def init_trainer():
dlds = DataloaderDryspots()
m = ModelTrainer(
lambda: model,
data_source_paths=filepaths,
save_path=save_path,
cache_path=cache_path,
batch_size=batch_size,
train_print_frequency=train_print_frequency,
looping_strategy=NoOpLoopingStrategy(),
epochs=epochs,
dummy_epoch=False,
num_workers=num_workers,
num_validation_samples=num_validation_samples,
num_test_samples=num_test_samples,
data_processing_function=dlds.
get_sensor_bool_dryspot_resized_matrix,
data_gather_function=get_filelist_within_folder_blacklisted,
data_root=data_root,
loss_criterion=torch.nn.BCELoss(),
optimizer_function=lambda params: torch.optim.AdamW(params,
lr=1e-4),
classification_evaluator_function=lambda:
BinaryClassificationEvaluator(),
lr_scheduler_function=lambda optim: ExponentialLR(optim, 0.5),
caching_torch=False,
demo_path=None,
hold_samples_in_memory=False,
)
return m
def create_trainer_and_start(self,
out_path,
epochs=1,
load_test_set=False):
dlds = DataloaderFlowfrontSensor(sensor_indizes=((1, 8), (1, 8)))
m = ModelTrainer(
lambda: S20DryspotModelFCWide(),
data_source_paths=tr_resources.get_data_paths_debug(),
save_path=out_path,
load_datasets_path=self.torch_dataset_resources /
"reference_datasets",
cache_path=None,
num_validation_samples=8,
num_test_samples=8,
num_workers=0,
epochs=epochs,
data_processing_function=dlds.get_flowfront_sensor_bool_dryspot,
data_gather_function=dg.get_filelist_within_folder_blacklisted,
loss_criterion=torch.nn.BCELoss(),
optimizer_function=lambda params: torch.optim.AdamW(params,
lr=1e-4),
classification_evaluator_function=lambda summary_writer:
BinaryClassificationEvaluator(summary_writer=summary_writer),
load_test_set_in_training_mode=load_test_set,
data_root=test_resources.test_src_dir,
)
return m
def test_training_ok_notok(self):
dls = DataLoaderSensor()
model_trainer = ModelTrainer(
lambda: ERFH5_PressureSequence_Model(),
self.training_data_paths,
self.training_save_path,
epochs=self.expected_num_epochs_during_training,
data_gather_function=dg.get_filelist_within_folder,
data_processing_function=dls.sensorgrid_simulationsuccess,
num_validation_samples=1,
num_test_samples=1,
loss_criterion=torch.nn.BCELoss(),
classification_evaluator_function=lambda summary_writer:
BinaryClassificationEvaluator(summary_writer=summary_writer),
data_root=test_resources.test_src_dir,
)
model_trainer.start_training()
dirs = [e for e in self.training_save_path.iterdir() if e.is_dir()]
with open(dirs[0] / "output.log") as f:
content = f.read()
epochs = re.findall("Mean Loss on Eval", content)
self.assertTrue(len(epochs) > 0)
def setUp(self):
self.training_save_path = resources.test_training_out_dir
self.training_data_paths = [
resources.test_training_src_dir / 'dry_spot_from_ff'
]
self.expected_num_epochs_during_training = 1
dlds = DataloaderDryspots(image_size=(143, 111),
ignore_useless_states=False)
self.dt = ModelTrainer(
lambda: DrySpotModel(),
data_source_paths=self.training_data_paths,
save_path=self.training_save_path,
batch_size=10,
epochs=self.expected_num_epochs_during_training,
num_validation_samples=5,
num_test_samples=5,
data_gather_function=dg.get_filelist_within_folder,
data_processing_function=dlds.get_flowfront_bool_dryspot,
loss_criterion=torch.nn.BCELoss(),
classification_evaluator_function=lambda summary_writer:
BinaryClassificationEvaluator(summary_writer=summary_writer,
save_path=self.training_save_path,
skip_images=True),
data_root=resources.test_src_dir,
)
def run_eval_w_binary_classificator(output_dir, modeltrainer, chkp_p: Path, ):
output_dir.mkdir(exist_ok=True)
modeltrainer.inference_on_test_set(
output_path=output_dir,
checkpoint_path=chkp_p,
classification_evaluator_function=lambda: BinaryClassificationEvaluator(output_dir,
skip_images=True,
with_text_overlay=True,
advanced_eval=True)
)
with open(output_dir / "predictions_per_run.p", "wb") as f:
pickle.dump(modeltrainer.classification_evaluator.origin_tracker, f)
freeze_nlayers=8),
data_source_paths=r.get_data_paths_base_0(),
save_path=r.save_path if args.demo is None else Path(args.demo),
load_datasets_path=r.datasets_dryspots,
cache_path=r.cache_path,
batch_size=2048,
train_print_frequency=100,
epochs=1000,
num_workers=75,
num_validation_samples=131072,
num_test_samples=1048576,
data_processing_function=dlds.get_sensor_bool_dryspot,
