Spaces:
Runtime error
Runtime error
File size: 4,486 Bytes
3c10b34 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 |
from typing import List, Optional, Tuple
import hydra
import lightning as L
import pyrootutils
import torch
from lightning import Callback, LightningDataModule, LightningModule, Trainer
from lightning.pytorch.loggers import Logger
from omegaconf import DictConfig
pyrootutils.setup_root(__file__, indicator=".project-root", pythonpath=True)
# ------------------------------------------------------------------------------------ #
# the setup_root above is equivalent to:
# - adding project root dir to PYTHONPATH
# (so you don't need to force user to install project as a package)
# (necessary before importing any local modules e.g. `from src import utils`)
# - setting up PROJECT_ROOT environment variable
# (which is used as a base for paths in "configs/paths/default.yaml")
# (this way all filepaths are the same no matter where you run the code)
# - loading environment variables from ".env" in root dir
#
# you can remove it if you:
# 1. either install project as a package or move entry files to project root dir
# 2. set `root_dir` to "." in "configs/paths/default.yaml"
#
# more info: https://github.com/ashleve/pyrootutils
# ------------------------------------------------------------------------------------ #
from diff_ttsg import utils
log = utils.get_pylogger(__name__)
@utils.task_wrapper
def train(cfg: DictConfig) -> Tuple[dict, dict]:
"""Trains the model. Can additionally evaluate on a testset, using best weights obtained during
training.
This method is wrapped in optional @task_wrapper decorator, that controls the behavior during
failure. Useful for multiruns, saving info about the crash, etc.
Args:
cfg (DictConfig): Configuration composed by Hydra.
Returns:
Tuple[dict, dict]: Dict with metrics and dict with all instantiated objects.
"""
# set seed for random number generators in pytorch, numpy and python.random
if cfg.get("seed"):
L.seed_everything(cfg.seed, workers=True)
log.info(f"Instantiating datamodule <{cfg.data._target_}>")
datamodule: LightningDataModule = hydra.utils.instantiate(cfg.data)
log.info(f"Instantiating model <{cfg.model._target_}>")
model: LightningModule = hydra.utils.instantiate(cfg.model)
log.info("Instantiating callbacks...")
callbacks: List[Callback] = utils.instantiate_callbacks(cfg.get("callbacks"))
log.info("Instantiating loggers...")
logger: List[Logger] = utils.instantiate_loggers(cfg.get("logger"))
log.info(f"Instantiating trainer <{cfg.trainer._target_}>")
trainer: Trainer = hydra.utils.instantiate(cfg.trainer, callbacks=callbacks, logger=logger)
object_dict = {
"cfg": cfg,
"datamodule": datamodule,
"model": model,
"callbacks": callbacks,
"logger": logger,
"trainer": trainer,
}
if logger:
log.info("Logging hyperparameters!")
utils.log_hyperparameters(object_dict)
if cfg.get("compile"):
log.info("Compiling model!")
model = torch.compile(model)
if cfg.get("train"):
log.info("Starting training!")
trainer.fit(model=model, datamodule=datamodule, ckpt_path=cfg.get("ckpt_path"))
train_metrics = trainer.callback_metrics
if cfg.get("test"):
log.info("Starting testing!")
ckpt_path = trainer.checkpoint_callback.best_model_path
if ckpt_path == "":
log.warning("Best ckpt not found! Using current weights for testing...")
ckpt_path = None
trainer.test(model=model, datamodule=datamodule, ckpt_path=ckpt_path)
log.info(f"Best ckpt path: {ckpt_path}")
test_metrics = trainer.callback_metrics
# merge train and test metrics
metric_dict = {**train_metrics, **test_metrics}
return metric_dict, object_dict
@hydra.main(version_base="1.3", config_path="../configs", config_name="train.yaml")
def main(cfg: DictConfig) -> Optional[float]:
# apply extra utilities
# (e.g. ask for tags if none are provided in cfg, print cfg tree, etc.)
utils.extras(cfg)
# train the model
metric_dict, _ = train(cfg)
# safely retrieve metric value for hydra-based hyperparameter optimization
metric_value = utils.get_metric_value(
metric_dict=metric_dict, metric_name=cfg.get("optimized_metric")
)
# return optimized metric
return metric_value
if __name__ == "__main__":
torch.set_float32_matmul_precision('medium')
main()
|