{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"!pip install /kaggle/input/facenet-pytorch-vggface2/facenet_pytorch-2.2.7-py3-none-any.whl\n\nfrom facenet_pytorch.models.inception_resnet_v1 import get_torch_home\ntorch_home = get_torch_home()\n\n# Copy model checkpoints to torch cache so they are loaded automatically by the package\n!mkdir -p $torch_home/checkpoints/\n!cp /kaggle/input/facenet-pytorch-vggface2/20180402-114759-vggface2-logits.pth $torch_home/checkpoints/vggface2_DG3kwML46X.pt\n!cp /kaggle/input/facenet-pytorch-vggface2/20180402-114759-vggface2-features.pth $torch_home/checkpoints/vggface2_G5aNV2VSMn.pt\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import os\nimport glob\nimport time\nimport torch\nimport cv2\nfrom PIL import Image\nimport numpy as np\nimport pandas as pd\nfrom matplotlib import pyplot as plt\nfrom tqdm.notebook import tqdm\n\n# See github.com/timesler/facenet-pytorch:\nfrom facenet_pytorch import MTCNN, InceptionResnetV1, extract_face\n\ndevice = 'cuda:0' if torch.cuda.is_available() else 'cpu'\nprint(f'Running on device: {device}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Load face detector\nmtcnn = MTCNN(margin=14, keep_all=True, factor=0.5, device=device).eval()\n\n# Load facial recognition model\nresnet = InceptionResnetV1(pretrained='vggface2', device=device).eval()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"mtcnn","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"resnet","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class DetectionPipeline:\n    \"\"\"Pipeline class for detecting faces in the frames of a video file.\"\"\"\n    \n    def __init__(self, detector, n_frames=None, batch_size=60, resize=None):\n        \"\"\"Constructor for DetectionPipeline class.\n        \n        Keyword Arguments:\n            n_frames {int} -- Total number of frames to load. These will be evenly spaced\n                throughout the video. If not specified (i.e., None), all frames will be loaded.\n                (default: {None})\n            batch_size {int} -- Batch size to use with MTCNN face detector. (default: {32})\n            resize {float} -- Fraction by which to resize frames from original prior to face\n                detection. A value less than 1 results in downsampling and a value greater than\n                1 result in upsampling. (default: {None})\n        \"\"\"\n        self.detector = detector\n        self.n_frames = n_frames\n        self.batch_size = batch_size\n        self.resize = resize\n    \n    def __call__(self, filename):\n        \"\"\"Load frames from an MP4 video and detect faces.\n\n        Arguments:\n            filename {str} -- Path to video.\n        \"\"\"\n        # Create video reader and find length\n        v_cap = cv2.VideoCapture(filename)\n        v_len = int(v_cap.get(cv2.CAP_PROP_FRAME_COUNT))\n\n        # Pick 'n_frames' evenly spaced frames to sample\n        if self.n_frames is None:\n            sample = np.arange(0, v_len)\n        else:\n            sample = np.linspace(0, v_len - 1, self.n_frames).astype(int)\n\n        # Loop through frames\n        faces = []\n        frames = []\n        for j in range(v_len):\n            success = v_cap.grab()\n            if j in sample:\n                # Load frame\n                success, frame = v_cap.retrieve()\n                if not success:\n                    continue\n                frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)\n                frame = Image.fromarray(frame)\n                \n                # Resize frame to desired size\n                if self.resize is not None:\n                    frame = frame.resize([int(d * self.resize) for d in frame.size])\n                frames.append(frame)\n\n                # When batch is full, detect faces and reset frame list\n                if len(frames) % self.batch_size == 0 or j == sample[-1]:\n                    faces.extend(self.detector(frames))\n                    frames = []\n\n        v_cap.release()\n\n        return faces    \n\n\ndef process_faces(faces, resnet):\n    # Filter out frames without faces\n    faces = [f for f in faces if f is not None]\n    faces = torch.cat(faces).to(device)\n\n    # Generate facial feature vectors using a pretrained model\n    embeddings = resnet(faces)\n\n    # Calculate centroid for video and distance of each face's feature vector from centroid\n    centroid = embeddings.mean(dim=0)\n    x = (embeddings - centroid).norm(dim=1).cpu().numpy()\n    \n    return x","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Define face detection pipeline\ndetection_pipeline = DetectionPipeline(detector=mtcnn, batch_size=60, resize=0.25, n_frames=150)\n\n# Get all test videos\nfilenames = glob.glob('/kaggle/input/deepfake-detection-challenge/test_videos/*.mp4')\n\nX = []\nstart = time.time()\nn_processed = 0\nwith torch.no_grad():\n    for i, filename in tqdm(enumerate(filenames), total=len(filenames)):\n        try:\n            # Load frames and find faces\n            faces = detection_pipeline(filename)\n            \n            # Calculate embeddings\n            X.append(process_faces(faces, resnet))\n\n        except KeyboardInterrupt:\n            print('\\nStopped.')\n            break\n\n        except Exception as e:\n            print(e)\n            X.append(None)\n        \n        n_processed += len(faces)\n        print(f'Frames per second (load+detect+embed): {n_processed / (time.time() - start):6.3}\\r', end='')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"bias = -0.2942\nweight = 0.68235746\n\nsubmission = []\nfor filename, x_i in zip(filenames, X):\n    if x_i is not None:\n        prob = 1 / (1 + np.exp(-(bias + (weight * x_i).mean())))\n    else:\n        prob = 0.5\n    submission.append([os.path.basename(filename), prob])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.DataFrame(submission, columns=['filename', 'label'])\nsubmission.sort_values('filename').to_csv('submission.csv', index=False)\n\nplt.hist(submission.label, 20)\nplt.show()","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}