[Relay] Fix TFlite frontend for unpack, stridedslice #10333
Merged
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
We found this while converting an RNN model. The relay tflite frontend use squeeze at converting unpack, but when the unpack.axis=0, `None` is passed to relay.squeeze(), which would squeeze all dimensions with length 1, causing different results from TFLite. A possible fix might be, assign the unpack.axis as-is to relay.squeeze() As for stridedslice, when the tflite frontend handles shrink_axis_mask, the wrapped `begin` should be used, instead of the original one which can be negative. It can cause errors at https://github.com/apache/tvm/blob/d65ff6594d4d6db0062537a1d43c0504173b8e5c/include/tvm/topi/detail/strided_slice.h#L140 Related cases are also added to the python test.
chiwwang
requested review from
Huyuwei,
areusch,
comaniac,
icemelon,
jroesch,
junrushao,
jwfromm,
kazum,
mbrookhart,
merrymercy,
siju-samuel,
srkreddy1238,
tqchen and
yzhliu
as code owners
masahi
approved these changes
Feb 22, 2022
pfk-beta
pushed a commit
to pfk-beta/tvm
that referenced
this pull request
Apr 11, 2022
We found this while converting an RNN model. The relay tflite frontend use squeeze at converting unpack, but when the unpack.axis=0, `None` is passed to relay.squeeze(), which would squeeze all dimensions with length 1, causing different results from TFLite. A possible fix might be, assign the unpack.axis as-is to relay.squeeze() As for stridedslice, when the tflite frontend handles shrink_axis_mask, the wrapped `begin` should be used, instead of the original one which can be negative. It can cause errors at https://github.com/apache/tvm/blob/d65ff6594d4d6db0062537a1d43c0504173b8e5c/include/tvm/topi/detail/strided_slice.h#L140 Related cases are also added to the python test.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
We found this while converting an RNN model.
The relay tflite frontend use squeeze at converting unpack, but when the
unpack.axis=0,
Noneis passed to relay.squeeze(), which would squeezeall dimensions with length 1, causing different results from TFLite.
A possible fix might be, assign the unpack.axis as-is to relay.squeeze()
As for stridedslice, when the tflite frontend handles shrink_axis_mask,
the wrapped
beginshould be used, instead of the original one whichcan be negative. It can cause errors at
tvm/include/tvm/topi/detail/strided_slice.h
Line 140 in d65ff65
Related cases are also added to the python test.
Thanks for contributing to TVM! Please refer to guideline https://tvm.apache.org/docs/contribute/ for useful information and tips. After the pull request is submitted, please request code reviews from Reviewers by @ them in the pull request thread.