data_gather_function=get_filelist_within_folder_blacklisted,
loss_criterion=torch.nn.BCELoss(),
optimizer_function=lambda params: torch.optim.AdamW(params, lr=1e-4),
classification_evaluator_function=lambda summary_writer:
BinaryClassificationEvaluator(summary_writer=summary_writer),
lr_scheduler_function=lambda optim: ExponentialLR(optim, 0.5),
demo_path=args.demo)
if not args.run_eval:
m.start_training()
else:
m.inference_on_test_set(
output_path=Path(args.eval),
checkpoint_path=Path(args.checkpoint_path),
classification_evaluator_function=lambda summary_writer:
BinaryClassificationEvaluator(Path(args.eval) / "eval_on_test_set",
skip_images=True,
with_text_overlay=True))
import torch
import Resources.training as r
from Models.erfh5_pressuresequence_CRNN import ERFH5_PressureSequence_Model
from Pipeline import data_loader_sensor as dls, data_gather as dg
from Trainer.ModelTrainer import ModelTrainer
from Trainer.evaluation import BinaryClassificationEvaluator
if __name__ == "__main__":
data_source_paths = [r.data_root / "2019-07-24_16-32-40_5000p"]
save_path = r.save_path
cache_path = r.cache_path
trainer = ModelTrainer(
lambda: ERFH5_PressureSequence_Model(),
data_source_paths,
save_path,
None,
epochs=2,
data_gather_function=dg.get_filelist_within_folder,
data_processing_function=dls.sensorgrid_simulationsuccess,
loss_criterion=torch.nn.BCELoss(),
classification_evaluator_function=BinaryClassificationEvaluator(),
)
trainer.start_training()
print("training finished")
from Trainer.ModelTrainer import ModelTrainer
from Trainer.evaluation import BinaryClassificationEvaluator
from Utils.eval_utils import run_eval_w_binary_classificator
if __name__ == "__main__":
dl = DataloaderDryspots(sensor_indizes=((1, 8), (1, 8)), aux_info=True)
checkpoint_p = r.chkp_S20_densenet_baseline_full_trainingset
adv_output_dir = checkpoint_p.parent / "advanced_eval"
m = ModelTrainer(
lambda: S20DryspotModelFCWide(),
data_source_paths=r.get_data_paths_base_0(),
save_path=r.save_path,
load_datasets_path=r.datasets_dryspots,
cache_path=r.cache_path,
batch_size=32768,
train_print_frequency=100,
epochs=1000,
num_workers=75,
num_validation_samples=131072,
num_test_samples=1048576,
data_processing_function=dl.get_sensor_bool_dryspot,
data_gather_function=get_filelist_within_folder_blacklisted,
loss_criterion=torch.nn.BCELoss(),
optimizer_function=lambda params: torch.optim.AdamW(params, lr=0.0001),
classification_evaluator_function=lambda summary_writer:
BinaryClassificationEvaluator(summary_writer=summary_writer),
caching_torch=False)
run_eval_w_binary_classificator(adv_output_dir, m, checkpoint_p)
from Trainer.ModelTrainer import ModelTrainer
from Trainer.evaluation import BinaryClassificationEvaluator
from Utils.eval_utils import run_eval_w_binary_classificator
if __name__ == "__main__":
dl = DataloaderDryspots(sensor_indizes=((1, 4), (1, 4)), aux_info=True)
checkpoint_p = r.chkp_S80_densenet_baseline
adv_output_dir = checkpoint_p.parent / "advanced_eval"
m = ModelTrainer(
lambda: S80DryspotModelFCWide(),
data_source_paths=r.get_data_paths_base_0(),
save_path=r.save_path,
dataset_split_path=r.dataset_split,
cache_path=r.cache_path,
batch_size=2048,
train_print_frequency=100,
epochs=1000,
num_workers=75,
num_validation_samples=131072,
num_test_samples=1048576,
data_processing_function=dl.get_sensor_bool_dryspot,
data_gather_function=get_filelist_within_folder_blacklisted,
loss_criterion=torch.nn.BCELoss(),
optimizer_function=lambda params: torch.optim.AdamW(params, lr=0.0001),
classification_evaluator_function=lambda:
BinaryClassificationEvaluator(),
caching_torch=False)
run_eval_w_binary_classificator(adv_output_dir, m, checkpoint_p)
looping_strategy=NoOpLoopingStrategy(),
epochs=epochs,
dummy_epoch=False,
num_workers=num_workers,
num_validation_samples=num_validation_samples,
num_test_samples=num_test_samples,
data_processing_function=dlds.get_sensor_bool_dryspot,
data_gather_function=get_filelist_within_folder_blacklisted,
data_root=data_root,
loss_criterion=torch.nn.BCELoss(),
optimizer_function=lambda params: torch.optim.AdamW(
params, lr=1e-4),
classification_evaluator_function=lambda: BinaryClassificationEvaluator(),
lr_scheduler_function=lambda optim: ExponentialLR(optim, 0.5),
caching_torch=False,
demo_path=None,
hold_samples_in_memory=False,
)
return m
print("Starting training.")
