From ba2ff90ac4e11d32ae5b90d0401e31e8a868ddad Mon Sep 17 00:00:00 2001
From: galthran-wq <levmorozov900@gmail.com>
Date: Wed, 12 Feb 2025 16:35:16 +0000
Subject: [PATCH] mtcnn batching

---
 deepface/models/face_detection/MtCnn.py | 62 +++++++++++++++----------
 1 file changed, 38 insertions(+), 24 deletions(-)

diff --git a/deepface/models/face_detection/MtCnn.py b/deepface/models/face_detection/MtCnn.py
index 014e4a5..8f4c624 100644
--- a/deepface/models/face_detection/MtCnn.py
+++ b/deepface/models/face_detection/MtCnn.py
@@ -1,5 +1,5 @@
 # built-in dependencies
-from typing import List
+from typing import List, Union
 
 # 3rd party dependencies
 import numpy as np
@@ -17,44 +17,58 @@ class MtCnnClient(Detector):
     def __init__(self):
         self.model = MTCNN()
 
-    def detect_faces(self, img: np.ndarray) -> List[FacialAreaRegion]:
+    def detect_faces(
+        self, 
+        img: Union[np.ndarray, 
+        List[np.ndarray]]
+    ) -> Union[List[FacialAreaRegion], List[List[FacialAreaRegion]]]:
         """
-        Detect and align face with mtcnn
+        Detect and align faces with mtcnn for a list of images
 
         Args:
-            img (np.ndarray): pre-loaded image as numpy array
+            imgs (Union[np.ndarray, List[np.ndarray]]): 
+                pre-loaded image as numpy array or a list of those
 
         Returns:
-            results (List[FacialAreaRegion]): A list of FacialAreaRegion objects
+            results (Union[List[FacialAreaRegion], List[List[FacialAreaRegion]]]): 
+                A list of FacialAreaRegion objects for a single image or a list of lists of FacialAreaRegion objects for each image
         """
 
+        if not isinstance(img, list):
+            img = [img]
+
         resp = []
 
         # mtcnn expects RGB but OpenCV read BGR
         # img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
-        img_rgb = img[:, :, ::-1]
+        img_rgb = [img[:, :, ::-1] for img in img]
         detections = self.model.detect_faces(img_rgb)
 
-        if detections is not None and len(detections) > 0:
+        for image_detections in detections:
+            image_resp = []
+            if image_detections is not None and len(image_detections) > 0:
+                for current_detection in image_detections:
+                    x, y, w, h = current_detection["box"]
+                    confidence = current_detection["confidence"]
+                    # mtcnn detector assigns left eye with respect to the observer
+                    # but we are setting it with respect to the person itself
+                    left_eye = current_detection["keypoints"]["right_eye"]
+                    right_eye = current_detection["keypoints"]["left_eye"]
 
-            for current_detection in detections:
-                x, y, w, h = current_detection["box"]
-                confidence = current_detection["confidence"]
-                # mtcnn detector assigns left eye with respect to the observer
-                # but we are setting it with respect to the person itself
-                left_eye = current_detection["keypoints"]["right_eye"]
-                right_eye = current_detection["keypoints"]["left_eye"]
+                    facial_area = FacialAreaRegion(
+                        x=x,
+                        y=y,
+                        w=w,
+                        h=h,
+                        left_eye=left_eye,
+                        right_eye=right_eye,
+                        confidence=confidence,
+                    )
 
-                facial_area = FacialAreaRegion(
-                    x=x,
-                    y=y,
-                    w=w,
-                    h=h,
-                    left_eye=left_eye,
-                    right_eye=right_eye,
-                    confidence=confidence,
-                )
+                    image_resp.append(facial_area)
 
-                resp.append(facial_area)
+            resp.append(image_resp)
 
+        if len(resp) == 1:
+            return resp[0]
         return resp