More mypy cleanup (#22658)

* Halfway point for fixing data processing

* Fix mixin types missing

* Cleanup LPR mypy

* Cleanup audio mypy

* Cleanup bird mypy

* Cleanup mypy for custom classification

* remove whisper

* Fix DB typing

* Cleanup events mypy

* Clenaup

* fix type evaluation

* Cleanup

* Fix broken imports

frigate/data_processing/real_time/audio_transcription.py

@@ -4,7 +4,7 @@ import logging
 import os
 import queue
 import threading
-from typing import Optional
+from typing import Any, Optional
 
 import numpy as np
 
@@ -39,11 +39,11 @@ class AudioTranscriptionRealTimeProcessor(RealTimeProcessorApi):
         self.config = config
         self.camera_config = camera_config
         self.requestor = requestor
-        self.stream = None
-        self.whisper_model = None
+        self.stream: Any = None
+        self.whisper_model: FasterWhisperASR | None = None
         self.model_runner = model_runner
-        self.transcription_segments = []
-        self.audio_queue = queue.Queue()
+        self.transcription_segments: list[str] = []
+        self.audio_queue: queue.Queue[tuple[dict[str, Any], np.ndarray]] = queue.Queue()
         self.stop_event = stop_event
 
     def __build_recognizer(self) -> None:
@@ -142,10 +142,10 @@ class AudioTranscriptionRealTimeProcessor(RealTimeProcessorApi):
             logger.error(f"Error processing audio stream: {e}")
             return None
 
-    def process_frame(self, obj_data: dict[str, any], frame: np.ndarray) -> None:
+    def process_frame(self, obj_data: dict[str, Any], frame: np.ndarray) -> None:
         pass
 
-    def process_audio(self, obj_data: dict[str, any], audio: np.ndarray) -> bool | None:
+    def process_audio(self, obj_data: dict[str, Any], audio: np.ndarray) -> bool | None:
         if audio is None or audio.size == 0:
             logger.debug("No audio data provided for transcription")
             return None
@@ -269,13 +269,13 @@ class AudioTranscriptionRealTimeProcessor(RealTimeProcessorApi):
         )
 
     def handle_request(
-        self, topic: str, request_data: dict[str, any]
-    ) -> dict[str, any] | None:
+        self, topic: str, request_data: dict[str, Any]
+    ) -> dict[str, Any] | None:
         if topic == "clear_audio_recognizer":
             self.stream = None
             self.__build_recognizer()
             return {"message": "Audio recognizer cleared and rebuilt", "success": True}
         return None
 
-    def expire_object(self, object_id: str) -> None:
+    def expire_object(self, object_id: str, camera: str) -> None:
         pass

frigate/data_processing/real_time/bird.py

@@ -14,7 +14,7 @@ from frigate.comms.event_metadata_updater import (
 from frigate.config import FrigateConfig
 from frigate.const import MODEL_CACHE_DIR
 from frigate.log import suppress_stderr_during
-from frigate.util.object import calculate_region
+from frigate.util.image import calculate_region
 
 from ..types import DataProcessorMetrics
 from .api import RealTimeProcessorApi
@@ -35,10 +35,10 @@ class BirdRealTimeProcessor(RealTimeProcessorApi):
         metrics: DataProcessorMetrics,
     ):
         super().__init__(config, metrics)
-        self.interpreter: Interpreter = None
+        self.interpreter: Interpreter | None = None
         self.sub_label_publisher = sub_label_publisher
-        self.tensor_input_details: dict[str, Any] = None
-        self.tensor_output_details: dict[str, Any] = None
+        self.tensor_input_details: list[dict[str, Any]] | None = None
+        self.tensor_output_details: list[dict[str, Any]] | None = None
         self.detected_birds: dict[str, float] = {}
         self.labelmap: dict[int, str] = {}
 
@@ -61,7 +61,7 @@ class BirdRealTimeProcessor(RealTimeProcessorApi):
             self.downloader = ModelDownloader(
                 model_name="bird",
                 download_path=download_path,
-                file_names=self.model_files.keys(),
+                file_names=list(self.model_files.keys()),
                 download_func=self.__download_models,
                 complete_func=self.__build_detector,
             )
@@ -102,8 +102,12 @@ class BirdRealTimeProcessor(RealTimeProcessorApi):
                 i += 1
                 line = f.readline()
 
-    def process_frame(self, obj_data, frame):
-        if not self.interpreter:
+    def process_frame(self, obj_data: dict[str, Any], frame: np.ndarray) -> None:
+        if (
+            not self.interpreter
+            or not self.tensor_input_details
+            or not self.tensor_output_details
+        ):
             return
 
         if obj_data["label"] != "bird":
@@ -145,7 +149,7 @@ class BirdRealTimeProcessor(RealTimeProcessorApi):
             self.tensor_output_details[0]["index"]
         )[0]
         probs = res / res.sum(axis=0)
-        best_id = np.argmax(probs)
+        best_id = int(np.argmax(probs))
 
         if best_id == 964:
             logger.debug("No bird classification was detected.")
@@ -179,9 +183,11 @@ class BirdRealTimeProcessor(RealTimeProcessorApi):
         self.config.classification = payload
         logger.debug("Bird classification config updated dynamically")
 
-    def handle_request(self, topic, request_data):
+    def handle_request(
+        self, topic: str, request_data: dict[str, Any]
+    ) -> dict[str, Any] | None:
         return None
 
-    def expire_object(self, object_id, camera):
+    def expire_object(self, object_id: str, camera: str) -> None:
         if object_id in self.detected_birds:
             self.detected_birds.pop(object_id)

frigate/data_processing/real_time/custom_classification.py

@@ -24,7 +24,8 @@ from frigate.const import CLIPS_DIR, MODEL_CACHE_DIR
 from frigate.log import suppress_stderr_during
 from frigate.types import TrackedObjectUpdateTypesEnum
 from frigate.util.builtin import EventsPerSecond, InferenceSpeed, load_labels
-from frigate.util.object import box_overlaps, calculate_region
+from frigate.util.image import calculate_region
+from frigate.util.object import box_overlaps
 
 from ..types import DataProcessorMetrics
 from .api import RealTimeProcessorApi
@@ -49,12 +50,16 @@ class CustomStateClassificationProcessor(RealTimeProcessorApi):
     ):
         super().__init__(config, metrics)
         self.model_config = model_config
+
+        if not self.model_config.name:
+            raise ValueError("Custom classification model name must be set.")
+
         self.requestor = requestor
         self.model_dir = os.path.join(MODEL_CACHE_DIR, self.model_config.name)
         self.train_dir = os.path.join(CLIPS_DIR, self.model_config.name, "train")
-        self.interpreter: Interpreter = None
-        self.tensor_input_details: dict[str, Any] | None = None
-        self.tensor_output_details: dict[str, Any] | None = None
+        self.interpreter: Interpreter | None = None
+        self.tensor_input_details: list[dict[str, Any]] | None = None
+        self.tensor_output_details: list[dict[str, Any]] | None = None
         self.labelmap: dict[int, str] = {}
         self.classifications_per_second = EventsPerSecond()
         self.state_history: dict[str, dict[str, Any]] = {}
@@ -63,7 +68,7 @@ class CustomStateClassificationProcessor(RealTimeProcessorApi):
             self.metrics
             and self.model_config.name in self.metrics.classification_speeds
         ):
-            self.inference_speed = InferenceSpeed(
+            self.inference_speed: InferenceSpeed | None = InferenceSpeed(
                 self.metrics.classification_speeds[self.model_config.name]
             )
         else:
@@ -172,12 +177,20 @@ class CustomStateClassificationProcessor(RealTimeProcessorApi):
 
         return None
 
-    def process_frame(self, frame_data: dict[str, Any], frame: np.ndarray):
+    def process_frame(self, frame_data: dict[str, Any], frame: np.ndarray) -> None:
+        if (
+            not self.model_config.name
+            or not self.model_config.state_config
+            or not self.tensor_input_details
+            or not self.tensor_output_details
+        ):
+            return
+
         if self.metrics and self.model_config.name in self.metrics.classification_cps:
             self.metrics.classification_cps[
                 self.model_config.name
             ].value = self.classifications_per_second.eps()
-        camera = frame_data.get("camera")
+        camera = str(frame_data.get("camera"))
 
         if camera not in self.model_config.state_config.cameras:
             return
@@ -283,7 +296,7 @@ class CustomStateClassificationProcessor(RealTimeProcessorApi):
         logger.debug(
             f"{self.model_config.name} Ran state classification with probabilities: {probs}"
         )
-        best_id = np.argmax(probs)
+        best_id = int(np.argmax(probs))
         score = round(probs[best_id], 2)
         self.__update_metrics(datetime.datetime.now().timestamp() - now)
 
@@ -319,7 +332,9 @@ class CustomStateClassificationProcessor(RealTimeProcessorApi):
                 verified_state,
             )
 
-    def handle_request(self, topic, request_data):
+    def handle_request(
+        self, topic: str, request_data: dict[str, Any]
+    ) -> dict[str, Any] | None:
         if topic == EmbeddingsRequestEnum.reload_classification_model.value:
             if request_data.get("model_name") == self.model_config.name:
                 self.__build_detector()
@@ -335,7 +350,7 @@ class CustomStateClassificationProcessor(RealTimeProcessorApi):
         else:
             return None
 
-    def expire_object(self, object_id, camera):
+    def expire_object(self, object_id: str, camera: str) -> None:
         pass
 
 
@@ -350,13 +365,17 @@ class CustomObjectClassificationProcessor(RealTimeProcessorApi):
     ):
         super().__init__(config, metrics)
         self.model_config = model_config
+
+        if not self.model_config.name:
+            raise ValueError("Custom classification model name must be set.")
+
         self.model_dir = os.path.join(MODEL_CACHE_DIR, self.model_config.name)
         self.train_dir = os.path.join(CLIPS_DIR, self.model_config.name, "train")
-        self.interpreter: Interpreter = None
+        self.interpreter: Interpreter | None = None
         self.sub_label_publisher = sub_label_publisher
         self.requestor = requestor
-        self.tensor_input_details: dict[str, Any] | None = None
-        self.tensor_output_details: dict[str, Any] | None = None
+        self.tensor_input_details: list[dict[str, Any]] | None = None
+        self.tensor_output_details: list[dict[str, Any]] | None = None
         self.classification_history: dict[str, list[tuple[str, float, float]]] = {}
         self.labelmap: dict[int, str] = {}
         self.classifications_per_second = EventsPerSecond()
@@ -365,7 +384,7 @@ class CustomObjectClassificationProcessor(RealTimeProcessorApi):
             self.metrics
             and self.model_config.name in self.metrics.classification_speeds
         ):
-            self.inference_speed = InferenceSpeed(
+            self.inference_speed: InferenceSpeed | None = InferenceSpeed(
                 self.metrics.classification_speeds[self.model_config.name]
             )
         else:
@@ -431,8 +450,8 @@ class CustomObjectClassificationProcessor(RealTimeProcessorApi):
             )
             return None, 0.0
 
-        label_counts = {}
-        label_scores = {}
+        label_counts: dict[str, int] = {}
+        label_scores: dict[str, list[float]] = {}
         total_attempts = len(history)
 
         for label, score, timestamp in history:
@@ -443,7 +462,7 @@ class CustomObjectClassificationProcessor(RealTimeProcessorApi):
             label_counts[label] += 1
             label_scores[label].append(score)
 
-        best_label = max(label_counts, key=label_counts.get)
+        best_label = max(label_counts, key=lambda k: label_counts[k])
         best_count = label_counts[best_label]
 
         consensus_threshold = total_attempts * 0.6
@@ -470,7 +489,15 @@ class CustomObjectClassificationProcessor(RealTimeProcessorApi):
         )
         return best_label, avg_score
 
