I have converted my Yolov3 model into tflite model using the following link - https://github.com/guichristmann/edge-tpu-tiny-yolo
The converted model can be found here. https://drive.google.com/drive/folders/181npG1SDJnMBBQOm_gXbL0XguSA4gGsy?usp=sharing
When I try to run the inference.py script, I get the following error.
(yolov3-tflite2) C:\pycoral_venv\Scripts\coral\pycoral1>python 5-classes-training\inference.py --model 5-classes-training\quant_model_edgetpu.tflite --anchors 5-classes-training\anchors.txt --classes 5-classes-training\classes.txt --image 5-classes-training\holes-test-input.jpg --edge_tpu --quant 2021-08-23 10:34:20.449509: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cudart64_100.dll'; dlerror: cudart64_100.dll not found 2021-08-23 10:34:20.449567: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. Allocating tensors. Traceback (most recent call last): File "5-classes-training\inference.py", line 228, in interpreter.allocate_tensors() File "C:\Users\Aksqwe\Anaconda3\envs\yolov3-tflite2\lib\site-packages\tensorflow_core\lite\python\interpreter.py", line 244, in allocate_tensors return self._interpreter.AllocateTensors() File "C:\Users\Aksqwe\Anaconda3\envs\yolov3-tflite2\lib\site-packages\tensorflow_core\lite\python\interpreter_wrapper\tensorflow_wrap_interpreter_wrapper.py", line 106, in AllocateTensors return _tensorflow_wrap_interpreter_wrapper.InterpreterWrapper_AllocateTensors(self) RuntimeError: Internal: Unsupported data type in custom op handler: -1328842432Node number 1 (EdgeTpuDelegateForCustomOp) failed to prepare.
The current conda environment(windows 10) consists: Python 3.7.3 Tensorflow: 1.15.0 Keras 2.2.4 tflite_runtime 2.5.0
Please let me know if there is any lead for me to solve this error. Thank you all in advance! :)