-
Notifications
You must be signed in to change notification settings - Fork 84
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
Design for operators with dynamic shape functions #948
Comments
Merged
causten
pushed a commit
that referenced
this issue
Sep 16, 2021
Add Loop operator for opset version 13. Notes: 1) Default max iteration number is 10 if no max iteration number is provided 2) To change the max iter number, a user can set the max_loop_iterations in the onnx_option struct when parsing a model. 3) The returned shape of the scan output is from the max_loop_iterations even the actual loop num is less than that. This issue also applies to other operators like NonZero and NonMaxSuppression. A issue #948 is created to track this and to be resolved later. Co-authored-by: Paul <pfultz2@yahoo.com> Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>
Merged
causten
pushed a commit
that referenced
this issue
Oct 28, 2021
This PR is the ref implementation of the nonmaxsuppression operator. It always returns the max possible output shape, which is the problem tracked in issue #948.
CharlieL7
changed the title
Operator dynamic output shape
Operators with dynamic shape functions
Jan 6, 2023
For reference we currently create a buffer of maximum size for NonMaxSuppression using the |
CharlieL7
changed the title
Operators with dynamic shape functions
Design for operators with dynamic shape functions
Jan 6, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Some operators output dynamic shape for different inputs (even input shapes are the same), but MIGraphX can only generate fixed output shape. Because of this, MIGraphX always use the max possible output shape even the actual output shape is smaller.
This problem applies to: Loop, NonZero, NonMaxSuppression. We need to come up with a general approach to resolve this problem.
The text was updated successfully, but these errors were encountered: