Didn't find op for builtin opcode 'EXP' version '2'. An older version of this builtin might be supported. Are you using an old TFLite binary with a newer model #71
Labels
comp:model
Model related isssues
Hardware:USB Accelerator
Coral USB Accelerator issues
subtype:ubuntu/linux
Ubuntu/Linux Build/installation issues
type:feature
Feature requests
Description
Hi!
I'm currently trying to compile a tensorflow lite model model_2.tflite for coral edge TPU, but I'm getting the error:
A get the same error when I run the lite model directly on the TPU using tflite_runtime.
The lite model was created from saved_model using:
It is integer (int8) quantized, and run well in a tensorflow default interpreter. How can I solve this problem for the Edge TPU?
Click to expand!
Issue Type
Feature Request
Operating System
Linux
Coral Device
USB Accelerator
Other Devices
No response
Programming Language
Other
Relevant Log Output
The text was updated successfully, but these errors were encountered: