Update code

01-crop_faces_with_mtcnn.py

@@ -14,6 +14,8 @@ if physical_devices:
 
 base_path = '.\\train_sample_videos\\FaceForensics++_C23\\'
 
+detector = MTCNN()
+
 def get_filename_only(file_path):
     file_basename = os.path.basename(file_path)
     filename_only = file_basename.split('.')[0]
@@ -60,7 +62,6 @@ for folder_name in sorted(os.listdir(base_path)):
         for frame in frame_images:
             print('Processing ', frame)
             try:
-                detector = MTCNN()
                 image = cv2.cvtColor(cv2.imread(os.path.join(tmp_path, frame)), cv2.COLOR_BGR2RGB)
                 results = detector.detect_faces(image)
             except Exception as e:

02-prepare_fake_real_dataset.py

@@ -7,7 +7,7 @@ from PIL import Image
 
 MIN_IMAGE_SIZE = 90  # minimum width and height in pixels
 
-base_path = '.\\train_sample_videos\\Deepfakes\\'
+base_path = '.\\train_sample_videos\\FaceForensics++_C23\\'
 dataset_path = '.\\prepared_dataset\\'
 print('Creating Directory: ' + dataset_path)
 os.makedirs(dataset_path, exist_ok=True)
@@ -43,13 +43,6 @@ def copy_large_faces(src_dir, dst_dir):
                 skipped += 1
         except Exception:
             skipped += 1
-   
-with open(os.path.join('.\\train_sample_videos\\csv\\', 'Deepfakes.csv'), newline='', encoding='utf-8') as csvfile:
-    reader = csv.DictReader(csvfile)
-    metadata = {}
-    for row in reader:
-        metadata[row['File Path']] = row['Label'].strip().upper()
-    print(len(metadata))
 
 real_path = os.path.join(dataset_path, 'real')
 print('Creating Directory: ' + real_path)
@@ -63,20 +56,42 @@ if os.path.exists(fake_path):
     shutil.rmtree(fake_path)
 os.makedirs(fake_path)
 
-for filename, label in metadata.items():
-    print(filename)
-    print(label)
-    tmp_path = os.path.join(os.path.join(base_path, get_filename_only(filename)), 'faces')
-    print(tmp_path)
-    if os.path.exists(tmp_path):
-        if label == 'REAL':
-            print('Copying to :' + real_path)
-            copy_large_faces(tmp_path, real_path)
-        elif label == 'FAKE':
-            print('Copying to :' + tmp_fake_path)
-            copy_large_faces(tmp_path, tmp_fake_path)
-        else:
-            print('Ignored..')
+# Iterate over all subfolders in FaceForensics++_C23 (excluding 'csv')
+for folder_name in sorted(os.listdir(base_path)):
+    folder_path = os.path.join(base_path, folder_name)
+    if not os.path.isdir(folder_path) or folder_name == 'csv':
+        continue
+
+    csv_file = os.path.join(base_path, 'csv', folder_name + '.csv')
+    if not os.path.isfile(csv_file):
+        print(f'CSV not found for {folder_name}, skipping: {csv_file}')
+        continue
+
+    print(f'\n{"="*60}')
+    print(f'Processing folder: {folder_name}')
+    print(f'{"="*60}')
+
+    with open(csv_file, newline='', encoding='utf-8') as csvfile:
+        reader = csv.DictReader(csvfile)
+        metadata = {}
+        for row in reader:
+            metadata[row['File Path']] = row['Label'].strip().upper()
+        print(f'{folder_name}: {len(metadata)} entries')
+
+    for filename, label in metadata.items():
+        print(filename)
+        print(label)
+        tmp_path = os.path.join(os.path.join(folder_path, get_filename_only(filename)), 'faces')
+        print(tmp_path)
+        if os.path.exists(tmp_path):
+            if label == 'REAL':
+                print('Copying to :' + real_path)
+                copy_large_faces(tmp_path, real_path)
+            elif label == 'FAKE':
+                print('Copying to :' + tmp_fake_path)
+                copy_large_faces(tmp_path, tmp_fake_path)
+            else:
+                print('Ignored..')
 
 all_real_faces = [f for f in os.listdir(real_path) if os.path.isfile(os.path.join(real_path, f))]
 print('Total Number of Real faces: ', len(all_real_faces))