Add argmax operator. #175
Open
Add argmax operator. #175
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
pixelspark
requested changes
Jul 18, 2023
| @@ -40,7 +40,9 @@ fn main(@builtin(global_invocation_id) global_id: vec3<u32>) { | |||
| Now for each reduced axis, iterate all values and reduce. Note, starting value may not always be zero. For | |||
| ReduceMin/Max we should initialize as NaN and keep a flag to check if we have seen at least one element -#} | |||
|
|
|||
| var accumulator = {% if op_type == "ReduceProd" %} {{ scalar_type }}(1) {% else %} Scalar() {% endif %}; | |||
| var accumulator = {% if op_type == "ReduceProd" %} {{ scalar_type }}(1) {% else %} Scalar() {% endif %}; | |||
| var max_element: Scalar = log(Scalar()); | |||
There was a problem hiding this comment.
Hm, perhaps add a note explaining why you initialize to log(Scalar()) (I assume it is a trick to initialize to -Inf so the first value is always higher).
| {% elif op_type == "ArgMax" %} | ||
| if(input_val > max_element) { | ||
| max_element = input_val; | ||
| accumulator = f32(count); |
There was a problem hiding this comment.
The output of ArgMax is actually specified as int64 (see here). This should work for now but we might have to fix it later.
There was a problem hiding this comment.
Good point, then it would probably make sense to move argmax out of reduce to not have to return mixed data types from reduce?
| @@ -223,6 +235,17 @@ fn reduce() { | |||
| &[3, 2], | |||
| ); | |||
|
|
|||
| // ONNX test case: do_not_keepdims with ArgMax | |||
There was a problem hiding this comment.
Can you also enable the corresponding test case in the ONNX backend test (Python scripts)?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds the argmax operator to wonnx.