128 lines
5.2 KiB
Python
128 lines
5.2 KiB
Python
# Imports
|
|
# =============================================================================
|
|
import os
|
|
from distutils.util import strtobool
|
|
from pathlib import Path
|
|
from argparse import ArgumentParser, Namespace
|
|
|
|
import warnings
|
|
|
|
import torch
|
|
from pytorch_lightning import Trainer
|
|
from pytorch_lightning.callbacks import ModelCheckpoint, EarlyStopping
|
|
from torch.utils.data import DataLoader
|
|
|
|
from lib.modules.utils import LightningBaseModule
|
|
from lib.utils.config import Config
|
|
from lib.utils.logging import Logger
|
|
|
|
from lib.evaluation.classification import ROCEvaluation
|
|
|
|
warnings.filterwarnings('ignore', category=FutureWarning)
|
|
warnings.filterwarnings('ignore', category=UserWarning)
|
|
|
|
_ROOT = Path(__file__).parent
|
|
|
|
# Paramter Configuration
|
|
# =============================================================================
|
|
# Argument Parser
|
|
main_arg_parser = ArgumentParser(description="parser for fast-neural-style")
|
|
|
|
# Main Parameters
|
|
main_arg_parser.add_argument("--main_debug", type=strtobool, default=False, help="")
|
|
main_arg_parser.add_argument("--main_eval", type=strtobool, default=False, help="")
|
|
main_arg_parser.add_argument("--main_seed", type=int, default=69, help="")
|
|
|
|
# Data Parameters
|
|
main_arg_parser.add_argument("--data_worker", type=int, default=10, help="")
|
|
main_arg_parser.add_argument("--data_batchsize", type=int, default=100, help="")
|
|
main_arg_parser.add_argument("--data_root", type=str, default='/data/', help="")
|
|
main_arg_parser.add_argument("--data_map_root", type=str, default='/res/maps', help="")
|
|
|
|
# Transformations
|
|
main_arg_parser.add_argument("--transformations_to_tensor", type=strtobool, default=False, help="")
|
|
|
|
# Transformations
|
|
main_arg_parser.add_argument("--train_outpath", type=str, default="output", help="")
|
|
main_arg_parser.add_argument("--train_version", type=strtobool, required=False, help="")
|
|
main_arg_parser.add_argument("--train_epochs", type=int, default=10, help="")
|
|
main_arg_parser.add_argument("--train_batch_size", type=int, default=256, help="")
|
|
main_arg_parser.add_argument("--train_lr", type=float, default=0.002, help="")
|
|
|
|
# Model
|
|
main_arg_parser.add_argument("--model_type", type=str, default="classifier_cnn", help="")
|
|
main_arg_parser.add_argument("--model_activation", type=str, default="relu", help="")
|
|
main_arg_parser.add_argument("--model_filters", type=str, default="[32, 16, 4]", help="")
|
|
main_arg_parser.add_argument("--model_classes", type=int, default=2, help="")
|
|
main_arg_parser.add_argument("--model_use_bias", type=strtobool, default=True, help="")
|
|
main_arg_parser.add_argument("--model_use_norm", type=strtobool, default=True, help="")
|
|
main_arg_parser.add_argument("--model_dropout", type=float, default=0.00, help="")
|
|
|
|
# Project
|
|
main_arg_parser.add_argument("--project_name", type=str, default='traj-gen', help="")
|
|
main_arg_parser.add_argument("--project_owner", type=str, default='si11ium', help="")
|
|
main_arg_parser.add_argument("--project_neptune_key", type=str, default=os.getenv('NEPTUNE_KEY'), help="")
|
|
|
|
# Parse it
|
|
args: Namespace = main_arg_parser.parse_args()
|
|
|
|
|
|
def run_lightning_loop(config_obj):
|
|
|
|
# Logging
|
|
# ================================================================================
|
|
# Logger
|
|
with Logger(config_obj) as logger:
|
|
# Callbacks
|
|
# =============================================================================
|
|
# Checkpoint Saving
|
|
checkpoint_callback = ModelCheckpoint(
|
|
filepath=str(logger.log_dir / 'ckpt_weights'),
|
|
verbose=True, save_top_k=5,
|
|
)
|
|
# =============================================================================
|
|
# Early Stopping
|
|
# TODO: For This to work, one must set a validation step and End Eval and Score
|
|
early_stopping_callback = EarlyStopping(
|
|
monitor='val_loss',
|
|
min_delta=0.0,
|
|
patience=0,
|
|
)
|
|
|
|
# Model
|
|
# =============================================================================
|
|
# Init
|
|
model: LightningBaseModule = config_obj.model_class(config_obj.model_paramters)
|
|
model.init_weights()
|
|
|
|
# Trainer
|
|
# =============================================================================
|
|
trainer = Trainer(max_epochs=config_obj.train.epochs,
|
|
show_progress_bar=True,
|
|
weights_save_path=logger.log_dir,
|
|
gpus=[0] if torch.cuda.is_available() else None,
|
|
row_log_interval=(model.data_len * 0.01), # TODO: Better Value / Setting
|
|
log_save_interval=(model.data_len * 0.04), # TODO: Better Value / Setting
|
|
checkpoint_callback=checkpoint_callback,
|
|
logger=logger,
|
|
fast_dev_run=config_obj.main.debug,
|
|
early_stop_callback=None
|
|
)
|
|
|
|
# Train It
|
|
trainer.fit(model,)
|
|
|
|
# Save the last state & all parameters
|
|
trainer.save_checkpoint(logger.log_dir / 'weights.ckpt')
|
|
model.save_to_disk(logger.log_dir)
|
|
|
|
# Evaluate It
|
|
trainer.test()
|
|
return model
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
config = Config.read_namespace(args)
|
|
trained_model = run_lightning_loop(config)
|