tvm
tvm copied to clipboard
[TFLite] Support quantized GREATER op in TFLite frontend
Support GREATER quantization operation conversion as part of issue #9187
cc @leandron and @lhutton1 for a second look
@dchauhan-arm just a friendly ping to update this PR with quantised testing for the operator.
yes, what I think I'll do is rewrite a test specifically for the greater op, and compare output of tvm against tflite.
@lhutton1 can you have another look on this one?
I believe its still waiting on an update, @dchauhan-arm please let me know if that's not the case
cc @lhutton1 for a second (second) look
hmmm looks like there's a seg fault happening in test_elemwise[_test_greater]
on aarch64 CI, so maybe there is an issue with this version of tensorflow on aarch64
With tflite 2.9.1 test_elemwise[_test_greater]
does not fail any more. We should wait for #12130 and #12131 to be merged.
This is now unblocked by https://github.com/apache/tvm/pull/12738 - @dchauhan-arm can you remove the conflict and resubmit this for CI to check?