-    def process_frame(self, obj_data, frame):
+    def process_frame(self, obj_data: dict[str, Any], frame: np.ndarray) -> None:
+        if (
+            not self.model_config.name
+            or not self.model_config.object_config
+            or not self.tensor_input_details
+            or not self.tensor_output_details
+        ):
+            return
+
         if self.metrics and self.model_config.name in self.metrics.classification_cps:
             self.metrics.classification_cps[
                 self.model_config.name
@@ -555,7 +582,7 @@ class CustomObjectClassificationProcessor(RealTimeProcessorApi):
         logger.debug(
             f"{self.model_config.name} Ran object classification with probabilities: {probs}"
         )
-        best_id = np.argmax(probs)
+        best_id = int(np.argmax(probs))
         score = round(probs[best_id], 2)
         self.__update_metrics(datetime.datetime.now().timestamp() - now)
 
@@ -650,7 +677,7 @@ class CustomObjectClassificationProcessor(RealTimeProcessorApi):
                     ),
                 )
 
-    def handle_request(self, topic, request_data):
+    def handle_request(self, topic: str, request_data: dict) -> dict | None:
         if topic == EmbeddingsRequestEnum.reload_classification_model.value:
             if request_data.get("model_name") == self.model_config.name:
                 self.__build_detector()
@@ -666,12 +693,11 @@ class CustomObjectClassificationProcessor(RealTimeProcessorApi):
         else:
             return None
 
-    def expire_object(self, object_id, camera):
+    def expire_object(self, object_id: str, camera: str) -> None:
         if object_id in self.classification_history:
             self.classification_history.pop(object_id)
 
 
-@staticmethod
 def write_classification_attempt(
     folder: str,
     frame: np.ndarray,

frigate/data_processing/real_time/face.py

@@ -52,11 +52,11 @@ class FaceRealTimeProcessor(RealTimeProcessorApi):
         self.face_config = config.face_recognition
         self.requestor = requestor
         self.sub_label_publisher = sub_label_publisher
-        self.face_detector: cv2.FaceDetectorYN = None
+        self.face_detector: cv2.FaceDetectorYN | None = None
         self.requires_face_detection = "face" not in self.config.objects.all_objects
         self.person_face_history: dict[str, list[tuple[str, float, int]]] = {}
         self.camera_current_people: dict[str, list[str]] = {}
-        self.recognizer: FaceRecognizer | None = None
+        self.recognizer: FaceRecognizer
         self.faces_per_second = EventsPerSecond()
         self.inference_speed = InferenceSpeed(self.metrics.face_rec_speed)
 
@@ -78,7 +78,7 @@ class FaceRealTimeProcessor(RealTimeProcessorApi):
             self.downloader = ModelDownloader(
                 model_name="facedet",
                 download_path=download_path,
-                file_names=self.model_files.keys(),
+                file_names=list(self.model_files.keys()),
                 download_func=self.__download_models,
                 complete_func=self.__build_detector,
             )
@@ -134,7 +134,7 @@ class FaceRealTimeProcessor(RealTimeProcessorApi):
 
     def __detect_face(
         self, input: np.ndarray, threshold: float
-    ) -> tuple[int, int, int, int]:
+    ) -> tuple[int, int, int, int] | None:
         """Detect faces in input image."""
         if not self.face_detector:
             return None
@@ -153,7 +153,7 @@ class FaceRealTimeProcessor(RealTimeProcessorApi):
         faces = self.face_detector.detect(input)
 
         if faces is None or faces[1] is None:
-            return None
+            return None  # type: ignore[unreachable]
 
         face = None
 
@@ -168,7 +168,7 @@ class FaceRealTimeProcessor(RealTimeProcessorApi):
             h: int = int(raw_bbox[3] / scale_factor)
             bbox = (x, y, x + w, y + h)
 
-            if face is None or area(bbox) > area(face):
+            if face is None or area(bbox) > area(face):  # type: ignore[unreachable]
                 face = bbox
 
         return face
@@ -177,7 +177,7 @@ class FaceRealTimeProcessor(RealTimeProcessorApi):
         self.faces_per_second.update()
         self.inference_speed.update(duration)
 
