wasi_nn_openvino.c: remove the tensor layout adjustment logic #4308
Conversation
This file contains hidden or 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
the logic in question seems like an attempt to work around some application bugs. my wild guess is that it was for classification-example. cf. bytecodealliance/wasmtime#10867 because wasi-nn api doesn't provide a way for users to express their intended layout, it seems impossible to "fix" it here without risking to break other applications. btw, i suspect the condition "if (wasi_nn_tensor->dimensions->size == 4 || ov_dims[1] == 3)" in the code in question was meant "if (wasi_nn_tensor->dimensions->size == 4 && ov_dims[1] == 3)". this commit fixes it by removing it. after this change, the classification-example mentioned above produces similar inferences as with wasmtime. (i used the fixed version of tensor.bgr mentioned in bytecodealliance/wasmtime#10867) wasm-micro-runtime with this commit: ``` Found results, sorted top 5: [InferenceResult(963, 0.71130574), InferenceResult(762, 0.07070772), InferenceResult(909, 0.036355656), InferenceResult(926, 0.015456188), InferenceResult(567, 0.015344019)] ``` wasmtime: ``` Found results, sorted top 5: [InferenceResult(963, 0.7113058), InferenceResult(762, 0.070707425), InferenceResult(909, 0.036355816), InferenceResult(926, 0.01545616), InferenceResult(567, 0.015344027)] ``` wasm-micro-runtime without this commit: ``` Found results, sorted top 5: [InferenceResult(505, 0.097339325), InferenceResult(459, 0.053065795), InferenceResult(849, 0.03836019), InferenceResult(582, 0.036462624), InferenceResult(725, 0.030435428)] ```
yamt
requested review from
loganek,
lum1n0us,
no1wudi,
TianlongLiang,
wenyongh and
xujuntwt95329
as code owners
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.
the logic in question seems like an attempt to work around some application bugs.
my wild guess is that it was for classification-example. cf. bytecodealliance/wasmtime#10867
because wasi-nn api doesn't provide a way for users to express their intended layout, it seems impossible to "fix" it here without risking to break other applications.
btw, i suspect the condition
"if (wasi_nn_tensor->dimensions->size == 4 || ov_dims[1] == 3)" in the code in question was meant
"if (wasi_nn_tensor->dimensions->size == 4 && ov_dims[1] == 3)". this commit fixes it by removing it.
after this change, the classification-example mentioned above produces similar inferences as with wasmtime.
(i used the fixed version of tensor.bgr mentioned in bytecodealliance/wasmtime#10867)
wasm-micro-runtime with this commit:
wasmtime:
wasm-micro-runtime without this commit: