how can the ai-edge-torch converter convert the operators supported on edgeTPU devices

[JinniPi]

Description of the bug:

• I converted the pytorch model format to tflite format with p2e quantization static. Then I compile the tflite file to run the EdgeTPU. But the problem is that almost operators aren't supported running on TPU. Instead, they will run on CPU.
• My question is: how can the ai-edge-torch converter convert the operators supported on edgeTPU devices?
• For example, here is my log:
• Model compiled successfully in 70 ms.

Input model: ZenNet-SA-M/rafdb_quant-m-sa_int8_pte.tflite
Input size: 1.57MiB
Output model: rafdb_quant-m-sa_int8_pte_edgetpu.tflite
Output size: 1.60MiB
On-chip memory used for caching model parameters: 0.00B
On-chip memory remaining for caching model parameters: 8.09MiB
Off-chip memory used for streaming uncached model parameters: 0.00B
Number of Edge TPU subgraphs: 1
Total number of operations: 243
Operation log: rafdb_quant-m-sa_int8_pte_edgetpu.log

Model successfully compiled but not all operations are supported by the Edge TPU. A percentage of the model will instead run on the CPU, which is slower. If possible, consider updating your model to use only operations supported by the Edge TPU. For details, visit g.co/coral/model-reqs.
Number of operations that will run on Edge TPU: 1
Number of operations that will run on CPU: 242
See the operation log file for individual operation details.
Compilation child process completed within timeout period.
Compilation succeeded!

Actual vs expected behavior:

The operators are supported on edgeTPU (not CPU)

Any other information you'd like to share?

No response

[pkgoogle]

Thanks for pointing this out. I don't believe this is 100% supported right now but would be a good optimization to have.