[JAX FE] Support lax.argmax operation for JAX #26671
Open
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
github-actions
bot
added
category: TF FE
halm-zenger
commented
Sep 19, 2024
| @@ -16,6 +16,7 @@ namespace jax { | |||
| void num_inputs_check(const NodeContext& context, size_t min_inputs, size_t max_inputs) { | |||
| auto inputs = context.inputs(); | |||
| FRONT_END_OP_CONVERSION_CHECK(inputs.size() >= min_inputs, "Got less inputs than expected"); | |||
| FRONT_END_OP_CONVERSION_CHECK(inputs.size() <= max_inputs, "Got more inputs than expected"); | |||
There was a problem hiding this comment.
Not sure if I can fix this here, or maybe it's better to move it to a separate PR?
There was a problem hiding this comment.
Thanks @rkazants Just to clarify, do you mean I should keep it here or I should move it to a separate PR?
halm-zenger
commented
Sep 19, 2024
| test_data = [] | ||
| for shape in input_shapes: | ||
| rank = len(shape) | ||
| # Only [0, rank - 1] are valid axes for lax.argmax |
There was a problem hiding this comment.
Just note that jax.numpy.argmax can accept negative axis, but jax.lax.argmax cannot.
There was a problem hiding this comment.
jax.numpy.argmax is a wrapper and it is represented with a sub-graph of lax operations. For us, it is sufficient to check lax operation.
halm-zenger
commented
Sep 19, 2024
| test_data = generate_shape_axis_pairs(input_shapes) | ||
|
|
||
| @pytest.mark.parametrize("params", test_data) | ||
| @pytest.mark.parametrize("index_dtype", [np.int32, np.int64]) |
There was a problem hiding this comment.
I didn't handle index_dtype in translate_argmax but everything seems fine. Is it okay?
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.
Details:
Tickets: