New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
TFLu: Port TFL detection postprocess operator #43566
TFLu: Port TFL detection postprocess operator #43566
Conversation
Change-Id: I117f9e3f206f2433d55d60e680bf7aa04b954445
Adding support for running test_kernel_detection_postprocess_test with Renode by using pre-generated Flexbuffers::Builder data.
@mansnils Can you please resolve conflicts? Thanks! |
@mansnils Any update on this PR? Please. Thanks! |
Removing support for unknown output dimensions. Because it does not work with TFLiteEvalTensor API and it would require major changes in TFLu. |
Still having issues unfortunately :-/ The CI is failing with:
but it is not reproducible locally. My current guess is that the gcc version used as part of CI is old (gcc-6.3.0). I have a change under review that updates
to
which should mean that we use gcc 8.3.0 as part of CI. Let's see what happens when that change get merged. |
@advaitjain It seems like the updated docker didn't help, or do we need to rebase? |
…cess Manually resolved the following conflicts: tensorflow/lite/micro/micro_mutable_op_resolver.h
I wasn't able to reproduce locally because I hadn't done a Created #45286 to address this issue. This comment has some additional context. |
This is fixing issue: #43565