def test_multi_gpu_model_dp(tmpdir):
"""
Make sure DP works
:return:
"""
tutils.reset_seed()
if not tutils.can_run_gpu_test():
return
model, hparams = tutils.get_model()
trainer_options = dict(
default_save_path=tmpdir,
show_progress_bar=False,
distributed_backend='dp',
max_nb_epochs=1,
train_percent_check=0.1,
val_percent_check=0.1,
gpus='-1'
)
tutils.run_model_test(trainer_options, model, hparams)
# test memory helper functions
memory.get_memory_profile('min_max')
def test_early_stopping_cpu_model(tmpdir):
"""Test each of the trainer options."""
tutils.reset_seed()
stopping = EarlyStopping(monitor='val_loss', min_delta=0.1)
trainer_options = dict(
default_save_path=tmpdir,
min_epochs=2,
early_stop_callback=stopping,
gradient_clip_val=1.0,
overfit_pct=0.20,
track_grad_norm=2,
print_nan_grads=True,
show_progress_bar=True,
logger=tutils.get_test_tube_logger(tmpdir),
train_percent_check=0.1,
val_percent_check=0.1,
)
model, hparams = tutils.get_model()
tutils.run_model_test(trainer_options,
model,
on_gpu=False,
early_stop=True)
# test freeze on cpu
model.freeze()
model.unfreeze()
def test_cpu_model(tmpdir):
"""Make sure model trains on CPU."""
tutils.reset_seed()
trainer_options = dict(default_save_path=tmpdir,
show_progress_bar=False,
logger=tutils.get_test_tube_logger(tmpdir),
max_epochs=1,
train_percent_check=0.4,
val_percent_check=0.4)
model, hparams = tutils.get_model()
tutils.run_model_test(trainer_options, model, on_gpu=False)
def test_cpu_model():
"""
Make sure model trains on CPU
:return:
"""
tutils.reset_seed()
trainer_options = dict(show_progress_bar=False,
logger=tutils.get_test_tube_logger(),
max_nb_epochs=1,
train_percent_check=0.4,
val_percent_check=0.4)
model, hparams = tutils.get_model()
tutils.run_model_test(trainer_options, model, hparams, on_gpu=False)
def test_cpu_model_with_amp(tmpdir):
"""Make sure model trains on CPU."""
tutils.reset_seed()
trainer_options = dict(default_save_path=tmpdir,
show_progress_bar=False,
logger=tutils.get_test_tube_logger(tmpdir),
max_epochs=1,
train_percent_check=0.4,
val_percent_check=0.4,
use_amp=True)
model, hparams = tutils.get_model()
with pytest.raises((MisconfigurationException, ModuleNotFoundError)):
tutils.run_model_test(trainer_options, model, on_gpu=False)
def test_amp_gpu_dp(tmpdir):
"""Make sure DP + AMP work."""
tutils.reset_seed()
if not tutils.can_run_gpu_test():
return
model, hparams = tutils.get_model()
trainer_options = dict(
default_save_path=tmpdir,
max_num_epochs=1,
gpus='0, 1', # test init with gpu string
distributed_backend='dp',
use_amp=True)
with pytest.raises(MisconfigurationException):
tutils.run_model_test(trainer_options, model, hparams)
def test_multi_gpu_none_backend(tmpdir):
"""Make sure when using multiple GPUs the user can't use `distributed_backend = None`."""
tutils.reset_seed()
if not tutils.can_run_gpu_test():
return
model, hparams = tutils.get_model()
trainer_options = dict(default_save_path=tmpdir,
show_progress_bar=False,
max_num_epochs=1,
train_percent_check=0.1,
val_percent_check=0.1,
gpus='-1')
with pytest.raises(MisconfigurationException):
tutils.run_model_test(trainer_options, model)
def test_single_gpu_model(tmpdir):
"""Make sure single GPU works (DP mode)."""
tutils.reset_seed()
if not torch.cuda.is_available():
warnings.warn('test_single_gpu_model cannot run.'
' Rerun on a GPU node to run this test')
return
model, hparams = tutils.get_model()
trainer_options = dict(default_save_path=tmpdir,
show_progress_bar=False,
max_epochs=1,
train_percent_check=0.1,
val_percent_check=0.1,
gpus=1)
tutils.run_model_test(trainer_options, model)
def test_all_features_cpu_model(tmpdir):
"""Test each of the trainer options."""
tutils.reset_seed()
trainer_options = dict(default_save_path=tmpdir,
gradient_clip_val=1.0,
overfit_pct=0.20,
track_grad_norm=2,
print_nan_grads=True,
show_progress_bar=False,
logger=tutils.get_test_tube_logger(tmpdir),
accumulate_grad_batches=2,
max_epochs=1,
train_percent_check=0.4,
val_percent_check=0.4)
model, hparams = tutils.get_model()
tutils.run_model_test(trainer_options, model, on_gpu=False)
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_multi_gpu_model_ddp(tmpdir):
"""Make sure DDP works."""
if not tutils.can_run_gpu_test():
return
tutils.reset_seed()
tutils.set_random_master_port()
model, hparams = tutils.get_model()
trainer_options = dict(default_save_path=tmpdir,
show_progress_bar=False,
max_num_epochs=1,
train_percent_check=0.4,
val_percent_check=0.2,
gpus=[0, 1],
distributed_backend='ddp')
tutils.run_model_test(trainer_options, model)
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_amp_gpu_ddp():
"""
Make sure DDP + AMP work
:return:
"""
if not tutils.can_run_gpu_test():
return
tutils.reset_seed()
tutils.set_random_master_port()
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
trainer_options = dict(show_progress_bar=True,
max_nb_epochs=1,
gpus=2,
distributed_backend='ddp',
use_amp=True)
tutils.run_model_test(trainer_options, model, hparams)
def test_multi_gpu_model_ddp2():
"""
Make sure DDP2 works
:return:
"""
if not tutils.can_run_gpu_test():
return
tutils.reset_seed()
tutils.set_random_master_port()
model, hparams = tutils.get_model()
trainer_options = dict(show_progress_bar=True,
max_nb_epochs=1,
train_percent_check=0.4,
val_percent_check=0.2,
gpus=2,
weights_summary=None,
distributed_backend='ddp2')
tutils.run_model_test(trainer_options, model, hparams)
