def test_mlflow_logger(tmpdir):
"""Verify that basic functionality of mlflow logger works."""
tutils.reset_seed()
try:
from pytorch_lightning.logging import MLFlowLogger
except ModuleNotFoundError:
return
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
mlflow_dir = os.path.join(tmpdir, "mlruns")
logger = MLFlowLogger("test",
tracking_uri=f"file:{os.sep * 2}{mlflow_dir}")
trainer_options = dict(default_save_path=tmpdir,
max_epochs=1,
train_percent_check=0.01,
logger=logger)
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
print('result finished')
assert result == 1, "Training failed"
def test_mlflow_logger():
"""
verify that basic functionality of mlflow logger works
"""
reset_seed()
try:
from pytorch_lightning.logging import MLFlowLogger
except ModuleNotFoundError:
return
hparams = testing_utils.get_hparams()
model = LightningTestModel(hparams)
root_dir = os.path.dirname(os.path.realpath(__file__))
mlflow_dir = os.path.join(root_dir, "mlruns")
logger = MLFlowLogger("test", f"file://{mlflow_dir}")
trainer_options = dict(
max_nb_epochs=1,
train_percent_check=0.01,
logger=logger
)
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
print('result finished')
assert result == 1, "Training failed"
testing_utils.clear_save_dir()
def test_mlflow_pickle():
"""
verify that pickling trainer with mlflow logger works
"""
reset_seed()
try:
from pytorch_lightning.logging import MLFlowLogger
except ModuleNotFoundError:
return
hparams = testing_utils.get_hparams()
model = LightningTestModel(hparams)
root_dir = os.path.dirname(os.path.realpath(__file__))
mlflow_dir = os.path.join(root_dir, "mlruns")
logger = MLFlowLogger("test", f"file://{mlflow_dir}")
trainer_options = dict(
max_nb_epochs=1,
logger=logger
)
trainer = Trainer(**trainer_options)
pkl_bytes = pickle.dumps(trainer)
trainer2 = pickle.loads(pkl_bytes)
trainer2.logger.log_metrics({"acc": 1.0})
testing_utils.clear_save_dir()
def test_mlflow_logger():
"""
verify that basic functionality of mlflow logger works
"""
reset_seed()
try:
from pytorch_lightning.logging import MLFlowLogger
except ModuleNotFoundError:
return
hparams = get_hparams()
model = LightningTestModel(hparams)
root_dir = os.path.dirname(os.path.realpath(__file__))
mlflow_dir = os.path.join(root_dir, "mlruns")
logger = MLFlowLogger("test", f"file://{mlflow_dir}")
logger.log_hyperparams(hparams)
logger.save()
trainer_options = dict(max_nb_epochs=1,
train_percent_check=0.01,
logger=logger)
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
assert result == 1, "Training failed"
n = RANDOM_FILE_PATHS.pop()
shutil.move(mlflow_dir, mlflow_dir + f'_{n}')
def command_execute(hparams, experiment_name):
# Check if the task if already finished
flag = check_finish(hparams, experiment_name)
if flag and not hparams.F:
logging.info("The task has been already finished or running")
logging.info("Skip this run")
logging.info(hparams)
else:
logging.info("Execute this run")
logging.info(hparams)
random.seed(hparams.seed)
torch.manual_seed(hparams.seed)
torch.cuda.manual_seed(hparams.seed)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
# Parameters
print("Build model...")
model = DomainGeneralization(hparams)
mlf_logger = MLFlowLogger(experiment_name=EXPERIMENT_NAME)
# mlf_logger = MLFlowLogger(experiment_name=EXPERIMENT_NAME, tracking_uri="s3://log")
logging.info("MLF Run ID: {}".format(mlf_logger.run_id))
if hparams.S is True:
checkpoint = ModelCheckpoint(
filepath=os.path.join(os.getcwd(), EXPERIMENT_NAME,
str(mlf_logger.run_id)),
save_top_k=-1,
)
trainer = pl.Trainer(mlf_logger,
gpus=1,
max_epochs=hparams.epoch,
early_stop_callback=False,
checkpoint_callback=checkpoint)
else:
trainer = pl.Trainer(mlf_logger,
gpus=1,
max_epochs=hparams.epoch,
early_stop_callback=False)
trainer.fit(model)
trainer.test()
print(model.test_result)
def test_mlflow_pickle(tmpdir):
"""Verify that pickling trainer with mlflow logger works."""
tutils.reset_seed()
try:
from pytorch_lightning.logging import MLFlowLogger
except ModuleNotFoundError:
return
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
mlflow_dir = os.path.join(tmpdir, "mlruns")
logger = MLFlowLogger("test", f"file://{mlflow_dir}")
trainer_options = dict(max_num_epochs=1, logger=logger)
trainer = Trainer(**trainer_options)
pkl_bytes = pickle.dumps(trainer)
trainer2 = pickle.loads(pkl_bytes)
trainer2.logger.log_metrics({"acc": 1.0})