hi,
I converted yolov8n.pt to a tflite file using:the following command “yolo export model=yolov8n.pt format=tflite”. This command line created a tflite file: yolov8n_float16.tflite
When I try to convert and quantized the tflite file so that it can compile to run on Edge TPU devices like the [Coral USB Accelerator] using the command: “edgetpu_compiler yolov8n_float16.tflite”, I get a error statement as follows:
Edge TPU Compiler version 16.0.384591198
Started a compilation timeout timer of 180 seconds.
ERROR: Regular TensorFlow ops are not supported by this interpreter. Make sure you apply/link the Flex delegate before inference.
ERROR: Node number 11 (FlexSplitV) failed to prepare.
*Compilation failed: Model failed in Tflite interpreter. Please ensure model can be loaded/run in Tflite interpreter.*
*Compilation child process completed within timeout period.*
*Compilation failed!*
When I convert a yolov5 model to a tflite file and try to convert and quantized the tflite file so that it can compile to run on Edge TPU devices using the command “edgetpu_compiler yolov5s-fp16.tflite” I dont get a error, I get the statement as follows:
*Edge TPU Compiler version 16.0.384591198*
*Started a compilation timeout timer of 180 seconds.*
*Model compiled successfully in 67 ms.*
*Input model: yolov5s-fp16.tflite*
*Input size: 13.88MiB*
*Output model: yolov5s-fp16_edgetpu.tflite*
*Output size: 13.87MiB*
*On-chip memory used for caching model parameters: 0.00B*
*On-chip memory remaining for caching model parameters: 0.00B*
*Off-chip memory used for streaming uncached model parameters: 0.00B*
*Number of Edge TPU subgraphs: 0*
*Total number of operations: 386*
*Operation log: yolov5s-fp16_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: 0*
*Number of operations that will run on CPU: 386*
*See the operation log file for individual operation details.*
*Compilation child process completed within timeout period.*
*Compilation succeeded!*
Do you know why the yolov8 file doesn’t convert