m = init_trainer()
m.start_training()
print("Training finished. Starting evaluation")
m.inference_on_test_set(
classification_evaluator_function=lambda: BinaryClassificationEvaluator(save_path / "eval_on_test_set",
skip_images=True,
with_text_overlay=True)
)
data_source_paths=filepaths,
save_path=save_path,
cache_path=cache_path,
batch_size=batch_size,
train_print_frequency=train_print_frequency,
epochs=epochs,
dummy_epoch=True,
num_workers=num_workers,
num_validation_samples=num_validation_samples,
num_test_samples=num_test_samples,
data_processing_function=dlm.get_sensor_dryspot_mesh,
data_gather_function=get_filelist_within_folder_blacklisted,
data_root=data_root,
loss_criterion=torch.nn.BCELoss(),
optimizer_function=lambda params: torch.optim.SGD(params, lr=0.001),
classification_evaluator_function=lambda:
BinaryClassificationEvaluator(),
lr_scheduler_function=None,
caching_torch=False,
demo_path=None,
drop_last_batch=True)
print("Starting training routine.")
m.start_training()
print("Training finished. Starting test.")
m.inference_on_test_set(
classification_evaluator_function=lambda summary_writer:
BinaryClassificationEvaluator(save_path / "eval_on_test_set",
skip_images=True,
with_text_overlay=True))
checkpoint_path=Path(checkpoint_path),
freeze_nlayers=9),
data_source_paths=r.get_data_paths_base_0(),
save_path=r.save_path if args.demo is None else Path(args.demo),
dataset_split_path=r.dataset_split,
cache_path=r.cache_path,
batch_size=2048,
train_print_frequency=100,
epochs=1000,
num_workers=75,
num_validation_samples=131072,
num_test_samples=1048576,
data_processing_function=dl.get_sensor_bool_dryspot,
data_gather_function=get_filelist_within_folder_blacklisted,
loss_criterion=torch.nn.MSELoss(),
optimizer_function=lambda params: torch.optim.AdamW(params, lr=0.0001),
classification_evaluator_function=lambda:
BinaryClassificationEvaluator(),
lr_scheduler_function=lambda optim: ExponentialLR(optim, 0.5),
demo_path=args.demo)
if not args.run_eval:
m.start_training()
else:
m.inference_on_test_set(
Path(args.eval),
Path(args.checkpoint_path),
lambda: BinaryClassificationEvaluator(
Path(args.eval) / "eval_on_test_set"),
)
round_at=0.8),
data_source_paths=r.get_data_paths_base_0(),
save_path=r.save_path if args.demo is None else Path(args.demo),
dataset_split_path=r.dataset_split,
cache_path=r.cache_path,
batch_size=2048,
train_print_frequency=100,
epochs=1000,
num_workers=75,
num_validation_samples=131072,
num_test_samples=1048576,
data_processing_function=dl.get_sensor_bool_dryspot,
data_gather_function=get_filelist_within_folder_blacklisted,
loss_criterion=torch.nn.BCELoss(),
optimizer_function=lambda params: torch.optim.AdamW(params, lr=1e-4),
classification_evaluator_function=lambda: BinaryClassificationEvaluator(),
lr_scheduler_function=lambda optim: ExponentialLR(optim, 0.5),
demo_path=args.demo
)
if not args.run_eval:
m.start_training()
else:
m.inference_on_test_set(
Path(args.eval),
Path(args.checkpoint_path),
lambda: BinaryClassificationEvaluator(
Path(args.eval) / "eval_on_test_set",
),
)
m = ModelTrainer(lambda: S1140DryspotModelFCWide(),
data_source_paths=r.get_data_paths_debug(),
save_path=r.save_path,
dataset_split_path=r.dataset_split,
cache_path=r.cache_path,
batch_size=2048,
train_print_frequency=100,
epochs=100,
num_workers=75,
num_validation_samples=512, # 131072,
num_test_samples=1024, # 1048576,
data_processing_function=dlds.get_flowfront_sensor_bool_dryspot,
