-
Notifications
You must be signed in to change notification settings - Fork 53
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.
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
Runtime error during testing panoptic segmentation (tensors on different devices) #3
Comments
Yes this seems like a valid fix. |
@VSainteuf I would probably do something like
which should get the device type. |
Hi @julianblue , |
Hello, you got to do a new training with your own dataset using this implementation? in file train_panoptic.py, on line 218 through line 235 is called training in conjunction with zones. Than you
|
@VSainteuf @watch24hrs-iiitd, Hello it is possible to do a new training with a new dataset. I am studying the implementation and I find that the file train_panoptic.py needs the zone parameters for this. What are zones and what type of data are they. Than you if mode != "train": with torch.no_grad(): predictions = model( x, batch_positions=dates, pseudo_nms=compute_metrics, heatmap_only=heatmap_only, ) else: zones = y[:, :, :, 2] if config.supmax else None optimizer.zero_grad() predictions = model( x, |
During testing panoptic segmentation, with the following command:
I ran into the following error:
It seems that tensor
self.cumulative_ious
is oncpu
while the other tensor is oncuda
.The following change in file
/utae-paps/src/panoptic/metrics.py
:manages to fix this issue. Kindly confirm the validity of this fix.
Kindly also note that I also tried transferring
self.cumulative_ious
tocuda
, but it runs into errors later during execution.The text was updated successfully, but these errors were encountered: