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_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_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_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()
def test_eval(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=self.expected_num_epochs_during_training,
num_workers=10,
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(self.eval_output_path /
"eval_on_test_set",
skip_images=False,
summary_writer=summary_writer),
data_root=test_resources.test_src_dir,
)
st.inference_on_test_set(
self.eval_output_path,
self.checkpoint,
classification_evaluator_function=lambda summary_writer:
SensorToFlowfrontEvaluator(self.eval_output_path /
"eval_on_test_set",
skip_images=False,
summary_writer=summary_writer))
with open(self.eval_output_path / "eval_on_test_set" /
"test_output.log") as f:
content = f.read()
loss = float(
re.findall(r'\d+.\d+',
re.findall(r'Eval: \d+\.\d+', content)[0])[0])
self.assertEqual(np.round(loss, 4), self.expected_loss)
img_path = self.eval_output_path / 'eval_on_test_set' / 'images'
list_all_imgs = list(img_path.glob('**/*.jpg'))
self.assertEqual(len(list_all_imgs), self.expected_num_frames)
import Resources.training as r
from Models.erfh5_DeconvModel import DeconvModelEfficient
from Pipeline.data_gather import get_filelist_within_folder_blacklisted
from Pipeline.data_loaders_IMG import DataloaderImages
from Trainer.ModelTrainer import ModelTrainer
from Trainer.evaluation import SensorToFlowfrontEvaluator
if __name__ == "__main__":
dl = DataloaderImages((149, 117))
checkpoint_p = r.chkp_S1140_to_ff_0_basepr
adv_output_dir = checkpoint_p.parent / "advanced_eval"
m = ModelTrainer(
lambda: DeconvModelEfficient(),
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=10,
epochs=1000,
num_workers=75,
num_validation_samples=131072,
num_test_samples=1048576,
data_processing_function=dl.get_sensordata_and_flowfront,
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: