sample_run, tmpfile):
basedir, obs = dir_obs
obs2 = FileStorageObserver.create(obs.basedir)
obs.started_event(**sample_run)
obs.resource_event(tmpfile.name)
# let's have another run from a different observer
sample_run["_id"] = None
_id = obs2.started_event(**sample_run)
run_dir = basedir.join(str(_id))
obs2.resource_event(tmpfile.name)
res_dir = basedir.join("_resources")
assert res_dir.exists()
assert len(res_dir.listdir()) == 1
assert res_dir.listdir()[0].read() == tmpfile.content
run = json.loads(run_dir.join("run.json").read())
assert len(run["resources"]) == 1
assert run["resources"][0] == [tmpfile.name, res_dir.listdir()[0].strpath]
def test_fs_observer_resource_event_does_not_duplicate(dir_obs, sample_run,
tmpfile):
basedir, obs = dir_obs
obs2 = FileStorageObserver.create(obs.basedir)
obs.started_event(**sample_run)
obs.resource_event(tmpfile.name)
# let's have another run from a different observer
sample_run['_id'] = None
_id = obs2.started_event(**sample_run)
run_dir = basedir.join(str(_id))
obs2.resource_event(tmpfile.name)
res_dir = basedir.join('_resources')
assert res_dir.exists()
assert len(res_dir.listdir()) == 1
assert res_dir.listdir()[0].read() == tmpfile.content
run = json.loads(run_dir.join('run.json').read())
assert len(run['resources']) == 1
assert run['resources'][0] == [tmpfile.name, res_dir.listdir()[0].strpath]
def config():
debug = False
batch_size = 6
database_json = "" # Path to WSJ0_2mix .json
if "WSJ0_2MIX" in os.environ:
database_json = os.environ.get("WSJ0_2MIX")
assert len(database_json) > 0, 'Set path to database Json on the command line or set environment variable WSJ0_2MIX'
train_dataset = "mix_2_spk_min_tr"
validate_dataset = "mix_2_spk_min_cv"
# dict describing the model parameters, to allow changing the paramters from the command line.
# Configurable automatically inserts default values of not mentioned parameters to the config.json
trainer = {
"model": {
"factory": pt.contrib.examples.pit.model.PermutationInvariantTrainingModel,
"dropout_input": 0.,
"dropout_hidden": 0.,
"dropout_linear": 0.
},
"storage_dir": None,
"optimizer": {
"factory": pt.optimizer.Adam,
"gradient_clipping": 1
},
"summary_trigger": (1000, "iteration"),
"stop_trigger": (300_000, "iteration"),
"loss_weights": {
"pit_ips_loss": 1.0,
"pit_mse_loss": 0.0,
}
}
pt.Trainer.get_config(trainer)
if trainer['storage_dir'] is None:
trainer['storage_dir'] = get_new_folder(path_template, mkdir=False)
ex.observers.append(FileStorageObserver.create(
Path(trainer['storage_dir']) / 'sacred')
)
def test_observer_equality(tmpdir):
observer_1 = FileStorageObserver.create(str(tmpdir / "a"))
observer_2 = FileStorageObserver.create(str(tmpdir / "b"))
observer_3 = FileStorageObserver.create(str(tmpdir / "a"))
assert observer_1 == observer_3
assert observer_1 != observer_2
def dir_obs(tmpdir):
basedir = tmpdir.join("file_storage")
return basedir, FileStorageObserver.create(basedir.strpath)
def dir_obs(tmpdir):
basedir = tmpdir.join('file_storage')
return basedir, FileStorageObserver.create(basedir.strpath)
def dir_obs(tmpdir):
return tmpdir, FileStorageObserver.create(tmpdir.strpath)
import sacred
from sacred.utils import apply_backspaces_and_linefeeds
from sacred.observers.file_storage import FileStorageObserver
GRAMTOOLS_INSTALL_PATH = '/home/robyn/Documents/gramtools'
GENERATE_PRG_SCRIPT_PATH = os.path.join(GRAMTOOLS_INSTALL_PATH,
'utils/vcf_to_linear_prg.pl')
GENERATE_KMERS_SCRIPT_PATH = os.path.join(GRAMTOOLS_INSTALL_PATH,
'utils/variantKmers.py')
MAP_READS_PATH = os.path.join(GRAMTOOLS_INSTALL_PATH, 'bin', 'gramtools')
experiment = sacred.Experiment()
experiment.captured_out_filter = apply_backspaces_and_linefeeds
file_observer = FileStorageObserver.create('gramtools_runs')
file_observer.save_sources = lambda x: None
experiment.observers.append(file_observer)
def generate_paths(vcf_path, fasta_path):
"""Generate and return all file paths associated with experiment."""
vcf_path = os.path.abspath(vcf_path)
file_observer.run_entry['artifacts'].append(vcf_path)
fasta_path = os.path.abspath(fasta_path)
file_observer.run_entry['artifacts'].append(fasta_path)
run_path = os.path.abspath(file_observer.dir)
data_path = os.path.join(run_path, 'data')
def dir_obs(tmpdir):
return tmpdir, FileStorageObserver.create(tmpdir.strpath)