Skip to content
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

Fix wrong device error created by a breaking change in torch when using DDP #120

Merged
merged 2 commits into from
Apr 24, 2024
Merged

Fix wrong device error created by a breaking change in torch when using DDP #120

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1e1abbe
Move IoU to GPU before compute
CharlesGaydon Apr 20, 2024
463c3a7
CHANGELOG
CharlesGaydon Apr 20, 2024
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
4 changes: 4 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,8 @@
# CHANGELOG

### 3.8.4
- fix: move IoU appropriately to fix wrong device error created by a breaking change in torch when using DDP.

### 3.8.3
- fix: prepare_data_per_node is a flag and was incorrectly used as a replacement for prepare_data.

Expand Down
2 changes: 1 addition & 1 deletion myria3d/_version.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
__version__ = "3.8.3"
__version__ = "3.8.4"


if __name__ == "__main__":
Expand Down
6 changes: 3 additions & 3 deletions myria3d/models/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,7 +148,7 @@ def training_step(self, batch: Batch, batch_idx: int) -> dict:
return {"loss": loss, "logits": logits, "targets": targets}

def on_train_epoch_end(self) -> None:
iou_epoch = self.train_iou.compute()
iou_epoch = self.train_iou.to(self.device).compute()
self.log("train/iou", iou_epoch, on_step=False, on_epoch=True, prog_bar=True)
self.log_all_class_ious(self.train_iou.confmat, "train")
log_comet_cm(self, self.train_iou.confmat, "train")
Expand Down Expand Up @@ -186,7 +186,7 @@ def on_validation_epoch_end(self) -> None:
outputs : output of validation_step

"""
iou_epoch = self.val_iou.compute()
iou_epoch = self.val_iou.to(self.device).compute()
self.log("val/iou", iou_epoch, on_step=False, on_epoch=True, prog_bar=True)
self.log_all_class_ious(self.val_iou.confmat, "val")
log_comet_cm(self, self.val_iou.confmat, "val")
Expand Down Expand Up @@ -221,7 +221,7 @@ def on_test_epoch_end(self) -> None:
outputs : output of test

"""
iou_epoch = self.test_iou.compute()
iou_epoch = self.test_iou.to(self.device).compute()
self.log("test/iou", iou_epoch, on_step=False, on_epoch=True, prog_bar=True)
self.log_all_class_ious(self.test_iou.confmat, "test")
log_comet_cm(self, self.test_iou.confmat, "test")
Expand Down