Fixes (#18500)

* fix i18n keys

* hide disable from context menu for viewers

* Fix auto live check for default dashboard and camera groups

Disabling the Automatic Live View switch in Settings should prevent streaming from occurring. Overriding any settings in a camera group will override the global setting. The check here incorrectly always returned false instead of undefined.

* clarify hardware accelerated enrichments

* clarify

* add note about detect stream to face rec docs

* add note about low end Dahuas for autotracking

* Catch invalid face box / image

* Video tab tweaks

With the changes in https://github.com/blakeblackshear/frigate/pull/18220, the video tab in the Tracked Object Details pane now correctly trims the in-browser HLS video. Because of keyframes and record/detect stream differences, we can manually subtract a couple of seconds from the event start_time to ensure the first few frames aren't cut off from the video

* Clarify

* Don't use Migraphx by default

* Provide better support for running embeddings on GPU

* correctly join cameras

* Adjust blur confidence reduction

---------

Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>

frigate/api/classification.py

@@ -154,7 +154,25 @@ def train_face(request: Request, name: str, body: dict = None):
         x2 = x1 + int(face_box[2] * detect_config.width) - 4
         y2 = y1 + int(face_box[3] * detect_config.height) - 4
         face = snapshot[y1:y2, x1:x2]
-        cv2.imwrite(os.path.join(new_file_folder, new_name), face)
+        success = True
+
+        if face.size > 0:
+            try:
+                cv2.imwrite(os.path.join(new_file_folder, new_name), face)
+                success = True
+            except Exception:
+                pass
+
+        if not success:
+            return JSONResponse(
+                content=(
+                    {
+                        "success": False,
+                        "message": "Invalid face box or no face exists",
+                    }
+                ),
+                status_code=404,
+            )
 
     context: EmbeddingsContext = request.app.embeddings
     context.clear_face_classifier()

frigate/data_processing/common/face/model.py

@@ -108,21 +108,21 @@ class FaceRecognizer(ABC):
             image, M, (output_width, output_height), flags=cv2.INTER_CUBIC
         )
 
-    def get_blur_factor(self, input: np.ndarray) -> float:
-        """Calculates the factor for the confidence based on the blur of the image."""
+    def get_blur_confidence_reduction(self, input: np.ndarray) -> tuple[float, float]:
+        """Calculates the reduction in confidence based on the blur of the image."""
         if not self.config.face_recognition.blur_confidence_filter:
             return 1.0
 
         variance = cv2.Laplacian(input, cv2.CV_64F).var()
 
-        if variance < 60:  # image is very blurry
-            return 0.96
-        elif variance < 70:  # image moderately blurry
-            return 0.98
-        elif variance < 80:  # image is slightly blurry
-            return 0.99
+        if variance < 80:  # image is very blurry
+            return variance, 0.05
+        elif variance < 100:  # image moderately blurry
+            return variance, 0.03
+        elif variance < 150:  # image is slightly blurry
+            return variance, 0.01
         else:
-            return 1.0
+            return variance, 0.0
 
 
 def similarity_to_confidence(
@@ -234,8 +234,8 @@ class FaceNetRecognizer(FaceRecognizer):
         # face recognition is best run on grayscale images
 
         # get blur factor before aligning face
-        blur_factor = self.get_blur_factor(face_image)
-        logger.debug(f"face detected with blurriness {blur_factor}")
+        variance, blur_reduction = self.get_blur_confidence_reduction(face_image)
+        logger.debug(f"face detected with blurriness {variance}")
 
         # align face and run recognition
         img = self.align_face(face_image, face_image.shape[1], face_image.shape[0])
@@ -258,7 +258,7 @@ class FaceNetRecognizer(FaceRecognizer):
                 score = confidence
                 label = name
 
-        return label, round(score * blur_factor, 2)
+        return label, round(score - blur_reduction, 2)
 
 
 class ArcFaceRecognizer(FaceRecognizer):
@@ -344,9 +344,9 @@ class ArcFaceRecognizer(FaceRecognizer):
 
         # face recognition is best run on grayscale images
 
-        # get blur factor before aligning face
-        blur_factor = self.get_blur_factor(face_image)
-        logger.debug(f"face detected with blurriness {blur_factor}")
+        # get blur reduction before aligning face
+        variance, blur_reduction = self.get_blur_confidence_reduction(face_image)
+        logger.debug(f"face detected with blurriness {variance}")
 
         # align face and run recognition
         img = self.align_face(face_image, face_image.shape[1], face_image.shape[0])
@@ -367,4 +367,4 @@ class ArcFaceRecognizer(FaceRecognizer):
                 score = confidence
                 label = name
 
-        return label, round(score * blur_factor, 2)
+        return label, round(score - blur_reduction, 2)

frigate/util/model.py

@@ -345,6 +345,13 @@ def get_ort_providers(
                     "device_type": device,
                 }
             )
+        elif provider == "MIGraphXExecutionProvider":
+            # MIGraphX uses more CPU than ROCM, while also being the same speed
+            if device == "MIGraphX":
+                providers.append(provider)
+                options.append({})
+            else:
+                continue
         elif provider == "CPUExecutionProvider":
             providers.append(provider)
             options.append(