-    def process_frame(self, obj_data: dict[str, Any], frame: np.ndarray):
+    def process_frame(self, obj_data: dict[str, Any], frame: np.ndarray) -> None:
         """Look for faces in image."""
         self.metrics.face_rec_fps.value = self.faces_per_second.eps()
         camera = obj_data["camera"]
@@ -349,7 +349,9 @@ class FaceRealTimeProcessor(RealTimeProcessorApi):
 
         self.__update_metrics(datetime.datetime.now().timestamp() - start)
 
-    def handle_request(self, topic, request_data) -> dict[str, Any] | None:
+    def handle_request(
+        self, topic: str, request_data: dict[str, Any]
+    ) -> dict[str, Any] | None:
         if topic == EmbeddingsRequestEnum.clear_face_classifier.value:
             self.recognizer.clear()
             return {"success": True, "message": "Face classifier cleared."}
@@ -432,7 +434,7 @@ class FaceRealTimeProcessor(RealTimeProcessorApi):
                 img = cv2.imread(current_file)
 
             if img is None:
-                return {
+                return {  # type: ignore[unreachable]
                     "message": "Invalid image file.",
                     "success": False,
                 }
@@ -469,7 +471,9 @@ class FaceRealTimeProcessor(RealTimeProcessorApi):
                 "score": score,
             }
 
-    def expire_object(self, object_id: str, camera: str):
+        return None
+
+    def expire_object(self, object_id: str, camera: str) -> None:
         if object_id in self.person_face_history:
             self.person_face_history.pop(object_id)
 
@@ -478,7 +482,7 @@ class FaceRealTimeProcessor(RealTimeProcessorApi):
 
     def weighted_average(
         self, results_list: list[tuple[str, float, int]], max_weight: int = 4000
-    ):
+    ) -> tuple[str | None, float]:
         """
         Calculates a robust weighted average, capping the area weight and giving more weight to higher scores.
 
@@ -493,8 +497,8 @@ class FaceRealTimeProcessor(RealTimeProcessorApi):
             return None, 0.0
 
         counts: dict[str, int] = {}
-        weighted_scores: dict[str, int] = {}
-        total_weights: dict[str, int] = {}
+        weighted_scores: dict[str, float] = {}
+        total_weights: dict[str, float] = {}
 
         for name, score, face_area in results_list:
             if name == "unknown":
@@ -509,7 +513,7 @@ class FaceRealTimeProcessor(RealTimeProcessorApi):
             counts[name] += 1
 
             # Capped weight based on face area
-            weight = min(face_area, max_weight)
+            weight: float = min(face_area, max_weight)
 
             # Score-based weighting (higher scores get more weight)
             weight *= (score - self.face_config.unknown_score) * 10
@@ -519,7 +523,7 @@ class FaceRealTimeProcessor(RealTimeProcessorApi):
         if not weighted_scores:
             return None, 0.0
 
-        best_name = max(weighted_scores, key=weighted_scores.get)
+        best_name = max(weighted_scores, key=lambda k: weighted_scores[k])
 
         # If the number of faces for this person < min_faces, we are not confident it is a correct result
         if counts[best_name] < self.face_config.min_faces:

frigate/data_processing/real_time/license_plate.py

@@ -61,14 +61,16 @@ class LicensePlateRealTimeProcessor(LicensePlateProcessingMixin, RealTimeProcess
         self,
         obj_data: dict[str, Any],
         frame: np.ndarray,
-        dedicated_lpr: bool | None = False,
-    ):
+        dedicated_lpr: bool = False,
+    ) -> None:
         """Look for license plates in image."""
         self.lpr_process(obj_data, frame, dedicated_lpr)
 
-    def handle_request(self, topic, request_data) -> dict[str, Any] | None:
-        return
+    def handle_request(
+        self, topic: str, request_data: dict[str, Any]
+    ) -> dict[str, Any] | None:
+        return None
 
-    def expire_object(self, object_id: str, camera: str):
+    def expire_object(self, object_id: str, camera: str) -> None:
         """Expire lpr objects."""
         self.lpr_expire(object_id, camera)