Skip to content
This repository has been archived by the owner on Dec 18, 2024. It is now read-only.

RuntimeError: view size is not compatible with input tensor's size #66

Closed
semel1 opened this issue Feb 15, 2022 · 2 comments
Closed

RuntimeError: view size is not compatible with input tensor's size #66

semel1 opened this issue Feb 15, 2022 · 2 comments

Comments

@semel1
Copy link

semel1 commented Feb 15, 2022

Successfully run:
python run_monodepth.py -t dpt_large

However attempt to run:
python run_monodepth.py (with dpt_hybrid (default) )

I've got an error:
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

My great appreciation for help to resolving this issue.
How/where I should "Use .reshape(...) instead." As it suggests ?

@olegsinavski
Copy link

@semel1 I faced the same issue and it turned out that my timm version was older than DPT requires. After installing timm==0.4.5 from the requirements, it all works now

@semel1
Copy link
Author

semel1 commented Apr 27, 2022

That's work. Thank you

@semel1 semel1 closed this as completed Apr 27, 2022
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants