{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport tensorflow as tf\nimport tensorflow_addons as tfa\nimport matplotlib.pyplot as plt\nimport matplotlib as mpl\nimport seaborn as sn\n\nfrom tqdm.notebook import tqdm\nfrom sklearn.model_selection import train_test_split, GroupShuffleSplit \n\nimport glob\nimport sys\nimport os\nimport math\nimport gc\nimport sys\nimport sklearn\nimport scipy\n\nprint(f'Tensorflow V{tf.__version__}')\nprint(f'Keras V{tf.keras.__version__}')\nprint(f'Python V{sys.version}')","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:18:29.982510Z","iopub.execute_input":"2023-08-30T16:18:29.983242Z","iopub.status.idle":"2023-08-30T16:18:29.991804Z","shell.execute_reply.started":"2023-08-30T16:18:29.983203Z","shell.execute_reply":"2023-08-30T16:18:29.990615Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Plot Config","metadata":{}},{"cell_type":"code","source":"# MatplotLib Global Settings\nmpl.rcParams.update(mpl.rcParamsDefault)\nmpl.rcParams['xtick.labelsize'] = 16\nmpl.rcParams['ytick.labelsize'] = 16\nmpl.rcParams['axes.labelsize'] = 18\nmpl.rcParams['axes.titlesize'] = 24","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:18:36.452124Z","iopub.execute_input":"2023-08-30T16:18:36.453260Z","iopub.status.idle":"2023-08-30T16:18:36.461212Z","shell.execute_reply.started":"2023-08-30T16:18:36.453210Z","shell.execute_reply":"2023-08-30T16:18:36.459976Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Config","metadata":{}},{"cell_type":"code","source":"# If True, processing data from scratch\n# If False, loads preprocessed data\nPREPROCESS_DATA = False\nTRAIN_MODEL = True\n# True: use 10% of participants as validation set\n# False: use all data for training -> gives better LB result\nUSE_VAL = False\n\nN_ROWS = 543\nN_DIMS = 3\nDIM_NAMES = ['x', 'y', 'z']\nSEED = 42\nNUM_CLASSES = 250\nIS_INTERACTIVE = os.environ['KAGGLE_KERNEL_RUN_TYPE'] == 'Interactive'\nVERBOSE = 1 if IS_INTERACTIVE else 2\n\nINPUT_SIZE = 64\n\nBATCH_ALL_SIGNS_N = 4\nBATCH_SIZE = 256\nN_EPOCHS = 100\nLR_MAX = 1e-3\nN_WARMUP_EPOCHS = 0\nWD_RATIO = 0.05\nMASK_VAL = 4237","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:18:39.702621Z","iopub.execute_input":"2023-08-30T16:18:39.703697Z","iopub.status.idle":"2023-08-30T16:18:39.712562Z","shell.execute_reply.started":"2023-08-30T16:18:39.703623Z","shell.execute_reply":"2023-08-30T16:18:39.711078Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Utils","metadata":{}},{"cell_type":"code","source":"# Prints Shape and Dtype For List Of Variables\ndef print_shape_dtype(l, names):\n    for e, n in zip(l, names):\n        print(f'{n} shape: {e.shape}, dtype: {e.dtype}')","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:18:46.582427Z","iopub.execute_input":"2023-08-30T16:18:46.583197Z","iopub.status.idle":"2023-08-30T16:18:46.588854Z","shell.execute_reply.started":"2023-08-30T16:18:46.583156Z","shell.execute_reply":"2023-08-30T16:18:46.587516Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Train","metadata":{}},{"cell_type":"markdown","source":"**Checking Info of CSV File**","metadata":{}},{"cell_type":"code","source":"csv_data = pd.read_csv('/kaggle/input/asl-signs/train.csv')\nprint(csv_data.head(5))\nprint(csv_data.shape)","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:19:07.037776Z","iopub.execute_input":"2023-08-30T16:19:07.038242Z","iopub.status.idle":"2023-08-30T16:19:07.221841Z","shell.execute_reply.started":"2023-08-30T16:19:07.038201Z","shell.execute_reply":"2023-08-30T16:19:07.220697Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Read