def test_model_freeze_unfreeze():
tutils.reset_seed()
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
model.freeze()
model.unfreeze()
def test_model_saving_loading():
"""
Tests use case where trainer saves the model, and user loads it from tags independently
:return:
"""
reset_seed()
hparams = get_hparams()
model = LightningTestModel(hparams)
save_dir = init_save_dir()
# logger file to get meta
logger = get_test_tube_logger(False)
logger.log_hyperparams(hparams)
logger.save()
trainer_options = dict(max_nb_epochs=1,
logger=logger,
checkpoint_callback=ModelCheckpoint(save_dir))
# fit model
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
# traning complete
assert result == 1, 'amp + ddp model failed to complete'
# make a prediction
for dataloader in model.test_dataloader():
for batch in dataloader:
break
x, y = batch
x = x.view(x.size(0), -1)
# generate preds before saving model
model.eval()
pred_before_saving = model(x)
# save model
new_weights_path = os.path.join(save_dir, 'save_test.ckpt')
trainer.save_checkpoint(new_weights_path)
# load new model
tags_path = logger.experiment.get_data_path(logger.experiment.name,
logger.experiment.version)
tags_path = os.path.join(tags_path, 'meta_tags.csv')
model_2 = LightningTestModel.load_from_metrics(
weights_path=new_weights_path, tags_csv=tags_path)
model_2.eval()
# make prediction
# assert that both predictions are the same
new_pred = model_2(x)
assert torch.all(torch.eq(pred_before_saving, new_pred)).item() == 1
clear_save_dir()
def get_model(use_test_model=False):
# set up model with these hyperparams
hparams = get_hparams()
if use_test_model:
model = LightningTestModel(hparams)
else:
model = LightningTemplateModel(hparams)
return model, hparams
def get_model(use_test_model=False, lbfgs=False):
# set up model with these hyperparams
hparams = get_hparams()
if lbfgs:
setattr(hparams, 'optimizer_name', 'lbfgs')
if use_test_model:
model = LightningTestModel(hparams)
else:
model = LightningTemplateModel(hparams)
return model, hparams
def test_running_test_pretrained_model_ddp():
"""Verify test() on pretrained model"""
if not can_run_gpu_test():
return
reset_seed()
set_random_master_port()
hparams = get_hparams()
model = LightningTestModel(hparams)
save_dir = init_save_dir()
# exp file to get meta
logger = get_test_tube_logger(False)
# exp file to get weights
checkpoint = init_checkpoint_callback(logger)
trainer_options = dict(show_progress_bar=False,
max_nb_epochs=1,
train_percent_check=0.4,
val_percent_check=0.2,
checkpoint_callback=checkpoint,
logger=logger,
gpus=[0, 1],
distributed_backend='ddp')
# fit model
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
exp = logger.experiment
print(os.listdir(exp.get_data_path(exp.name, exp.version)))
# correct result and ok accuracy
assert result == 1, 'training failed to complete'
pretrained_model = load_model(logger.experiment,
save_dir,
module_class=LightningTestModel)
# run test set
new_trainer = Trainer(**trainer_options)
new_trainer.test(pretrained_model)
[
run_prediction(dataloader, pretrained_model)
for dataloader in model.test_dataloader()
]
# test we have good test accuracy
clear_save_dir()
def test_testtube_logger(tmpdir):
"""Verify that basic functionality of test tube logger works."""
tutils.reset_seed()
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
logger = tutils.get_test_tube_logger(tmpdir, False)
trainer_options = dict(max_num_epochs=1,
train_percent_check=0.01,
logger=logger)
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
assert result == 1, "Training failed"
def test_running_test_pretrained_model_ddp(tmpdir):
"""Verify `test()` on pretrained model."""
if not tutils.can_run_gpu_test():
return
tutils.reset_seed()
tutils.set_random_master_port()
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
# exp file to get meta
logger = tutils.get_test_tube_logger(tmpdir, False)
# exp file to get weights
checkpoint = tutils.init_checkpoint_callback(logger)
trainer_options = dict(
show_progress_bar=False,
max_epochs=1,
train_percent_check=0.4,
val_percent_check=0.2,
checkpoint_callback=checkpoint,
logger=logger,
gpus=[0, 1],
distributed_backend='ddp'
)
# fit model
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
exp = logger.experiment
logging.info(os.listdir(exp.get_data_path(exp.name, exp.version)))
# correct result and ok accuracy
assert result == 1, 'training failed to complete'
pretrained_model = tutils.load_model(logger.experiment,
trainer.checkpoint_callback.filepath,
module_class=LightningTestModel)
# run test set
new_trainer = Trainer(**trainer_options)
new_trainer.test(pretrained_model)
for dataloader in model.test_dataloader():
tutils.run_prediction(dataloader, pretrained_model)
def test_neptune_logger(tmpdir):
"""Verify that basic functionality of neptune logger works."""
tutils.reset_seed()
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
logger = NeptuneLogger(offline_mode=True)
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_tensorboard_logger(tmpdir):
"""Verify that basic functionality of Tensorboard logger works."""
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
logger = TensorBoardLogger(save_dir=tmpdir, name="tensorboard_logger_test")
trainer_options = dict(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_running_test_pretrained_model_ddp():
"""Verify test() on pretrained model"""
if not can_run_gpu_test():
return
hparams = get_hparams()
model = LightningTestModel(hparams)
save_dir = init_save_dir()
# exp file to get meta
exp = get_exp(False)
exp.argparse(hparams)
exp.save()
# exp file to get weights
checkpoint = ModelCheckpoint(save_dir)
trainer_options = dict(show_progress_bar=False,
max_nb_epochs=1,
train_percent_check=0.4,
val_percent_check=0.2,
checkpoint_callback=checkpoint,
experiment=exp,
gpus=[0, 1],
distributed_backend='ddp')
# fit model
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
# correct result and ok accuracy
assert result == 1, 'training failed to complete'
pretrained_model = load_model(exp,
save_dir,
on_gpu=True,
module_class=LightningTestModel)
# run test set
new_trainer = Trainer(**trainer_options)
new_trainer.test(pretrained_model)
run_prediction(model.test_dataloader, pretrained_model)
# test we have good test accuracy
clear_save_dir()
def test_testtube_pickle():
"""Verify that pickling a trainer containing a test tube logger works"""
hparams = get_hparams()
model = LightningTestModel(hparams)
save_dir = init_save_dir()
logger = get_test_tube_logger(False)
logger.log_hyperparams(hparams)
logger.save()
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})
def test_custom_logger(tmpdir):
class CustomLogger(LightningLoggerBase):
def __init__(self):
super().__init__()
self.hparams_logged = None
self.metrics_logged = None
self.finalized = False
@rank_zero_only
def log_hyperparams(self, params):
self.hparams_logged = params
@rank_zero_only
def log_metrics(self, metrics, step_num):
self.metrics_logged = metrics
@rank_zero_only
def finalize(self, status):
self.finalized_status = status
@property
def name(self):
return "name"
@property
def version(self):
return "1"
hparams = testing_utils.get_hparams()
model = LightningTestModel(hparams)
logger = CustomLogger()
trainer_options = dict(
max_nb_epochs=1,
train_percent_check=0.01,
logger=logger,
default_save_path=tmpdir
)
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
assert result == 1, "Training failed"
assert logger.hparams_logged == hparams
assert logger.metrics_logged != {}
assert logger.finalized_status == "success"
def test_running_test_pretrained_model_dp():
tutils.reset_seed()
"""Verify test() on pretrained model"""
if not tutils.can_run_gpu_test():
return
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
save_dir = tutils.init_save_dir()
# logger file to get meta
logger = tutils.get_test_tube_logger(False)
# logger file to get weights
checkpoint = tutils.init_checkpoint_callback(logger)
trainer_options = dict(
show_progress_bar=True,
max_nb_epochs=1,
train_percent_check=0.4,
val_percent_check=0.2,
checkpoint_callback=checkpoint,
logger=logger,
gpus=[0, 1],
distributed_backend='dp'
)
# fit model
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
# correct result and ok accuracy
assert result == 1, 'training failed to complete'
pretrained_model = tutils.load_model(logger.experiment,
trainer.checkpoint_callback.filepath,
module_class=LightningTestModel)
new_trainer = Trainer(**trainer_options)
new_trainer.test(pretrained_model)
# test we have good test accuracy
tutils.assert_ok_test_acc(new_trainer)
tutils.clear_save_dir()
def test_amp_single_gpu(tmpdir):
"""Make sure DDP + AMP work."""
tutils.reset_seed()
if not tutils.can_run_gpu_test():
return
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
trainer_options = dict(default_save_path=tmpdir,
show_progress_bar=True,
max_epochs=1,
gpus=1,
distributed_backend='ddp',
use_amp=True)
tutils.run_model_test(trainer_options, model)
def test_amp_gpu_ddp_slurm_managed(tmpdir):
"""Make sure DDP + AMP work."""
