-
Notifications
You must be signed in to change notification settings - Fork 2.9k
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
Resize with mode linear is missing output elements #12019
Labels
core runtime
issues related to core runtime
Comments
hariharans29
added
core runtime
issues related to core runtime
component:operator
labels
Jun 28, 2022
@hariharans29 @yihonglyu - any comment/feedback is more than welcome. |
@diyessi Could you provide simple reproducer? Thanks. |
produces
I've also seen NaN's in the output where those 0s are. |
Could not reproduce using onnxruntime 1.14 or 1.15. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Describe the bug
Resize
withmode="linear"
and a specified output shape has garbage in the last output tensor elements. I see this for multiple coordinate transformation modes and input and output shapes. For a trivial example, with an input size of[1,1,1,1]
on a float input tensor whose single element is 1.0, resizing to[1, 2, 2, 1]
I get outputwhere the
[5, 10]
is wrong. I am running a number of these tests, usingi^2+1
as inputs, so these particular outputs seem likely to be uninitialized memory from earlier inputs. I also see bunches of NaNs in the bad elements.Urgency
None
System information
To Reproduce
I can give you a branch of a simple repo if you need one.
Expected behavior
In this case, all elements should be 1.
Additional context
nearest
mode doesn't seem to have any problems. I was actually trying to use ONNX Runtime to generate gold values for testing my own implementation for an accelerator and for creating a doc PR for the ONNX specification.The text was updated successfully, but these errors were encountered: