Machine Learning

1 readers

1 users here now

Community Rules:

Be nice. No offensive behavior, insults or attacks: we encourage a diverse community in which members feel safe and have a voice.
Make your post clear and comprehensive: posts that lack insight or effort will be removed. (ex: questions which are easily googled)
Beginner or career related questions go elsewhere. This community is focused in discussion of research and new projects that advance the state-of-the-art.
Limit self-promotion. Comments and posts should be first and foremost about topics of interest to ML observers and practitioners. Limited self-promotion is tolerated, but the sub is not here as merely a source for free advertisement. Such posts will be removed at the discretion of the mods.

founded 11 months ago

MODERATORS

communick@academy.garden

[D] Didn't find op for builtin opcode 'SHAPE' version '1'. Version mismatch (alien.top)

submitted 10 months ago by sumolpp@alien.top to c/machinelearning@academy.garden

1 comments fedilink hide all child comments

Hey guys! Learning Tensorflow lite.

Ive been working on a project that involves image processing and I have successfully dumped a model onto my ESP32-S3-DevKitC-1 board. However, while running the program, I get the following errors while allocating tensors:

Didn't find op for builtin opcode 'SHAPE' version '1'. An older version of this builtin might be supported. Are you using an old TFLite binary with a newer model?

Failed to get registration from op code SHAPE

AllocateTensors() failed

On furthur research, I have come to believe its an OP code version mismatch, which I dont know how to change.

Note: Just to test my idea, I compiled another dummy model with only one convolutional layer instead of 4 (which my original model has), and that seems to work without throwing any errors. Only when I use my 4 layer model, it seems to throw this error.

How do I resolve this error? Please help me out

top 1 comments

sorted by: hot top controversial new old

[–] PM_ME_YOUR_BAYES@alien.top 1 points 10 months ago

stackoverflow.com