data_gather_function=get_filelist_within_folder_blacklisted,
loss_criterion=torch.nn.BCELoss(),
optimizer_function=lambda params: torch.optim.AdamW(params, lr=1e-4),
classification_evaluator_function=lambda: BinaryClassificationEvaluator(),
dont_care_num_samples=True
)
if not args.run_eval:
m.start_training()
else:
m.inference_on_test_set(
output_path=Path(args.eval),
checkpoint_path=Path(args.checkpoint_path),
classification_evaluator_function=lambda: BinaryClassificationEvaluator(
Path(args.eval) / "eval_on_test_set",
skip_images=True,
with_text_overlay=True)
)
from Trainer.evaluation import BinaryClassificationEvaluator
from Utils.eval_utils import run_eval_w_binary_classificator
if __name__ == "__main__":
dl = DataloaderDryspots(sensor_indizes=((1, 8), (1, 8)),
aux_info=True)
checkpoint_p = r.chkp_S20_densenet_baseline_full_trainingset
adv_output_dir = checkpoint_p.parent / "advanced_eval"
m = ModelTrainer(
lambda: S20DryspotModelFCWide(),
data_source_paths=r.get_data_paths_base_0(),
save_path=r.save_path,
dataset_split_path=r.dataset_split,
cache_path=r.cache_path,
batch_size=32768,
train_print_frequency=100,
epochs=1000,
num_workers=75,
num_validation_samples=131072,
num_test_samples=1048576,
data_processing_function=dl.get_sensor_bool_dryspot,
data_gather_function=get_filelist_within_folder_blacklisted,
loss_criterion=torch.nn.BCELoss(),
optimizer_function=lambda params: torch.optim.AdamW(params, lr=0.0001),
classification_evaluator_function=lambda: BinaryClassificationEvaluator(),
caching_torch=False
)
run_eval_w_binary_classificator(adv_output_dir, m, checkpoint_p)
r.save_path,
dataset_split_path=None, # r.dataset_split,
data_root=data_root,
cache_path=r.cache_path,
batch_size=batch_size,
epochs=num_epochs,
num_workers=num_workers,
num_validation_samples=num_val,
num_test_samples=num_test,
data_processing_function=dl.get_sensor_bool_dryspot_runlevel,
data_gather_function=get_filelist_within_folder_blacklisted,
loss_criterion=torch.nn.BCELoss(),
optimizer_function=lambda params: torch.optim.AdamW(params, lr=lr),
classification_evaluator_function=lambda:
BinaryClassificationEvaluator(skip_images=not create_data_plots,
max_epochs=num_epochs,
data_loader=dl),
# lr_scheduler_function=lambda optim: ExponentialLR(optim, 0.5),
dummy_epoch=False,
caching_torch=use_cache,
run_name=run_name,
save_in_mlflow_directly=True)
if not args.run_eval:
m.start_training()
else:
m.inference_on_test_set(
Path(args.eval), Path(args.checkpoint_path),
lambda: BinaryClassificationEvaluator(save_path=Path(args.eval) /
"eval_on_test_set",
skip_images=False))
m = ModelTrainer(
lambda: DrySpotModel(),
data_source_paths=r.get_data_paths_base_0(),
save_path=r.save_path,
load_datasets_path=r.datasets_dryspots,
cache_path=r.cache_path,
batch_size=2048,
train_print_frequency=100,
epochs=1000,
num_workers=75,
num_validation_samples=131072,
num_test_samples=1048576,
data_processing_function=dl.get_flowfront_bool_dryspot,
data_gather_function=get_filelist_within_folder_blacklisted,
loss_criterion=torch.nn.MSELoss(),
optimizer_function=lambda params: torch.optim.AdamW(params, lr=0.0001),
classification_evaluator_function=lambda summary_writer:
BinaryClassificationEvaluator(summary_writer=summary_writer),
)
if not args.run_eval:
m.start_training()
else:
m.inference_on_test_set(
Path(args.eval),
Path(args.checkpoint_path),
lambda summary_writer: BinaryClassificationEvaluator(
Path(args.eval) / "eval_on_test_set",
),
)