Training Data\n\nif IS_INTERACTIVE or not PREPROCESS_DATA:\n    train = pd.read_csv('/kaggle/input/asl-signs/train.csv').sample(int(5e3), random_state=SEED)\nelse:\n    train = pd.read_csv('/kaggle/input/asl-signs/train.csv')\n\nN_SAMPLES = len(train)\nprint(f'N_SAMPLES: {N_SAMPLES}')","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:21:02.442571Z","iopub.execute_input":"2023-08-30T16:21:02.443744Z","iopub.status.idle":"2023-08-30T16:21:02.574114Z","shell.execute_reply.started":"2023-08-30T16:21:02.443692Z","shell.execute_reply":"2023-08-30T16:21:02.572867Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Add File Path","metadata":{}},{"cell_type":"code","source":"# Get complete file path to file\ndef get_file_path(path):\n    return f'/kaggle/input/asl-signs/{path}'\n\ntrain['file_path'] = train['path'].apply(get_file_path)\n\n#adding another column to the train dataframe called file_path where it contains absolute path of the info\nprint(train.head(2))","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:27:18.172496Z","iopub.execute_input":"2023-08-30T16:27:18.173937Z","iopub.status.idle":"2023-08-30T16:27:18.188183Z","shell.execute_reply.started":"2023-08-30T16:27:18.173888Z","shell.execute_reply":"2023-08-30T16:27:18.187057Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Ordinally Encode Sign","metadata":{}},{"cell_type":"code","source":"# Add ordinally Encoded Sign (assign number to each sign name)\ntrain['sign_ord'] = train['sign'].astype('category').cat.codes\n# Dictionaries to translate sign <-> ordinal encoded sign\nSIGN2ORD = train[['sign', 'sign_ord']].set_index('sign').squeeze().to_dict()\n\nORD2SIGN = train[['sign_ord', 'sign']].set_index('sign_ord').squeeze().to_dict()\n\n#dataframe after encoding sign with number as a column named sign_ord\nprint(train.head(2))","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:29:19.262761Z","iopub.execute_input":"2023-08-30T16:29:19.263556Z","iopub.status.idle":"2023-08-30T16:29:19.294663Z","shell.execute_reply.started":"2023-08-30T16:29:19.263513Z","shell.execute_reply":"2023-08-30T16:29:19.293326Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display(train.head(30))\ndisplay(train.info())","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:29:53.662622Z","iopub.execute_input":"2023-08-30T16:29:53.663366Z","iopub.status.idle":"2023-08-30T16:29:53.700827Z","shell.execute_reply.started":"2023-08-30T16:29:53.663328Z","shell.execute_reply":"2023-08-30T16:29:53.699711Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Video Statistics","metadata":{}},{"cell_type":"code","source":"N = int(1e3) if (IS_INTERACTIVE or not PREPROCESS_DATA) else int(10e3)\nprint(N)\nN_UNIQUE_FRAMES = np.zeros(N, dtype=np.uint16)\nN_MISSING_FRAMES = np.zeros(N, dtype=np.uint16)\nMAX_FRAME = np.zeros(N, dtype=np.uint16)\n\nPERCENTILES = [0.01, 0.05, 0.25, 0.50, 0.75, 0.95, 0.99, 0.999]\n\nfor idx, file_path in enumerate(tqdm(train['file_path'].sample(N, random_state=SEED))):\n    df = pd.read_parquet(file_path)\n    N_UNIQUE_FRAMES[idx] = df['frame'].nunique()\n    N_MISSING_FRAMES[idx] = (df['frame'].max() - df['frame'].min()) - df['frame'].nunique() + 1\n    