Skip to content

Feature/hyperparameter tuning #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
naurlaunim wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Feature/hyperparameter tuning #3

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c655599
metrics update
Dec 20, 2021
66b47c1
add f1 to tune
Dec 20, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 4 additions & 6 deletions tuning.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,25 +3,23 @@
import torch.cuda
from pytorch_lightning.callbacks import ModelCheckpoint
from pytorch_lightning import Trainer
from train_pl import *
from ray import tune
from ray.tune.integration.pytorch_lightning import TuneReportCallback

from train_pl import *


args = PLOptions().parse()

def train_segmentation(config):
for k, v in config.items():
args.__dict__[k] = v

model = MeshSegmenter(args)
callback_tune = TuneReportCallback(metrics='val_iou', on="validation_end")
callback_tune = TuneReportCallback(metrics=['val_iou', 'val_f1'], on="validation_end")
callback_lightning = ModelCheckpoint(monitor='val_iou', mode='max', save_top_k=3,
filename='{epoch:02d}-{val_acc_epoch:.2f}', )

# callback_tune_f1 = TuneReportCallback(metrics='val_f1', on="validation_end")
# callback_lightning_f1 = ModelCheckpoint(monitor='val_f1', mode='max', save_top_k=3,
# filename='{epoch:02d}-{val_acc_epoch:.2f}', )

trainer = Trainer.from_argparse_args(args, callbacks=[callback_tune, callback_lightning])
trainer.fit(model)
torch.cuda.empty_cache()
Expand Down