{"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_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"\n# Table of Contents\n1. [Introduction](#introduction)\n1. [Configure hyper-parameters](#configure_hyper_parameters)\n1. [Install dependencies](#install_dependencies)\n1. [Import libraries](#import_libraries)\n1. [Define useful classes](#define_useful_classes)\n1. [Define helper-functions](#define_helper_functions)\n1. [Start inference process](#start_inference_process)\n1. [Create submission.csv](#create_submission_csv)\n1. [Conclusion](#conclusion)","metadata":{}},{"cell_type":"markdown","source":"\n# Introduction\nLet's use our trained Logistic Regression model in the previous step to infer all test videos, and submit the result to see how our simple model perform :)\n\n---\n## Baseline's diagram\n\n\n---\n## Pipeline\nThis end-to-end solution includes 3 steps:\n1. [*Data Preparation* ](https://www.kaggle.com/phunghieu/deepfake-detection-data-preparation-baseline)\n1. [*Training*](https://www.kaggle.com/phunghieu/deepfake-detection-training-baseline)\n1. *Inference* <- **you're here**\n\n---\n[Back to Table of Contents](#toc)","metadata":{}},{"cell_type":"markdown","source":"\n# Hyper parameter configuration\n[Back to Table of Contents](#toc)","metadata":{}},{"cell_type":"code","source":"TEST_DIR = '/kaggle/input/deepfake-detection-challenge/test_videos/'\nMODEL_PATH = '/kaggle/input/deepfake-detection-logistic-regression/model.pth'\n\nBATCH_SIZE = 60\nSCALE = 0.25\nN_FRAMES = None # 'None' means using all available frames\nDEFAULT_PROB = 0.5","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n# Install dependencies\n[Back to Table of Contents](#toc)","metadata":{}},{"cell_type":"code","source":"# Install facenet-pytorch\n!pip install /kaggle/input/facenet-pytorch-vggface2/facenet_pytorch-2.0.0-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","metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_kg_hide-output":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n# Import libraries\n[Back to Table of Contents](#toc)","metadata":{}},{"cell_type":"code","source":"import os\nimport glob\nimport json\nimport torch\nimport torch.nn as nn\nimport cv2\nimport matplotlib.pyplot as plt\nfrom PIL import Image\nimport numpy as np\nimport pandas as pd\nfrom tqdm.notebook import tqdm\nfrom facenet_pytorch import MTCNN, InceptionResnetV1, extract_face\n\nif torch.cuda.is_available():\n device = 'cuda:0'\n torch.set_default_tensor_type('torch.cuda.FloatTensor')\nelse:\n device = 'cpu'\nprint(f'Running on device: {device}')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n# Define useful classes\n[Back to Table of Contents](#toc)","metadata":{}},{"cell_type":"code","source":"# Source: https://www.kaggle.com/timesler/facial-recognition-model-in-pytorch\nclass 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\nclass LogisticRegression(nn.Module):\n def __init__(self, D_in=1, D_out=1):\n super(LogisticRegression, self).__init__()\n self.linear = nn.Linear(D_in, D_out)\n \n def forward(self, x):\n y_pred = self.linear(x)\n y_pred = torch.sigmoid(y_pred)\n \n return y_pred","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n# Define helper-functions\n[Back to Table of Contents](#toc)","metadata":{}},{"cell_type":"code","source":"# Source: https://www.kaggle.com/timesler/facial-recognition-model-in-pytorch\ndef process_faces(faces, feature_extractor):\n # Filter out frames without faces\n faces = [f for f in faces if f is not None]\n if len(faces) == 0:\n return None\n faces = torch.cat(faces).to(device)\n\n # Generate facial feature vectors using a pretrained model\n embeddings = feature_extractor(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","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n# Start inference process\n[Back to Table of Contents](#toc)","metadata":{}},{"cell_type":"code","source":"# Load model.\nclassifier = LogisticRegression()\nclassifier.load_state_dict(torch.load(MODEL_PATH))\nclassifier.eval()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Get all test videos.\nall_test_videos = glob.glob(os.path.join(TEST_DIR, '*.mp4'))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Load face detector.\nface_detector = MTCNN(margin=14, keep_all=True, factor=0.5, device=device).eval()\n\n# Load facial recognition model.\nfeature_extractor = InceptionResnetV1(pretrained='vggface2', device=device).eval()\n\n# Define face detection pipeline.\ndetection_pipeline = DetectionPipeline(detector=face_detector, n_frames=N_FRAMES, batch_size=BATCH_SIZE, resize=SCALE)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_test = []\n\nwith torch.no_grad():\n for path in tqdm(all_test_videos):\n try:\n # Detect all faces occur in the video.\n faces = detection_pipeline(path)\n\n # Calculate the distances of all faces' feature vectors to the centroid.\n distances = process_faces(faces, feature_extractor)\n X_test.append(distances)\n except:\n X_test.append(None)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = []\n\nwith torch.no_grad():\n for path, distances in zip(all_test_videos, X_test):\n file_name = os.path.basename(path)\n\n if distances is not None:\n distances = torch.tensor(distances).unsqueeze(dim=1).float().to(device)\n y_pred = classifier(distances)\n y_pred = float(y_pred.mean().cpu().numpy())\n else:\n y_pred = DEFAULT_PROB\n\n submission.append([file_name, y_pred])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n# Create submission.csv\n[Back to Table of Contents](#toc)","metadata":{}},{"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()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n# Conclusion\nFinally, we made it! Let's submit the result to see whether we can get a better position in the Public Leaderboard =]]\n\nIf you have any questions or suggestions, feel free to move to the `comments` section below.\n\nPlease upvote this kernel if you think it is worth reading; and remember to upvote `@timesler`'s [*kernel*](https://www.kaggle.com/timesler/facial-recognition-model-in-pytorch), too. Thank you so much!\n\n---\n[Back to Table of Contents](#toc)","metadata":{}}]}