if not tutils.can_run_gpu_test():
return
tutils.reset_seed()
# simulate setting slurm flags
tutils.set_random_master_port()
os.environ['SLURM_LOCALID'] = str(0)
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
trainer_options = dict(show_progress_bar=True,
max_epochs=1,
gpus=[0],
distributed_backend='ddp',
use_amp=True)
# exp file to get meta
logger = tutils.get_test_tube_logger(tmpdir, False)
# exp file to get weights
checkpoint = tutils.init_checkpoint_callback(logger)
# add these to the trainer options
trainer_options['checkpoint_callback'] = checkpoint
trainer_options['logger'] = logger
# fit model
trainer = Trainer(**trainer_options)
trainer.is_slurm_managing_tasks = True
result = trainer.fit(model)
# correct result and ok accuracy
assert result == 1, 'amp + ddp model failed to complete'
# test root model address
assert trainer.resolve_root_node_address('abc') == 'abc'
assert trainer.resolve_root_node_address('abc[23]') == 'abc23'
assert trainer.resolve_root_node_address('abc[23-24]') == 'abc23'
assert trainer.resolve_root_node_address(
'abc[23-24, 45-40, 40]') == 'abc23'
def test_no_amp_single_gpu(tmpdir):
"""Make sure DDP + AMP work."""
tutils.reset_seed()
if not tutils.can_run_gpu_test():
return
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
trainer_options = dict(default_save_path=tmpdir,
show_progress_bar=True,
max_num_epochs=1,
gpus=1,
distributed_backend='dp',
use_amp=True)
with pytest.raises((MisconfigurationException, ModuleNotFoundError)):
tutils.run_model_test(trainer_options, model)
def test_testtube_pickle(tmpdir):
"""Verify that pickling a trainer containing a test tube logger works."""
tutils.reset_seed()
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
logger = tutils.get_test_tube_logger(tmpdir, False)
logger.log_hyperparams(hparams)
logger.save()
trainer_options = dict(max_num_epochs=1,
train_percent_check=0.01,
logger=logger)
trainer = Trainer(**trainer_options)
pkl_bytes = pickle.dumps(trainer)
trainer2 = pickle.loads(pkl_bytes)
trainer2.logger.log_metrics({"acc": 1.0})
def test_amp_gpu_ddp():
"""
Make sure DDP + AMP work
:return:
"""
if not can_run_gpu_test():
return
os.environ['MASTER_PORT'] = str(np.random.randint(12000, 19000, 1)[0])
hparams = get_hparams()
model = LightningTestModel(hparams)
trainer_options = dict(show_progress_bar=True,
max_nb_epochs=1,
gpus=2,
distributed_backend='ddp',
use_amp=True)
run_gpu_model_test(trainer_options, model, hparams)
def test_mlflow_logger(tmpdir):
"""Verify that basic functionality of mlflow logger works."""
tutils.reset_seed()
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_testtube_logger():
"""verify that basic functionality of test tube logger works"""
hparams = get_hparams()
model = LightningTestModel(hparams)
save_dir = init_save_dir()
logger = get_test_tube_logger(False)
logger.log_hyperparams(hparams)
logger.save()
trainer_options = dict(max_nb_epochs=1, logger=logger)
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
assert result == 1, "Training failed"
clear_save_dir()
def test_simple_cpu(tmpdir):
"""Verify continue training session on CPU."""
tutils.reset_seed()
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
# logger file to get meta
trainer_options = dict(
default_save_path=tmpdir,
max_epochs=1,
val_percent_check=0.1,
train_percent_check=0.1,
)
# fit model
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
# traning complete
assert result == 1, 'amp + ddp model failed to complete'
def test_amp_gpu_ddp():
"""
Make sure DDP + AMP work
:return:
"""
if not can_run_gpu_test():
return
reset_seed()
set_random_master_port()
hparams = get_hparams()
model = LightningTestModel(hparams)
trainer_options = dict(show_progress_bar=True,
max_nb_epochs=1,
gpus=2,
distributed_backend='ddp',
use_amp=True)
run_gpu_model_test(trainer_options, model, hparams)
def test_running_test_pretrained_model():
"""Verify test() on pretrained model"""
hparams = get_hparams()
model = LightningTestModel(hparams)
save_dir = init_save_dir()
# exp file to get meta
exp = get_exp(False)
exp.argparse(hparams)
exp.save()
# exp file to get weights
checkpoint = ModelCheckpoint(save_dir)
trainer_options = dict(
show_progress_bar=False,
max_nb_epochs=1,
train_percent_check=0.4,
val_percent_check=0.2,
checkpoint_callback=checkpoint,
experiment=exp
)
# fit model
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
# correct result and ok accuracy
assert result == 1, 'training failed to complete'
pretrained_model = load_model(
exp, save_dir, on_gpu=False, module_class=LightningTestModel
)
new_trainer = Trainer(**trainer_options)
new_trainer.test(pretrained_model)
# test we have good test accuracy
assert_ok_test_acc(new_trainer)
clear_save_dir()
