{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceType":"competition","sourceId":16880,"databundleVersionId":858837},{"sourceType":"datasetVersion","sourceId":9809008,"datasetId":5917503,"databundleVersionId":10055154}],"dockerImageVersionId":29844,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"!pip install -U --upgrade tensorflow","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:18:56.550634Z","iopub.execute_input":"2024-11-05T05:18:56.551106Z","iopub.status.idle":"2024-11-05T05:19:03.805224Z","shell.execute_reply.started":"2024-11-05T05:18:56.551048Z","shell.execute_reply":"2024-11-05T05:19:03.803997Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pip install tensorflow-docs\n","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:03.808789Z","iopub.execute_input":"2024-11-05T05:19:03.809187Z","iopub.status.idle":"2024-11-05T05:19:06.551255Z","shell.execute_reply.started":"2024-11-05T05:19:03.809130Z","shell.execute_reply":"2024-11-05T05:19:06.549648Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow_docs.vis import embed\nfrom tensorflow import keras\n#from imutils import paths\n\nimport matplotlib.pyplot as plt\nimport tensorflow as tf\nimport pandas as pd\nimport numpy as np\nimport imageio\nimport cv2\nimport os","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.553671Z","iopub.execute_input":"2024-11-05T05:19:06.554088Z","iopub.status.idle":"2024-11-05T05:19:06.616016Z","shell.execute_reply.started":"2024-11-05T05:19:06.554024Z","shell.execute_reply":"2024-11-05T05:19:06.612301Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nDATA_FOLDER = '../input/deepfake-detection-challenge'\nTRAIN_SAMPLE_FOLDER = 'train_sample_videos'\nTEST_FOLDER = 'test_videos'\n\nprint(f\"Train samples: {len(os.listdir(os.path.join(DATA_FOLDER, TRAIN_SAMPLE_FOLDER)))}\")\n\nprint(f\"Test samples: {len(os.listdir(os.path.join(DATA_FOLDER, TEST_FOLDER)))}\")\n","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.617560Z","iopub.status.idle":"2024-11-05T05:19:06.618446Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\ntrain_sample_metadata = pd.read_json('../input/deepfake-detection-challenge/train_sample_videos/metadata.json').T\ntrain_sample_metadata.head()","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.619990Z","iopub.status.idle":"2024-11-05T05:19:06.620576Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\ntrain_sample_metadata.groupby('label')['label'].count().plot(figsize=(15, 5), kind='bar', title='Distribution of Labels in the Training Set')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.622759Z","iopub.status.idle":"2024-11-05T05:19:06.623467Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_sample_metadata.shape","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.625096Z","iopub.status.idle":"2024-11-05T05:19:06.625665Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fake_train_sample_video = list(train_sample_metadata.loc[train_sample_metadata.label=='FAKE'].sample(3).index)\nfake_train_sample_video","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.627375Z","iopub.status.idle":"2024-11-05T05:19:06.628016Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def display_image_from_video(video_path):\n    '''\n    input: video_path - path for video\n    process:\n    1. perform a video capture from the video\n    2. read the image\n    3. display the image\n    '''\n    capture_image = cv2.VideoCapture(video_path) \n    ret, frame = capture_image.read()\n    fig = plt.figure(figsize=(10,10))\n    ax = fig.add_subplot(111)\n    frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)\n    ax.imshow(frame)","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.629794Z","iopub.status.idle":"2024-11-05T05:19:06.630394Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import cv2\nfor video_file in fake_train_sample_video:\n    display_image_from_video(os.path.join(DATA_FOLDER, TRAIN_SAMPLE_FOLDER, video_file))","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.632149Z","iopub.status.idle":"2024-11-05T05:19:06.632867Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"real_train_sample_video = list(train_sample_metadata.loc[train_sample_metadata.label=='REAL'].sample(3).index)\nreal_train_sample_video","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.634413Z","iopub.status.idle":"2024-11-05T05:19:06.635070Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for video_file in real_train_sample_video:\n    display_image_from_video(os.path.join(DATA_FOLDER, TRAIN_SAMPLE_FOLDER, video_file))","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.636539Z","iopub.status.idle":"2024-11-05T05:19:06.637199Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_sample_metadata['original'].value_counts()[0:5]","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.638655Z","iopub.status.idle":"2024-11-05T05:19:06.639275Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def display_image_from_video_list(video_path_list, video_folder=TRAIN_SAMPLE_FOLDER):\n    '''\n    input: video_path_list - path for video\n    process:\n    0. for each video in the video path list\n        1. perform a video capture from the video\n        2. read the image\n        3. display the image\n    '''\n    plt.figure()\n    fig, ax = plt.subplots(2,3,figsize=(16,8))\n    # we only show images extracted from the first 6 videos\n    for i, video_file in enumerate(video_path_list[0:6]):\n        video_path = os.path.join(DATA_FOLDER, video_folder,video_file)\n        capture_image = cv2.VideoCapture(video_path) \n        ret, frame = capture_image.read()\n        frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)\n        ax[i//3, i%3].imshow(frame)\n        ax[i//3, i%3].set_title(f\"Video: {video_file}\")\n        ax[i//3, i%3].axis('on')","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.640890Z","iopub.status.idle":"2024-11-05T05:19:06.641466Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"same_original_fake_train_sample_video = list(train_sample_metadata.loc[train_sample_metadata.original=='atvmxvwyns.mp4'].index)\ndisplay_image_from_video_list(same_original_fake_train_sample_video)","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.643001Z","iopub.status.idle":"2024-11-05T05:19:06.643589Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_videos = pd.DataFrame(list(os.listdir(os.path.join(DATA_FOLDER, TEST_FOLDER))), columns=['video'])","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.645434Z","iopub.status.idle":"2024-11-05T05:19:06.646062Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_videos.head()","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.647382Z","iopub.status.idle":"2024-11-05T05:19:06.647990Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display_image_from_video(os.path.join(DATA_FOLDER, TEST_FOLDER, test_videos.iloc[2].video))","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.649501Z","iopub.status.idle":"2024-11-05T05:19:06.650089Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fake_videos = list(train_sample_metadata.loc[train_sample_metadata.label=='FAKE'].index)","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.651703Z","iopub.status.idle":"2024-11-05T05:19:06.652361Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from IPython.display import HTML\nfrom base64 import b64encode\n\ndef play_video(video_file, subset=TRAIN_SAMPLE_FOLDER):\n    '''\n    Display video\n    param: video_file - the name of the video file to display\n    param: subset - the folder where the video file is located (can be TRAIN_SAMPLE_FOLDER or TEST_Folder)\n    '''\n    video_url = open(os.path.join(DATA_FOLDER, subset,video_file),'rb').read()\n    data_url = \"data:video/mp4;base64,\" + b64encode(video_url).decode()\n    return HTML(\"\"\"<video width=500 controls><source src=\"%s\" type=\"video/mp4\"></video>\"\"\" % data_url)\n\nplay_video(fake_videos[10])","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.653742Z","iopub.status.idle":"2024-11-05T05:19:06.654400Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"IMG_SIZE = 224\nBATCH_SIZE = 64\nEPOCHS = 10\n\nMAX_SEQ_LENGTH = 20\nNUM_FEATURES = 2048","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.655901Z","iopub.status.idle":"2024-11-05T05:19:06.656462Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def crop_center_square(frame):\n    y, x = frame.shape[0:2]\n    min_dim = min(y, x)\n    start_x = (x // 2) - (min_dim // 2)\n    start_y = (y // 2) - (min_dim // 2)\n    return frame[start_y : start_y + min_dim, start_x : start_x + min_dim]\n\n\ndef load_video(path, max_frames=0, resize=(IMG_SIZE, IMG_SIZE)):\n    cap = cv2.VideoCapture(path)\n    frames = []\n    try:\n        while True:\n            ret, frame = cap.read()\n            if not ret:\n                break\n            frame = crop_center_square(frame)\n            frame = cv2.resize(frame, resize)\n            frame = frame[:, :, [2, 1, 0]]\n            frames.append(frame)\n\n            if len(frames) == max_frames:\n                break\n    finally:\n        cap.release()\n    return np.array(frames)","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.657810Z","iopub.status.idle":"2024-11-05T05:19:06.658392Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow import keras\ndef build_feature_extractor():\n    feature_extractor = keras.applications.InceptionV3(\n        weights=\"imagenet\",\n        include_top=False,\n        pooling=\"avg\",\n        input_shape=(IMG_SIZE, IMG_SIZE, 3),\n    )\n    preprocess_input = keras.applications.inception_v3.preprocess_input\n\n    inputs = keras.Input((IMG_SIZE, IMG_SIZE, 3))\n    preprocessed = preprocess_input(inputs)\n\n    outputs = feature_extractor(preprocessed)\n    return keras.Model(inputs, outputs, name=\"feature_extractor\")\n\n\nfeature_extractor = build_feature_extractor()","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.659948Z","iopub.status.idle":"2024-11-05T05:19:06.660485Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def prepare_all_videos(df, root_dir):\n    num_samples = len(df)\n    video_paths = list(df.index)\n    labels = df[\"label\"].values\n    labels = np.array(labels=='FAKE').astype(np.int)\n\n    # `frame_masks` and `frame_features` are what we will feed to our sequence model.\n    # `frame_masks` will contain a bunch of booleans denoting if a timestep is\n    # masked with padding or not.\n    frame_masks = np.zeros(shape=(num_samples, MAX_SEQ_LENGTH), dtype=\"bool\")\n    frame_features = np.zeros(\n        shape=(num_samples, MAX_SEQ_LENGTH, NUM_FEATURES), dtype=\"float32\"\n    )\n\n    # For each video.\n    for idx, path in enumerate(video_paths):\n        # Gather all its frames and add a batch dimension.\n        frames = load_video(os.path.join(root_dir, path))\n        frames = frames[None, ...]\n\n        # Initialize placeholders to store the masks and features of the current video.\n        temp_frame_mask = np.zeros(shape=(1, MAX_SEQ_LENGTH,), dtype=\"bool\")\n        temp_frame_features = np.zeros(\n            shape=(1, MAX_SEQ_LENGTH, NUM_FEATURES), dtype=\"float32\"\n        )\n\n        # Extract features from the frames of the current video.\n        for i, batch in enumerate(frames):\n            video_length = batch.shape[0]\n            length = min(MAX_SEQ_LENGTH, video_length)\n            for j in range(length):\n                temp_frame_features[i, j, :] = feature_extractor.predict(\n                    batch[None, j, :]\n                )\n            temp_frame_mask[i, :length] = 1  # 1 = not masked, 0 = masked\n\n        frame_features[idx,] = temp_frame_features.squeeze()\n        frame_masks[idx,] = temp_frame_mask.squeeze()\n\n    return (frame_features, frame_masks), labels","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.662110Z","iopub.status.idle":"2024-11-05T05:19:06.662665Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\nTrain_set, Test_set = train_test_split(train_sample_metadata,test_size=0.1,random_state=42,stratify=train_sample_metadata['label'])\n\nprint(Train_set.shape, Test_set.shape )","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.664222Z","iopub.status.idle":"2024-11-05T05:19:06.665193Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np\ntrain_data, train_labels = prepare_all_videos(Train_set, \"train\")\ntest_data, test_labels = prepare_all_videos(Test_set, \"test\")\n\nprint(f\"Frame features in train set: {train_data[0].shape}\")\nprint(f\"Frame masks in train set: {train_data[1].shape}\")","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.666628Z","iopub.status.idle":"2024-11-05T05:19:06.667405Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"frame_features_input = keras.Input((MAX_SEQ_LENGTH, NUM_FEATURES))\nmask_input = keras.Input((MAX_SEQ_LENGTH,), dtype=\"bool\")\n\n# Refer to the following tutorial to understand the significance of using `mask`:\n# https://keras.io/api/layers/recurrent_layers/gru/\nx = keras.layers.GRU(16, return_sequences=True)(\n    frame_features_input, mask=mask_input\n)\nx = keras.layers.GRU(8)(x)\nx = keras.layers.Dropout(0.4)(x)\nx = keras.layers.Dense(8, activation=\"relu\")(x)\noutput = keras.layers.Dense(1, activation=\"sigmoid\")(x)\n\nmodel = keras.Model([frame_features_input, mask_input], output)\n\nmodel.compile(loss=\"binary_crossentropy\", optimizer=\"adam\", metrics=[\"accuracy\"])\nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.669070Z","iopub.status.idle":"2024-11-05T05:19:06.669621Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"checkpoint = keras.callbacks.ModelCheckpoint('./', save_weights_only=True, save_best_only=True)\nhistory = model.fit(\n        [train_data[0], train_data[1]],\n        train_labels,\n        validation_data=([test_data[0], test_data[1]],test_labels),\n        callbacks=[checkpoint],\n        epochs=EPOCHS,\n        batch_size=8\n    )","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.670956Z","iopub.status.idle":"2024-11-05T05:19:06.671733Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ndef prepare_single_video(frames):\n    frames = frames[None, ...]\n    frame_mask = np.zeros(shape=(1, MAX_SEQ_LENGTH,), dtype=\"bool\")\n    frame_features = np.zeros(shape=(1, MAX_SEQ_LENGTH, NUM_FEATURES), dtype=\"float32\")\n\n    for i, batch in enumerate(frames):\n        video_length = batch.shape[0]\n        length = min(MAX_SEQ_LENGTH, video_length)\n        for j in range(length):\n            frame_features[i, j, :] = feature_extractor.predict(batch[None, j, :])\n        frame_mask[i, :length] = 1  # 1 = not masked, 0 = masked\n\n    return frame_features, frame_mask\n\ndef sequence_prediction(path):\n    frames = load_video(os.path.join(DATA_FOLDER, TEST_FOLDER,path))\n    frame_features, frame_mask = prepare_single_video(frames)\n    return model.predict([frame_features, frame_mask])[0]\n    \n# This utility is for visualization.\n# Referenced from:\n# https://www.tensorflow.org/hub/tutorials/action_recognition_with_tf_hub\ndef to_gif(images):\n    converted_images = images.astype(np.uint8)\n    imageio.mimsave(\"animation.gif\", converted_images, fps=10)\n    return embed.embed_file(\"animation.gif\")\n\n\n#test_video = np.random.choice(test_videos[\"video\"].values.tolist())\n\n#test_video = \"/kaggle/input/deepfake-detection-challenge/train_sample_videos/abqwwspghj.mp4\"\n#test_video = \"/kaggle/input/deepfake-detection-challenge/train_sample_videos/acqfdwsrhi.mp4\"\n#test_video = \"/kaggle/input/deepfake-detection-challenge/train_sample_videos/acxnxvbsxk.mp4\"\n#test_video = \"/kaggle/input/deepfake-detection-challenge/train_sample_videos/efwfxwwlbw.mp4\"\n\n#test_video = \"/kaggle/input/testing/real1.mp4\"\n#test_video = \"/kaggle/input/testing/fake1.mp4\"\ntest_video = \"/kaggle/input/testing/real_vid.mp4\"\n\n#test_video = \"/kaggle/input/deepfake-detection-challenge/test_videos/aktnlyqpah.mp4\"\n#test_video = \"/kaggle/input/deepfake-detection-challenge/train_sample_videos/adohikbdaz.mp4\"\nprint(f\"Test video path: {test_video}\")\n\nif(sequence_prediction(test_video)>=0.5):\n    print(f'The predicted class of the video is FAKE')\nelse:\n    print(f'The predicted class of the video is REAL')\n\nplay_video(test_video,TEST_FOLDER)","metadata":{"execution":{"iopub.status.busy":"2024-11-05T05:19:06.674001Z","iopub.status.idle":"2024-11-05T05:19:06.674560Z"},"trusted":true},"execution_count":null,"outputs":[]}]}