remove tip that indicates other YOLO models may be supported.

docs/docs/configuration/object_detectors.md

@@ -161,12 +161,6 @@ A Tensorflow Lite is provided in the container at `/openvino-model/ssdlite_mobil
 
 [YOLOv9](https://github.com/dbro/frigate-detector-edgetpu-yolo9/releases/download/v1.0/yolov9-s-relu6-best_320_int8_edgetpu.tflite) models that are compiled for Tensorflow Lite and properly quantized are supported, but not included by default. To provide your own model, bind mount the file into the container and provide the path with `model.path`. Note that the model may require a custom label file (eg. [use this 17 label file](https://raw.githubusercontent.com/dbro/frigate-detector-edgetpu-yolo9/refs/heads/main/labels-coco17.txt) for the model linked above.)
 
-:::tip
-
-The YOLO detector has been designed to support YOLOv9 models, and may support other YOLO model architectures as well.
-
-:::
-
 <details>
   <summary>YOLOv9 Setup & Config</summary>
 

frigate/detectors/plugins/edgetpu_tfl.py

@@ -9,7 +9,6 @@ from typing_extensions import Literal
 
 from frigate.detectors.detection_api import DetectionApi
 from frigate.detectors.detector_config import BaseDetectorConfig, ModelTypeEnum
-from frigate.util.model import post_process_yolo
 
 try:
     from tflite_runtime.interpreter import Interpreter, load_delegate
@@ -81,7 +80,7 @@ class EdgeTpuTfl(DetectionApi):
         if self.model_type == ModelTypeEnum.yologeneric:
             logger.debug("Using YOLO preprocessing/postprocessing")
 
-            if len(self.tensor_output_details) not in [2,3]:
+            if len(self.tensor_output_details) not in [2, 3]:
                 logger.error(
                     f"Invalid count of output tensors in YOLO model. Found {len(self.tensor_output_details)}, expecting 2 or 3."
                 )
@@ -114,9 +113,7 @@ class EdgeTpuTfl(DetectionApi):
                     # to differentiate from (not used) max score tensor
                     output_classes_index = i
             if output_boxes_index is None or output_classes_index is None:
-                logger.warning(
+                logger.warning("Unrecognized model output, unexpected tensor shapes.")
-                    "Unrecognized model output, unexpected tensor shapes."
-                )
                 output_classes_index = (
                     0
                     if (output_boxes_index is None or output_classes_index == 1)
@@ -125,19 +122,14 @@ class EdgeTpuTfl(DetectionApi):
                 output_boxes_index = 1 if (output_boxes_index == 0) else 0
 
             scores_details = self.tensor_output_details[output_classes_index]
-            classes_count = scores_details["shape"][2]
             self.scores_tensor_index = scores_details["index"]
-            self.scores_scale, self.scores_zero_point = scores_details[
+            self.scores_scale, self.scores_zero_point = scores_details["quantization"]
-                "quantization"
-            ]
             # calculate the quantized version of the min_score
             self.min_score_quantized = int(
                 (self.min_logit_value / self.scores_scale) + self.scores_zero_point
             )
             self.logit_shift_to_positive_values = (
-                max(
+                max(0, math.ceil((128 + self.scores_zero_point) * self.scores_scale))
-                    0, math.ceil((128 + self.scores_zero_point) * self.scores_scale)
-                )
                 + 1
             )  # round up
 
@@ -145,11 +137,7 @@ class EdgeTpuTfl(DetectionApi):
             self.boxes_tensor_index = boxes_details["index"]
             self.boxes_scale, self.boxes_zero_point = boxes_details["quantization"]
 
-        else:
+        elif self.model_type == ModelTypeEnum.ssd:
-            if self.model_type not in [ModelTypeEnum.ssd, None]:
-                logger.warning(
-                    f"Unsupported model_type '{self.model_type}' for EdgeTPU detector, falling back to SSD"
-                )
             logger.debug("Using SSD preprocessing/postprocessing")
 
             # SSD model indices (4 outputs: boxes, class_ids, scores, count)
@@ -162,6 +150,11 @@ class EdgeTpuTfl(DetectionApi):
             self.output_class_ids_index = None
             self.output_class_scores_index = None
 
+        else:
+            raise Exception(
+                f"{self.model_type} is currently not supported for edgetpu. See the docs for more info on supported models."
+            )
+
     def _generate_anchors_and_strides(self):
         # for decoding the bounding box DFL information into xy coordinates
         all_anchors = []
@@ -244,9 +237,7 @@ class EdgeTpuTfl(DetectionApi):
             scores_output_quantized = self.interpreter.get_tensor(
                 self.scores_tensor_index
             )[0]  # (2100, NC)
-            max_scores_quantized = np.max(
+            max_scores_quantized = np.max(scores_output_quantized, axis=1)  # (2100,)
-                scores_output_quantized, axis=1
-            )  # (2100,)
             mask = max_scores_quantized >= self.min_score_quantized  # (2100,)
 
             if not np.any(mask):
@@ -276,9 +267,7 @@ class EdgeTpuTfl(DetectionApi):
             # Softmax over the 16 bins
             dfl_max = np.max(dfl_distributions, axis=2, keepdims=True)
             dfl_exp = np.exp(dfl_distributions - dfl_max)
-            dfl_probs = dfl_exp / np.sum(
+            dfl_probs = dfl_exp / np.sum(dfl_exp, axis=2, keepdims=True)  # (N, 4, 16)
-                dfl_exp, axis=2, keepdims=True
-            )  # (N, 4, 16)
 
             # Weighted sum: (N, 4, 16) * (16,) -> (N, 4)
             distances = np.einsum("pcr,r->pc", dfl_probs, self.project)
@@ -334,8 +323,7 @@ class EdgeTpuTfl(DetectionApi):
             detections[:num_detections, 5] = final_boxes[:, 2] / self.model_width
             return detections
 
-        else:
+        elif self.model_type == ModelTypeEnum.ssd:
-            # Default SSD model
             self.determine_indexes_for_non_yolo_models()
             boxes = self.interpreter.tensor(self.tensor_output_details[0]["index"])()[0]
             class_ids = self.interpreter.tensor(
@@ -366,3 +354,8 @@ class EdgeTpuTfl(DetectionApi):
                 ]
 
             return detections
+
+        else:
+            raise Exception(
+                f"{self.model_type} is currently not supported for edgetpu. See the docs for more info on supported models."
+            )