def test_load_model_from_checkpoint(tmpdir):
tutils.reset_seed()
"""Verify test() on pretrained model"""
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
trainer_options = dict(
show_progress_bar=False,
max_epochs=2,
train_percent_check=0.4,
val_percent_check=0.2,
checkpoint_callback=ModelCheckpoint(tmpdir, save_top_k=-1),
logger=False,
default_save_path=tmpdir,
)
# fit model
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
# correct result and ok accuracy
assert result == 1, 'training failed to complete'
# load last checkpoint
last_checkpoint = os.path.join(trainer.checkpoint_callback.filepath,
"_ckpt_epoch_1.ckpt")
if not os.path.isfile(last_checkpoint):
last_checkpoint = os.path.join(trainer.checkpoint_callback.filepath,
"_ckpt_epoch_0.ckpt")
pretrained_model = LightningTestModel.load_from_checkpoint(last_checkpoint)
# test that hparams loaded correctly
for k, v in vars(hparams).items():
assert getattr(pretrained_model.hparams, k) == v
new_trainer = Trainer(**trainer_options)
new_trainer.test(pretrained_model)
# test we have good test accuracy
tutils.assert_ok_model_acc(new_trainer)
def test_testtube_logger():
"""
verify that basic functionality of test tube logger works
"""
reset_seed()
hparams = testing_utils.get_hparams()
model = LightningTestModel(hparams)
save_dir = testing_utils.init_save_dir()
logger = testing_utils.get_test_tube_logger(False)
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"
testing_utils.clear_save_dir()
def test_amp_single_gpu():
"""
Make sure DDP + AMP work
:return:
"""
testing_utils.reset_seed()
if not testing_utils.can_run_gpu_test():
return
hparams = testing_utils.get_hparams()
model = LightningTestModel(hparams)
trainer_options = dict(
show_progress_bar=True,
max_nb_epochs=1,
gpus=1,
distributed_backend='ddp',
use_amp=True
)
testing_utils.run_gpu_model_test(trainer_options, model, hparams)
def test_running_test_pretrained_model():
reset_seed()
"""Verify test() on pretrained model"""
hparams = get_hparams()
model = LightningTestModel(hparams)
save_dir = init_save_dir()
# logger file to get meta
logger = get_test_tube_logger(False)
logger.log_hyperparams(hparams)
logger.save()
# logger file to get weights
checkpoint = ModelCheckpoint(save_dir)
trainer_options = dict(show_progress_bar=False,
max_nb_epochs=1,
train_percent_check=0.4,
val_percent_check=0.2,
checkpoint_callback=checkpoint,
logger=logger)
# fit model
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
# correct result and ok accuracy
assert result == 1, 'training failed to complete'
pretrained_model = load_model(logger.experiment,
save_dir,
module_class=LightningTestModel)
new_trainer = Trainer(**trainer_options)
new_trainer.test(pretrained_model)
# test we have good test accuracy
assert_ok_test_acc(new_trainer)
clear_save_dir()
def test_running_test_pretrained_model(tmpdir):
tutils.reset_seed()
"""Verify test() on pretrained model"""
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
save_dir = tmpdir
# logger file to get meta
logger = tutils.get_test_tube_logger(save_dir, False)
# logger file to get weights
checkpoint = tutils.init_checkpoint_callback(logger)
trainer_options = dict(
show_progress_bar=False,
max_nb_epochs=4,
train_percent_check=0.4,
val_percent_check=0.2,
checkpoint_callback=checkpoint,
logger=logger
)
# fit model
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
# correct result and ok accuracy
assert result == 1, 'training failed to complete'
pretrained_model = tutils.load_model(
logger.experiment, trainer.checkpoint_callback.filepath, module_class=LightningTestModel
)
new_trainer = Trainer(**trainer_options)
new_trainer.test(pretrained_model)
# test we have good test accuracy
tutils.assert_ok_test_acc(new_trainer)
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})
def test_load_model_from_checkpoint():
tutils.reset_seed()
"""Verify test() on pretrained model"""
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
save_dir = tutils.init_save_dir()
trainer_options = dict(
show_progress_bar=False,
max_nb_epochs=1,
train_percent_check=0.4,
val_percent_check=0.2,
checkpoint_callback=True,
logger=False,
default_save_path=save_dir
)
# fit model
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
# correct result and ok accuracy
assert result == 1, 'training failed to complete'
pretrained_model = LightningTestModel.load_from_checkpoint(
os.path.join(trainer.checkpoint_callback.filepath, "_ckpt_epoch_0.ckpt")
)
# test that hparams loaded correctly
for k, v in vars(hparams).items():
assert getattr(pretrained_model.hparams, k) == v
new_trainer = Trainer(**trainer_options)
new_trainer.test(pretrained_model)
# test we have good test accuracy
tutils.assert_ok_test_acc(new_trainer)
tutils.clear_save_dir()
