Added VIM3 components - There has to be a smarter way to select the LIB only when

needed on the platform.

docker/rootfs/etc/ld.so.conf.d/vim3.conf

@@ -0,0 +1,2 @@
+#VIM3 objects
+/lib/vim3

frigate/detectors/plugins/vim3.py

@@ -0,0 +1,79 @@
+import logging
+import numpy as np
+
+from frigate.detectors.detection_api import DetectionApi
+from frigate.detectors.detector_config import BaseDetectorConfig
+from typing import Literal
+from pydantic import Extra, Field
+
+try:
+    from tflite_runtime.interpreter import Interpreter, load_delegate
+except ModuleNotFoundError:
+    from tensorflow.lite.python.interpreter import Interpreter, load_delegate
+
+
+logger = logging.getLogger(__name__)
+
+DETECTOR_KEY = "vim3"
+
+
+class vim3DetectorConfig(BaseDetectorConfig):
+    type: Literal[DETECTOR_KEY]
+    device: str = Field(default=None, title="Device Type")
+
+
+class vim3Tfl(DetectionApi):
+    type_key = DETECTOR_KEY
+
+    def __init__(self, detector_config: vim3DetectorConfig):
+        device_config = {"device": "usb"}
+        if detector_config.device is not None:
+            device_config = {"device": detector_config.device}
+
+        edge_tpu_delegate = None
+
+        try:
+            logger.info(f"Attempting to register VIM3 TPU")
+            edge_tpu_delegate = load_delegate("libvx_delegate.so")
+            logger.info("TPU found")
+            self.interpreter = Interpreter(
+                model_path=detector_config.model.path or "/cpu_model.tflite",
+                experimental_delegates=[edge_tpu_delegate],
+            )
+        except ValueError:
+            logger.error(
+                "No EdgeTPU was detected. If you do not have a Accelerator (VIM3) device yet, you must configure CPU detectors."
+            )
+            raise
+
+        self.interpreter.allocate_tensors()
+
+        self.tensor_input_details = self.interpreter.get_input_details()
+        self.tensor_output_details = self.interpreter.get_output_details()
+
+    def detect_raw(self, tensor_input):
+        self.interpreter.set_tensor(self.tensor_input_details[0]["index"], tensor_input)
+        self.interpreter.invoke()
+
+        boxes = self.interpreter.tensor(self.tensor_output_details[0]["index"])()[0]
+        class_ids = self.interpreter.tensor(self.tensor_output_details[1]["index"])()[0]
+        scores = self.interpreter.tensor(self.tensor_output_details[2]["index"])()[0]
+        count = int(
+            self.interpreter.tensor(self.tensor_output_details[3]["index"])()[0]
+        )
+
+        detections = np.zeros((20, 6), np.float32)
+
+        for i in range(count):
+            if scores[i] < 0.4 or i == 20:
+                break
+            detections[i] = [
+                class_ids[i],
+                float(scores[i]),
+                boxes[i][0],
+                boxes[i][1],
+                boxes[i][2],
+                boxes[i][3],
+            ]
+
+        return detections