MAX_FRAME[idx] = df['frame'].max()\nprint(N_UNIQUE_FRAMES[0],N_MISSING_FRAMES[0],MAX_FRAME[0])","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:36:57.233346Z","iopub.execute_input":"2023-08-30T16:36:57.233769Z","iopub.status.idle":"2023-08-30T16:37:09.892012Z","shell.execute_reply.started":"2023-08-30T16:36:57.233733Z","shell.execute_reply":"2023-08-30T16:37:09.890856Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Number of unique frames in each video\ndisplay(pd.Series(N_UNIQUE_FRAMES).describe(percentiles=PERCENTILES).to_frame('N_UNIQUE_FRAMES'))\n\nplt.figure(figsize=(15,8))\nplt.title('Number of Unique Frames', size=24)\npd.Series(N_UNIQUE_FRAMES).plot(kind='hist', bins=128)\nplt.grid()\nxlim = math.ceil(plt.xlim()[1])\nplt.xlim(0, xlim)\nplt.xticks(np.arange(0, xlim+25, 25))\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:37:17.532595Z","iopub.execute_input":"2023-08-30T16:37:17.533349Z","iopub.status.idle":"2023-08-30T16:37:18.037739Z","shell.execute_reply.started":"2023-08-30T16:37:17.533311Z","shell.execute_reply":"2023-08-30T16:37:18.036620Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Number of missing frames, consecutive frames with missing intermediate frame, i.e. 1,2,4,5 -> 3 is missing\ndisplay(pd.Series(N_MISSING_FRAMES).describe(percentiles=PERCENTILES).to_frame('N_MISSING_FRAMES'))\n\nplt.figure(figsize=(15,8))\nplt.title('Number of Missing Frames', size=24)\npd.Series(N_MISSING_FRAMES).plot(kind='hist', bins=128)\nplt.grid()\nplt.xlim(0, math.ceil(plt.xlim()[1]))\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:37:33.298290Z","iopub.execute_input":"2023-08-30T16:37:33.299442Z","iopub.status.idle":"2023-08-30T16:37:33.764604Z","shell.execute_reply.started":"2023-08-30T16:37:33.299390Z","shell.execute_reply":"2023-08-30T16:37:33.763612Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Maximum frame number\ndisplay(pd.Series(MAX_FRAME).describe(percentiles=PERCENTILES).to_frame('MAX_FRAME'))\n\nplt.figure(figsize=(15,8))\nplt.title('Maximum Frames Index', size=24)\npd.Series(MAX_FRAME).plot(kind='hist', bins=128)\nplt.grid()\nplt.xlim(0, math.ceil(plt.xlim()[1]))\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:37:40.337462Z","iopub.execute_input":"2023-08-30T16:37:40.338208Z","iopub.status.idle":"2023-08-30T16:37:40.850931Z","shell.execute_reply.started":"2023-08-30T16:37:40.338167Z","shell.execute_reply":"2023-08-30T16:37:40.849888Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Landmark Indices","metadata":{}},{"cell_type":"code","source":"USE_TYPES = ['left_hand', 'pose', 'right_hand']\nSTART_IDX = 468\nLIPS_IDXS0 = np.array([\n        61, 185, 40, 39, 37, 0, 267, 269, 270, 409,\n        291, 146, 91, 181, 84, 17, 314, 405, 321, 375,\n        78, 191, 80, 81, 82, 13, 312, 311, 310, 415,\n        95, 88, 178, 87, 14, 317, 402, 318, 324, 308,\n    ])\n# Landmark indices in original data\nLEFT_HAND_IDXS0 = np.arange(468,489)\nRIGHT_HAND_IDXS0 = np.arange(522,543)\nLEFT_POSE_IDXS0 = np.array([502, 504, 506, 508, 510])\nRIGHT_POSE_IDXS0 = np.array([503, 505, 507, 509, 511])\nLANDMARK_IDXS_LEFT_DOMINANT0 = np.concatenate((LIPS_IDXS0, LEFT_HAND_IDXS0, LEFT_POSE_IDXS0))\nLANDMARK_IDXS_RIGHT_DOMINANT0 = np.concatenate((LIPS_IDXS0, RIGHT_HAND_IDXS0, RIGHT_POSE_IDXS0))\nHAND_IDXS0 = np.concatenate((LEFT_HAND_IDXS0, RIGHT_HAND_IDXS0), axis=0)\nN_COLS = LANDMARK_IDXS_LEFT_DOMINANT0.size\n# Landmark indices in processed data\nLIPS_IDXS = np.argwhere(np.isin(LANDMARK_IDXS_LEFT_DOMINANT0, LIPS_IDXS0)).squeeze()\nLEFT_HAND_IDXS = np.argwhere(np.isin(LANDMARK_IDXS_LEFT_DOMINANT0, LEFT_HAND_IDXS0)).squeeze()\nRIGHT_HAND_IDXS = np.argwhere(np.isin(LANDMARK_IDXS_LEFT_DOMINANT0, RIGHT_HAND_IDXS0)).squeeze()\nHAND_IDXS = np.argwhere(np.isin(LANDMARK_IDXS_LEFT_DOMINANT0, HAND_IDXS0)).squeeze()\nPOSE_IDXS = np.argwhere(np.isin(LANDMARK_IDXS_LEFT_DOMINANT0, LEFT_POSE_IDXS0)).squeeze()\n\nprint(f'# HAND_IDXS: {len(HAND_IDXS)}, N_COLS: {N_COLS}')","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:39:19.243428Z","iopub.execute_input":"2023-08-30T16:39:19.244208Z","iopub.status.idle":"2023-08-30T16:39:19.260820Z","shell.execute_reply.started":"2023-08-30T16:39:19.244164Z","shell.execute_reply":"2023-08-30T16:39:19.259245Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"LIPS_START = 0\nLEFT_HAND_START = LIPS_IDXS.size\nRIGHT_HAND_START = LEFT_HAND_START + LEFT_HAND_IDXS.size\nPOSE_START = RIGHT_HAND_START + RIGHT_HAND_IDXS.size\n\nprint(f'LIPS_START: {LIPS_START}, LEFT_HAND_START: {LEFT_HAND_START}, RIGHT_HAND_START: {RIGHT_HAND_START}, POSE_START: {POSE_START}')","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:39:30.567345Z","iopub.execute_input":"2023-08-30T16:39:30.567861Z","iopub.status.idle":"2023-08-30T16:39:30.574381Z","shell.execute_reply.started":"2023-08-30T16:39:30.567822Z","shell.execute_reply":"2023-08-30T16:39:30.573218Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Process Data Tensorflow","metadata":{}},{"cell_type":"code","source":"# Source: https://www.kaggle.com/competitions/asl-signs/overview/evaluation\n# A parquet file contains total 543 rows\nROWS_PER_FRAME = 543  # number of landmarks per frame\n\ndef load_relevant_data_subset(pq_path):\n    data_columns = ['x', 'y', 'z']\n    data = pd.read_parquet(pq_path, columns=data_columns)\n    n_frames = int(len(data) / ROWS_PER_FRAME)\n    data = data.values.reshape(n_frames, ROWS_PER_FRAME, len(data_columns))\n    return data.astype(np.float32)","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:47:27.708778Z","iopub.execute_input":"2023-08-30T16:47:27.709178Z","iopub.status.idle":"2023-08-30T16:47:27.716531Z","shell.execute_reply.started":"2023-08-30T16:47:27.709141Z","shell.execute_reply":"2023-08-30T16:47:27.715349Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\"\"\"\n    Tensorflow layer to process data in TFLite\n    Data needs to be processed in the model itself, so we can not use Python\n\"\"\" \nclass PreprocessLayer(tf.keras.layers.Layer):\n    def __init__(self):\n        super(PreprocessLayer, self).__init__()\n        normalisation_correction = tf.constant([\n                    # Add 0.50 to left hand (original right hand) and substract 0.50 of right hand (original left hand)\n                    [0] * len(LIPS_IDXS) + [0.50] * len(LEFT_HAND_IDXS) + [0.50] * len(POSE_IDXS),\n                    # Y coordinates stay intact\n                    [0] * len(LANDMARK_IDXS_LEFT_DOMINANT0),\n                    # Z coordinates stay intact\n                    [0] * len(LANDMARK_IDXS_LEFT_DOMINANT0),\n                ],\n                dtype=tf.float32,\n            )\n        self.normalisation_correction = tf.transpose(normalisation_correction, [1,0])\n        \n    def pad_edge(self, t, repeats, side):\n        if side == 'LEFT':\n            return tf.concat((tf.repeat(t[:1], repeats=repeats, axis=0), t), axis=0)\n        elif side == 'RIGHT':\n            return tf.concat((t, tf.repeat(t[-1:], repeats=repeats, axis=0)), axis=0)\n    \n    @tf.function(\n        input_signature=(tf.TensorSpec(shape=[None,N_ROWS,N_DIMS], dtype=tf.float32),),\n    )\n    def call(self, data0):\n        # Number of Frames in Video\n        N_FRAMES0 = tf.shape(data0)[0]\n        \n        # Find dominant hand by comparing summed absolute coordinates\n        left_hand_sum = tf.math.reduce_sum(tf.where(tf.math.is_nan(tf.gather(data0, LEFT_HAND_IDXS0, axis=1)), 0, 1))\n        right_hand_sum = tf.math.reduce_sum(tf.where(tf.math.is_nan(tf.gather(data0, RIGHT_HAND_IDXS0, axis=1)), 0, 1))\n        left_dominant = left_hand_sum >= right_hand_sum\n        \n        # Count non NaN Hand values in each frame for the dominant hand\n        if left_dominant:\n            frames_hands_non_nan_sum = tf.math.reduce_sum(\n                    tf.where(tf.math.is_nan(tf.gather(data0, LEFT_HAND_IDXS0, axis=1)), 0, 1),\n                    axis=[1, 2],\n                )\n        else:\n            frames_hands_non_nan_sum = tf.math.reduce_sum(\n                    tf.where(tf.math.is_nan(tf.gather(data0, RIGHT_HAND_IDXS0, axis=1)), 0, 1),\n                    axis=[1, 2],\n                )\n        \n        # Find frames indices with coordinates of dominant hand\n        non_empty_frames_idxs = tf.where(frames_hands_non_nan_sum > 0)\n        non_empty_frames_idxs = tf.squeeze(non_empty_frames_idxs, axis=1)\n        # Filter frames\n        data = tf.gather(data0, non_empty_frames_idxs, axis=0)\n        \n        # Cast Indices in float32 to be compatible with Tensorflow Lite\n        non_empty_frames_idxs = tf.cast(non_empty_frames_idxs, tf.float32)\n        # Normalize to start with 0\n        non_empty_frames_idxs -= tf.reduce_min(non_empty_frames_idxs)\n        \n        # Number of Frames in Filtered Video\n        N_FRAMES = tf.shape(data)[0]\n        \n        # Gather Relevant Landmark Columns\n        if left_dominant:\n            data = tf.gather(data, LANDMARK_IDXS_LEFT_DOMINANT0, axis=1)\n        else:\n            data = tf.gather(data, LANDMARK_IDXS_RIGHT_DOMINANT0, axis=1)\n            data = (\n                    self.normalisation_correction + (\n                        (data - self.normalisation_correction) * tf.where(self.normalisation_correction != 0, -1.0, 1.0))\n                )\n        \n        # Video fits in INPUT_SIZE\n        if N_FRAMES < INPUT_SIZE:\n            # Pad With -1 to indicate padding\n            non_empty_frames_idxs = tf.pad(non_empty_frames_idxs, [[0, INPUT_SIZE-N_FRAMES]], constant_values=-1)\n            # Pad Data With Zeros\n            data = tf.pad(data, [[0, INPUT_SIZE-N_FRAMES], [0,0], [0,0]], constant_values=0)\n            # Fill NaN Values With 0\n            data = tf.where(tf.math.is_nan(data), 0.0, data)\n            return data, non_empty_frames_idxs\n        # Video needs to be downsampled to INPUT_SIZE\n        else:\n            # Repeat\n            if N_FRAMES < INPUT_SIZE**2:\n                repeats = tf.math.floordiv(INPUT_SIZE * INPUT_SIZE, N_FRAMES0)\n                data = tf.repeat(data, repeats=repeats, axis=0)\n                non_empty_frames_idxs = tf.repeat(non_empty_frames_idxs, repeats=repeats, axis=0)\n\n            # Pad To Multiple Of Input Size\n            pool_size = tf.math.floordiv(len(data), INPUT_SIZE)\n            if tf.math.mod(len(data), INPUT_SIZE) > 0:\n                pool_size += 1\n\n            if pool_size == 1:\n                pad_size = (pool_size * INPUT_SIZE) - len(data)\n            else:\n                pad_size = (pool_size * INPUT_SIZE) % len(data)\n\n            # Pad Start/End with Start/End value\n            pad_left = tf.math.floordiv(pad_size, 2) + tf.math.floordiv(INPUT_SIZE, 2)\n            pad_right = tf.math.floordiv(pad_size, 2) + tf.math.floordiv(INPUT_SIZE, 2)\n            if tf.math.mod(pad_size, 2) > 0:\n                pad_right += 1\n\n            # Pad By Concatenating Left/Right Edge Values\n            data = self.pad_edge(data, pad_left, 'LEFT')\n            data = self.pad_edge(data, pad_right, 'RIGHT')\n\n            # Pad Non Empty Frame Indices\n            non_empty_frames_idxs = self.pad_edge(non_empty_frames_idxs, pad_left, 'LEFT')\n            non_empty_frames_idxs = self.pad_edge(non_empty_frames_idxs, pad_right, 'RIGHT')\n\n            # Reshape to Mean Pool\n            data = tf.reshape(data, [INPUT_SIZE, -1, N_COLS, N_DIMS])\n            non_empty_frames_idxs = tf.reshape(non_empty_frames_idxs, [INPUT_SIZE, -1])\n\n            # Mean Pool\n            data = tf.experimental.numpy.nanmean(data, axis=1)\n            non_empty_frames_idxs = tf.experimental.numpy.nanmean(non_empty_frames_idxs, axis=1)\n\n            # Fill NaN Values With 0\n            data = tf.where(tf.math.is_nan(data), 0.0, data)\n            \n            return data, non_empty_frames_idxs\n    \npreprocess_layer = PreprocessLayer()","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:53:05.776877Z","iopub.execute_input":"2023-08-30T16:53:05.777265Z","iopub.status.idle":"2023-08-30T16:53:05.813816Z","shell.execute_reply.started":"2023-08-30T16:53:05.777230Z","shell.execute_reply":"2023-08-30T16:53:05.812716Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Interpolate NaN Values","metadata":{}},{"cell_type":"code","source":"\"\"\"\n    face: 0:468\n    left_hand: 468:489\n    pose: 489:522\n    right_hand: 522:544\n        \n\"\"\"\ndef get_data(file_path):\n    # Load Raw Data\n    data = load_relevant_data_subset(file_path)\n    # Process Data Using Tensorflow\n    data = preprocess_layer(data)\n    return data","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:53:22.062895Z","iopub.execute_input":"2023-08-30T16:53:22.063281Z","iopub.status.idle":"2023-08-30T16:53:22.069256Z","shell.execute_reply.started":"2023-08-30T16:53:22.063247Z","shell.execute_reply":"2023-08-30T16:53:22.068080Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Create Dataset","metadata":{}},{"cell_type":"code","source":"# Get the full dataset\ndef preprocess_data():\n    # Create arrays to save data\n    X = np.zeros([N_SAMPLES, INPUT_SIZE, N_COLS, N_DIMS], dtype=np.float32)\n    y = np.zeros([N_SAMPLES], dtype=np.int32)\n    NON_EMPTY_FRAME_IDXS = np.full([N_SAMPLES, INPUT_SIZE], -1, dtype=np.float32)\n\n    # Fill X/y\n    for row_idx, (file_path, sign_ord) in enumerate(tqdm(train[['file_path', 'sign_ord']].values)):\n        # Log message every 5000 samples\n        if row_idx % 5000 == 0:\n            print(f'Generated {row_idx}/{N_SAMPLES}')\n\n        data, non_empty_frame_idxs = get_data(file_path)\n        X[row_idx] = data\n        y[row_idx] = sign_ord\n        NON_EMPTY_FRAME_IDXS[row_idx] = non_empty_frame_idxs\n        # Sanity check, data should not contain NaN values\n        if np.isnan(data).sum() > 0:\n            print(row_idx)\n            return data\n\n    # Save X/y\n    np.save('X.npy', X)\n    np.save('y.npy', y)\n    np.save('NON_EMPTY_FRAME_IDXS.npy', NON_EMPTY_FRAME_IDXS)\n    \n    # Save Validation\n    splitter = GroupShuffleSplit(test_size=0.10, n_splits=2, random_state=SEED)\n    PARTICIPANT_IDS = train['participant_id'].values\n    train_idxs, val_idxs = next(splitter.split(X, y, groups=PARTICIPANT_IDS))\n\n    # Save Train\n    X_train = X[train_idxs]\n    NON_EMPTY_FRAME_IDXS_TRAIN = NON_EMPTY_FRAME_IDXS[train_idxs]\n    y_train = y[train_idxs]\n    np.save('X_train.npy', X_train)\n    np.save('y_train.npy', y_train)\n    np.save('NON_EMPTY_FRAME_IDXS_TRAIN.npy', NON_EMPTY_FRAME_IDXS_TRAIN)\n    # Save Validation\n    X_val = X[val_idxs]\n    NON_EMPTY_FRAME_IDXS_VAL = NON_EMPTY_FRAME_IDXS[val_idxs]\n    y_val = y[val_idxs]\n    np.save('X_val.npy', X_val)\n    np.save('y_val.npy', y_val)\n    np.save('NON_EMPTY_FRAME_IDXS_VAL.npy', NON_EMPTY_FRAME_IDXS_VAL)\n    # Split Statistics\n    print(f'Patient ID Intersection Train/Val: {set(PARTICIPANT_IDS[train_idxs]).intersection(PARTICIPANT_IDS[val_idxs])}')\n    print(f'X_train shape: {X_train.shape}, X_val shape: {X_val.shape}')\n    print(f'y_train shape: {y_train.shape}, y_val shape: {y_val.shape}')","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:53:30.243140Z","iopub.execute_input":"2023-08-30T16:53:30.243991Z","iopub.status.idle":"2023-08-30T16:53:30.260861Z","shell.execute_reply.started":"2023-08-30T16:53:30.243954Z","shell.execute_reply":"2023-08-30T16:53:30.259625Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Preprocess All Data From Scratch\nif PREPROCESS_DATA:\n    preprocess_data()\n    ROOT_DIR = '.'\nelse:\n    ROOT_DIR = '/kaggle/input/gislr-dataset-public'\n    \n# Load Data\nif USE_VAL:\n    # Load Train\n    X_train = np.load(f'{ROOT_DIR}/X_train.npy')\n    y_train = np.load(f'{ROOT_DIR}/y_train.npy')\n    NON_EMPTY_FRAME_IDXS_TRAIN = np.load(f'{ROOT_DIR}/NON_EMPTY_FRAME_IDXS_TRAIN.npy')\n    # Load Val\n    X_val = np.load(f'{ROOT_DIR}/X_val.npy')\n    y_val = np.load(f'{ROOT_DIR}/y_val.npy')\n    NON_EMPTY_FRAME_IDXS_VAL = np.load(f'{ROOT_DIR}/NON_EMPTY_FRAME_IDXS_VAL.npy')\n    # Define validation Data\n    validation_data = ({ 'frames': X_val, 'non_empty_frame_idxs': NON_EMPTY_FRAME_IDXS_VAL }, y_val)\nelse:\n    X_train = np.load(f'{ROOT_DIR}/X.npy')\n    y_train = np.load(f'{ROOT_DIR}/y.npy')\n    NON_EMPTY_FRAME_IDXS_TRAIN = np.load(f'{ROOT_DIR}/NON_EMPTY_FRAME_IDXS.npy')\n    validation_data = None\n\n# Train \nprint_shape_dtype([X_train, y_train, NON_EMPTY_FRAME_IDXS_TRAIN], ['X_train', 'y_train', 'NON_EMPTY_FRAME_IDXS_TRAIN'])\n# Val\nif USE_VAL:\n    print_shape_dtype([X_val, y_val, NON_EMPTY_FRAME_IDXS_VAL], ['X_val', 'y_val', 'NON_EMPTY_FRAME_IDXS_VAL'])\n# Sanity Check\nprint(f'# NaN Values X_train: {np.isnan(X_train).sum()}')","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:53:48.358559Z","iopub.execute_input":"2023-08-30T16:53:48.359322Z","iopub.status.idle":"2023-08-30T16:54:27.483121Z","shell.execute_reply.started":"2023-08-30T16:53:48.359281Z","shell.execute_reply":"2023-08-30T16:54:27.481880Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Class Count\ndisplay(pd.Series(y_train).value_counts().to_frame('Class Count').iloc[[0,1,2,3,4, -5,-4,-3,-2,-1]])","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:54:35.672596Z","iopub.execute_input":"2023-08-30T16:54:35.673797Z","iopub.status.idle":"2023-08-30T16:54:35.691501Z","shell.execute_reply.started":"2023-08-30T16:54:35.673750Z","shell.execute_reply":"2023-08-30T16:54:35.690183Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Number Of