feat : deepFace custom

Pipfile

@@ -0,0 +1,11 @@
+[[source]]
+url = "https://pypi.org/simple"
+verify_ssl = true
+name = "pypi"
+
+[packages]
+
+[dev-packages]
+
+[requires]
+python_version = "3.11"

app.py

@@ -1,8 +1,7 @@
-import io
 import os
-from pytorch import mosaic_jiyeon
 from createTarget import extract_and_identify_faces_from_video
 from yoona_target import yoona_test
+import mosaic
 
 
 from flask import (Flask, request, send_file, jsonify)
@@ -42,40 +41,26 @@ def yoona():
 
 @app.route('/video', methods=['POST'])
 def handle_video():
-    print('start')
     video_file = request.files['video']
     image_count = int(request.form['imageSize'])
     print(image_count)
 
-    # 파일 저장 경로 지정, 여기서는 임시로 파일 이름으로 저장
-    #filename = os.path.join('tmp', file.filename)
     video_file.save(video_file.filename)
-    print('success file')
 
     image_paths = []
-    for i in range(1, image_count+1):
-        image_file = request.files['image{}'.format(i)]
-
+    for i in range(1, image_count + 1):
+        image_file = request.files[f'image{i}']
         if image_file:
-            # 이미지를 저장할 경로 지정 (여기서는 루트 디렉토리에 저장)
             filename, extension = os.path.splitext(image_file.filename)
-            image_filename = os.path.join('./pytorch/train/Gongyoo', f'image{i}{extension}')
+            image_filename = os.path.join('save/train/Gongyoo', f'image{i}{extension}')
             image_file.save(image_filename)
             image_paths.append(image_filename)
-            print('Image {} saved successfully.'.format(i))
-        else:
-            print('No image received for image{}.'.format(i))
-
-    print('success img')
-    print(image_paths)
-
-    # 여기서 파일을 처리하는 로직을 추가할 수 있습니다.
-    # 예를 들어, 처리된 파일을 다시 클라이언트에게 보낼 수 있습니다.
-    # 이 예시에서는 단순히 저장된 파일을 그대로 반환합니다.
-    print('start mosaic')
-    output_video_path = mosaic_jiyeon.mosaic(video_file.filename, image_paths)
+            print(f'Image {i} saved successfully.')
+
+    output_video_path = mosaic.mosaic(video_file.filename, image_paths)
+    # output_video_path = mosaic_jiyeon.mosaic(video_file.filename, image_paths)
     print(output_video_path)
-    return send_file(output_video_path, mimetype='video/mp4', as_attachment=True)
+    return send_file(output_video_path, mimetype='video/mp4', as_attachment=True, download_name='output_video.mp4')
 
 @app.route('/image', methods=['POST'])
 def image_test():

pytorch/mosaic_jiyeon.py → model_mosaic.py

@@ -6,9 +6,9 @@
 
 def mosaic(video_path, image_paths):
     # YOLOv5 모델 로드
-    # model = torch.hub.load('./pytorch/yolov5', 'custom', path='./pytorch/best.pt', source='local')
-    model = torch.hub.load('ultralytics/yolov5', 'custom', path='./pytorch/best.pt')
-    output_video_path = os.path.join('tmp', video_path)
+    # model = torch.hub.load('./save/yolov5', 'custom', path='./save/best.pt', source='local')
+    model = torch.hub.load('ultralytics/yolov5', 'custom', path='best.pt', force_reload=True)
+    output_video_path = os.path.join('save/tmp', video_path)
     # 특정 사람의 얼굴 이미지 로드
     # person_image = face_recognition.load_image_file("goognyoo.png")
     # person_encoding = face_recognition.face_encodings(person_image)[0]

mosaic.py

@@ -0,0 +1,90 @@
+import cv2
+import os
+from deepface import DeepFace
+import torch
+
+
+def mosaic(video_path, image_paths):
+    model_name = "Facenet"
+
+    output_video_path = os.path.join('tmp', 'output2.mp4')
+    cap = cv2.VideoCapture(video_path)
+    fps = int(cap.get(cv2.CAP_PROP_FPS))
+    frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    out = cv2.VideoWriter(output_video_path, cv2.VideoWriter.fourcc(*'mp4v'), fps, (frame_width, frame_height))
+    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))  # 동영상의 전체 프레임 수를 얻음
+
+    print(f"Total number of frames in the video: {total_frames}")
+
+    threshold = 0.465
+    not_threshold = 0.47
+
+    faces_dir = os.path.join('tmp', 'faces')
+    if not os.path.exists(faces_dir):
+        os.makedirs(faces_dir)
+
+    face_count = 0
+    current_frame_count = 0
+
+    model = torch.hub.load('ultralytics/yolov5', 'custom', path='macWideface.pt', force_reload=True)
+
+    embedding_list = []
+    for image_path in image_paths:
+        embedding_result = DeepFace.create_verification_result(
+            img1_path=image_path,
+            detector_backend='retinaface',
+            model_name=model_name,
+            enforce_detection=False
+        )
+        embedding_list.append(embedding_result["embeddings"][0])
+
+    while cap.isOpened():
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        # detections = RetinaFace.detect_faces(img_path=frame)
+        detections = model(frame)
+
+        print(f"{current_frame_count}감지 시작")
+
+        for face_id in detections.xyxy[0]:
+            x1, y1, x2, y2 = face_id[:4].int().tolist()
+            if y2 - y1 > 50 and x2 - x1 > 50:
+                face_image = frame[y1:y2, x1:x2]
+                for ref_face in embedding_list:
+                    result = DeepFace.verify(img1_path=face_image, img2_path=ref_face, model_name=model_name,
+                                             detector_backend='retinaface', enforce_detection=False)
+                    distance = result['distance']
+
+                    if not_threshold >= distance >= threshold:
+                        face_filename = f"face_{face_count}.jpg"
+                        verified_str = 'Different'
+                        distance_str = '(%.4f <= %.4f)' % (distance, threshold)
+                        print(face_filename,verified_str, distance_str)
+                        face = cv2.resize(face_image, (10, 10))
+                        face = cv2.resize(face, (x2 - x1, y2 - y1), interpolation=cv2.INTER_AREA)
+                        frame[y1:y2, x1:x2] = face
+                        face_filepath = os.path.join(faces_dir, face_filename)
+                        cv2.imwrite(face_filepath, face_image)
+
+                    if distance < threshold:
+                        break
+
+                    if distance > not_threshold:
+                        face = cv2.resize(face_image, (10, 10))
+                        face = cv2.resize(face, (x2 - x1, y2 - y1), interpolation=cv2.INTER_AREA)
+                        frame[y1:y2, x1:x2] = face
+                        break
+
+                face_count += 1
+        current_frame_count += 1
+        out.write(frame)
+
+    cap.release()
+    out.release()
+    cv2.destroyAllWindows()
+
+    return output_video_path
+