def test_cpu_restore_training():
"""
Verify continue training session on CPU
:return:
"""
hparams = get_hparams()
model = LightningTestModel(hparams)
save_dir = init_save_dir()
# exp file to get meta
test_exp_version = 10
exp = get_exp(False, version=test_exp_version)
exp.argparse(hparams)
exp.save()
trainer_options = dict(max_nb_epochs=2,
val_check_interval=0.50,
val_percent_check=0.2,
train_percent_check=0.2,
experiment=exp,
checkpoint_callback=ModelCheckpoint(save_dir))
# fit model
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
real_global_epoch = trainer.current_epoch
# traning complete
assert result == 1, 'amp + ddp model failed to complete'
# wipe-out trainer and model
# retrain with not much data... this simulates picking training back up after slurm
# we want to see if the weights come back correctly
new_exp = get_exp(False, version=test_exp_version)
trainer_options = dict(
max_nb_epochs=2,
val_check_interval=0.50,
val_percent_check=0.2,
train_percent_check=0.2,
experiment=new_exp,
checkpoint_callback=ModelCheckpoint(save_dir),
)
trainer = Trainer(**trainer_options)
model = LightningTestModel(hparams)
# set the epoch start hook so we can predict before the model does the full training
def assert_good_acc():
assert trainer.current_epoch == real_global_epoch and trainer.current_epoch > 0
# if model and state loaded correctly, predictions will be good even though we
# haven't trained with the new loaded model
trainer.model.eval()
_ = [
run_prediction(dataloader, trainer.model)
for dataloader in trainer.val_dataloader
]
model.on_sanity_check_start = assert_good_acc
# by calling fit again, we trigger training, loading weights from the cluster
# and our hook to predict using current model before any more weight updates
trainer.fit(model)
clear_save_dir()
def test_cpu_restore_training(tmpdir):
"""Verify continue training session on CPU."""
tutils.reset_seed()
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
# logger file to get meta
test_logger_version = 10
logger = tutils.get_test_tube_logger(tmpdir,
False,
version=test_logger_version)
trainer_options = dict(max_num_epochs=2,
val_check_interval=0.50,
val_percent_check=0.2,
train_percent_check=0.2,
logger=logger,
checkpoint_callback=ModelCheckpoint(tmpdir))
# fit model
trainer = Trainer(**trainer_options)
result = trainer.fit(model)
real_global_epoch = trainer.current_epoch
# traning complete
assert result == 1, 'amp + ddp model failed to complete'
# wipe-out trainer and model
# retrain with not much data... this simulates picking training back up after slurm
# we want to see if the weights come back correctly
new_logger = tutils.get_test_tube_logger(tmpdir,
False,
version=test_logger_version)
trainer_options = dict(
max_num_epochs=2,
val_check_interval=0.50,
val_percent_check=0.2,
train_percent_check=0.2,
logger=new_logger,
checkpoint_callback=ModelCheckpoint(tmpdir),
)
trainer = Trainer(**trainer_options)
model = LightningTestModel(hparams)
# set the epoch start hook so we can predict before the model does the full training
def assert_good_acc():
assert trainer.current_epoch == real_global_epoch
assert trainer.current_epoch >= 0
# if model and state loaded correctly, predictions will be good even though we
# haven't trained with the new loaded model
trainer.model.eval()
for dataloader in trainer.get_val_dataloaders():
tutils.run_prediction(dataloader, trainer.model)
model.on_sanity_check_start = assert_good_acc
# by calling fit again, we trigger training, loading weights from the cluster
# and our hook to predict using current model before any more weight updates
trainer.fit(model)
def test_dp_resume():
"""
Make sure DP continues training correctly
:return:
"""
if not tutils.can_run_gpu_test():
return
tutils.reset_seed()
hparams = tutils.get_hparams()
model = LightningTestModel(hparams)
trainer_options = dict(
show_progress_bar=True,
max_nb_epochs=2,
gpus=2,
distributed_backend='dp',
)
save_dir = tutils.init_save_dir()
# get logger
logger = tutils.get_test_tube_logger(debug=False)
# exp file to get weights
# logger file to get weights
checkpoint = tutils.init_checkpoint_callback(logger)
# add these to the trainer options
trainer_options['logger'] = logger
trainer_options['checkpoint_callback'] = checkpoint
# fit model
trainer = Trainer(**trainer_options)
trainer.is_slurm_managing_tasks = True
result = trainer.fit(model)
# track epoch before saving
real_global_epoch = trainer.current_epoch
# correct result and ok accuracy
assert result == 1, 'amp + dp model failed to complete'
# ---------------------------
# HPC LOAD/SAVE
# ---------------------------
# save
trainer.hpc_save(save_dir, logger)
# init new trainer
new_logger = tutils.get_test_tube_logger(version=logger.version)
trainer_options['logger'] = new_logger
trainer_options['checkpoint_callback'] = ModelCheckpoint(save_dir)
trainer_options['train_percent_check'] = 0.2
trainer_options['val_percent_check'] = 0.2
trainer_options['max_nb_epochs'] = 1
new_trainer = Trainer(**trainer_options)
# set the epoch start hook so we can predict before the model does the full training
def assert_good_acc():
assert new_trainer.current_epoch == real_global_epoch and new_trainer.current_epoch > 0
# if model and state loaded correctly, predictions will be good even though we
# haven't trained with the new loaded model
dp_model = new_trainer.model
dp_model.eval()
dataloader = trainer.get_train_dataloader()
tutils.run_prediction(dataloader, dp_model, dp=True)
# new model
model = LightningTestModel(hparams)
model.on_sanity_check_start = assert_good_acc
# fit new model which should load hpc weights
new_trainer.fit(model)
# test freeze on gpu
model.freeze()
model.unfreeze()
tutils.clear_save_dir()
def main():
"""
Make sure DDP + AMP continue training correctly
:return:
"""
hparams = get_hparams()
model = LightningTestModel(hparams)
trainer_options = dict(
show_progress_bar=True,
max_nb_epochs=4,
gpus=2,
distributed_backend='dp',
)
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)
# add these to the trainer options
trainer_options['experiment'] = exp
trainer_options['checkpoint_callback'] = checkpoint
# fit model
trainer = Trainer(**trainer_options)
trainer.is_slurm_managing_tasks = True
result = trainer.fit(model)
# track epoch before saving
real_global_epoch = trainer.current_epoch
# correct result and ok accuracy
assert result == 1, 'amp + dp model failed to complete'
# ---------------------------
# HPC LOAD/SAVE
# ---------------------------
# save
trainer.hpc_save(save_dir, exp)
# init new trainer
new_exp = get_exp(False, version=exp.version)
trainer_options['experiment'] = new_exp
trainer_options['checkpoint_callback'] = ModelCheckpoint(save_dir)
trainer_options['train_percent_check'] = 0.2
trainer_options['val_percent_check'] = 0.2
trainer_options['max_nb_epochs'] = 1
new_trainer = Trainer(**trainer_options)
# set the epoch start hook so we can predict before the model does the full training
def assert_good_acc():
assert trainer.current_epoch == real_global_epoch and trainer.current_epoch > 0
# if model and state loaded correctly, predictions will be good even though we
# haven't trained with the new loaded model
dp_model = new_trainer.model
dp_model.eval()
_ = [run_prediction(dataloader, dp_model, dp=True) for dataloader in trainer.val_dataloader]
# new model
model = LightningTestModel(hparams)
model.on_sanity_check_start = assert_good_acc
# fit new model which should load hpc weights
new_trainer.fit(model)
# test freeze on gpu
model.freeze()
model.unfreeze()
clear_save_dir()
