Handle edgetpu model inference (#5372)

* Handle edgetpu model inference

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Cleanup

Rename `tflite_runtime.interpreter as tflite` to `tflite_runtime.interpreter as tflri` to avoid conflict with existing `tflite` boolean

Co-authored-by: Nam Vu <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Glenn Jocher <[email protected]>

Author: 4 people

detect.py

@@ -8,6 +8,7 @@
 
 import argparse
 import os
+import platform
 import sys
 from pathlib import Path
 
@@ -107,7 +108,14 @@ def wrap_frozen_graph(gd, inputs, outputs):
         elif saved_model:
             model = tf.keras.models.load_model(w)
         elif tflite:
-            interpreter = tf.lite.Interpreter(model_path=w)  # load TFLite model
+            if "edgetpu" in w:  # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python
+                import tflite_runtime.interpreter as tflri
+                delegate = {'Linux': 'libedgetpu.so.1',  # install libedgetpu https://coral.ai/software/#edgetpu-runtime
+                            'Darwin': 'libedgetpu.1.dylib',
+                            'Windows': 'edgetpu.dll'}[platform.system()]
+                interpreter = tflri.Interpreter(model_path=w, experimental_delegates=[tflri.load_delegate(delegate)])
+            else:
+                interpreter = tf.lite.Interpreter(model_path=w)  # load TFLite model
             interpreter.allocate_tensors()  # allocate
             input_details = interpreter.get_input_details()  # inputs
             output_details = interpreter.get_output_details()  # outputs