def test_eval_preparation(self):
dl = DataloaderImages((149, 117), ignore_useless_states=False)
st = ModelTrainer(
lambda: DeconvModelEfficient(),
self.test_src_dir,
self.eval_output_path,
load_datasets_path=self.test_split_dir,
cache_path=None,
batch_size=2,
train_print_frequency=10,
epochs=0,
num_workers=4,
num_validation_samples=2,
num_test_samples=self.num_test_samples,
data_processing_function=dl.get_sensordata_and_flowfront,
data_gather_function=get_filelist_within_folder_blacklisted,
classification_evaluator_function=lambda summary_writer:
SensorToFlowfrontEvaluator(summary_writer=summary_writer),
data_root=test_resources.test_src_dir,
)
st.start_training()
dirs = [e for e in self.eval_output_path.iterdir() if e.is_dir()]
code_dir = dirs[0] / 'rtm-predictions'
slurm_script = dirs[0] / 'run_model_eval.sh'
self.assertTrue(os.path.isdir(code_dir))
self.assertTrue(os.path.isfile(slurm_script))
with open(slurm_script) as f:
lines = f.read().splitlines()
tokens = lines[-1].split()
self.assertEqual(dirs[0], Path(tokens[-3]))
st.writer.flush()
st.writer.close()
def test_training(self):
num_epochs = 2
dl = DataloaderImages((149, 117), ignore_useless_states=False)
st = ModelTrainer(
lambda: DeconvModelEfficient(),
self.test_src_dir,
self.training_save_path,
load_datasets_path=self.test_split_dir,
cache_path=None,
batch_size=16,
train_print_frequency=10,
epochs=num_epochs,
num_workers=4,
num_validation_samples=2,
num_test_samples=self.num_test_samples,
data_processing_function=dl.get_sensordata_and_flowfront,
data_gather_function=get_filelist_within_folder_blacklisted,
loss_criterion=torch.nn.BCELoss(),
classification_evaluator_function=lambda summary_writer:
SensorToFlowfrontEvaluator(summary_writer=summary_writer),
data_root=test_resources.test_src_dir,
)
st.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.assertEqual(num_epochs, len(epochs))
# Check if steps are growing / if there are doubled steps in the output
steps = [
int(re.findall(r'\d+', x)[0])
for x in re.findall(r'Duration of step.+\d:', content)
]
self.assertEqual(len(set(steps)), len(steps))
def test_training_load_optimizer(self):
dl = DataloaderImages((149, 117), ignore_useless_states=False)
st = ModelTrainer(
lambda: DeconvModelEfficient(),
self.test_src_dir,
self.training_save_path,
load_datasets_path=self.test_split_dir,
cache_path=None,
batch_size=16,
train_print_frequency=10,
epochs=self.expected_num_epochs_during_training,
num_workers=4,
num_validation_samples=2,
num_test_samples=self.num_test_samples,
data_processing_function=dl.get_sensordata_and_flowfront,
data_gather_function=get_filelist_within_folder_blacklisted,
loss_criterion=torch.nn.BCELoss(),
optimizer_path=self.checkpoint,
classification_evaluator_function=lambda summary_writer:
SensorToFlowfrontEvaluator(summary_writer=summary_writer),
data_root=test_resources.test_src_dir,
)
st.start_training()
after = len(st.optimizer.state.keys())
""" Optimizer has now more than 0 states, therefore was loaded """
self.assertGreater(after, 0)
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 test_save_load_training(self):
num_epochs = 2
dl = DataloaderImages((149, 117), ignore_useless_states=False)
st = ModelTrainer(
lambda: DeconvModelEfficient(),
self.test_src_dir,
self.training_save_path,
load_datasets_path=self.test_split_dir,
cache_path=None,
batch_size=16,
train_print_frequency=10,
epochs=num_epochs,
num_workers=4,
num_validation_samples=2,
num_test_samples=self.num_test_samples,
data_processing_function=dl.get_sensordata_and_flowfront,
data_gather_function=get_filelist_within_folder_blacklisted,
loss_criterion=torch.nn.BCELoss(),
classification_evaluator_function=lambda summary_writer:
SensorToFlowfrontEvaluator(summary_writer=summary_writer),
data_root=test_resources.test_src_dir,
)
st.start_training()
num_epochs = 2
dl = DataloaderImages((149, 117), ignore_useless_states=False)
st = ModelTrainer(
lambda: DeconvModelEfficient(),
self.test_src_dir,
self.training_save_path,
load_datasets_path=self.test_split_dir,
cache_path=None,
batch_size=16,
train_print_frequency=10,
epochs=num_epochs,
num_workers=4,
num_validation_samples=2,
num_test_samples=self.num_test_samples,
data_processing_function=dl.get_sensordata_and_flowfront,
data_gather_function=get_filelist_within_folder_blacklisted,
loss_criterion=torch.nn.BCELoss(),
classification_evaluator_function=lambda summary_writer:
SensorToFlowfrontEvaluator(summary_writer=summary_writer),
data_root=test_resources.test_src_dir,
)
st.start_training()
class TestTrainingDryspotFF(unittest.TestCase):
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 test_training(self):
self.dt.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 tearDown(self) -> None:
logging.shutdown()
r = logging.getLogger("")
[r.removeHandler(x) for x in r.handlers]
shutil.rmtree(self.training_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))
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")