Frames","metadata":{}},{"cell_type":"code","source":"# Vast majority of samples fits has less than 32 non empty frames\nN_EMPTY_FRAMES = (NON_EMPTY_FRAME_IDXS_TRAIN != -1).sum(axis=1) \nN_EMPTY_FRAMES_WATERFALL = []\nfor n in tqdm(range(1,INPUT_SIZE+1)):\n    N_EMPTY_FRAMES_WATERFALL.append(sum(N_EMPTY_FRAMES >= n) / len(NON_EMPTY_FRAME_IDXS_TRAIN) * 100)\n\nplt.figure(figsize=(18,10))\nplt.title('Waterfall Plot For Number Of Non Empty Frames')\npd.Series(N_EMPTY_FRAMES_WATERFALL).plot(kind='bar')\nplt.grid(axis='y')\nplt.xticks(np.arange(INPUT_SIZE), np.arange(1, INPUT_SIZE+1))\nplt.xlabel('Number of Non Empty Frames', size=16)\nplt.yticks(np.arange(0, 100+10, 10))\nplt.ylim(0, 100)\nplt.ylabel('Percentage of Samples With At Least N Non Empty Frames', size=16)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:18:22.241170Z","iopub.execute_input":"2023-08-30T12:18:22.241472Z","iopub.status.idle":"2023-08-30T12:18:43.250571Z","shell.execute_reply.started":"2023-08-30T12:18:22.241443Z","shell.execute_reply":"2023-08-30T12:18:43.249463Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Percentage of Frames Filled","metadata":{}},{"cell_type":"code","source":"# Percentage of frames filled, this is the maximum fill percentage of each landmark\nP_DATA_FILLED = (NON_EMPTY_FRAME_IDXS_TRAIN != -1).sum() / NON_EMPTY_FRAME_IDXS_TRAIN.size * 100\nprint(f'P_DATA_FILLED: {P_DATA_FILLED:.2f}%')","metadata":{"execution":{"iopub.status.busy":"2023-08-30T16:59:59.383628Z","iopub.execute_input":"2023-08-30T16:59:59.384274Z","iopub.status.idle":"2023-08-30T16:59:59.402398Z","shell.execute_reply.started":"2023-08-30T16:59:59.384235Z","shell.execute_reply":"2023-08-30T16:59:59.401147Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Feature Statistics - Lips","metadata":{}},{"cell_type":"code","source":"# Percentage of Lips Measurements\nP_LEFT_LIPS_MEASUREMENTS = (X_train[:,:,LIPS_IDXS] != 0).sum() / X_train[:,:,LIPS_IDXS].size / P_DATA_FILLED * 1e4\nprint(f'P_LEFT_LIPS_MEASUREMENTS: {P_LEFT_LIPS_MEASUREMENTS:.2f}%')","metadata":{"execution":{"iopub.status.busy":"2023-08-30T17:00:04.417956Z","iopub.execute_input":"2023-08-30T17:00:04.418729Z","iopub.status.idle":"2023-08-30T17:00:21.834787Z","shell.execute_reply.started":"2023-08-30T17:00:04.418686Z","shell.execute_reply":"2023-08-30T17:00:21.833552Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_lips_mean_std():\n    # LIPS\n    LIPS_MEAN_X = np.zeros([LIPS_IDXS.size], dtype=np.float32)\n    LIPS_MEAN_Y = np.zeros([LIPS_IDXS.size], dtype=np.float32)\n    LIPS_STD_X = np.zeros([LIPS_IDXS.size], dtype=np.float32)\n    LIPS_STD_Y = np.zeros([LIPS_IDXS.size], dtype=np.float32)\n\n    fig, axes = plt.subplots(3, 1, figsize=(15, N_DIMS*6))\n\n    for col, ll in enumerate(tqdm( np.transpose(X_train[:,:,LIPS_IDXS], [2,3,0,1]).reshape([LIPS_IDXS.size, N_DIMS, -1]) )):\n        for dim, l in enumerate(ll):\n            v = l[np.nonzero(l)]\n            if dim == 0: # X\n                LIPS_MEAN_X[col] = v.mean()\n                LIPS_STD_X[col] = v.std()\n            if dim == 1: # Y\n                LIPS_MEAN_Y[col] = v.mean()\n                LIPS_STD_Y[col] = v.std()\n\n            axes[dim].boxplot(v, notch=False, showfliers=False, positions=[col], whis=[5,95])\n\n    for ax, dim_name in zip(axes, DIM_NAMES):\n        ax.set_title(f'Lips {dim_name.upper()} Dimension', size=24)\n        ax.tick_params(axis='x', labelsize=8)\n        ax.grid(axis='y')\n\n    plt.subplots_adjust(hspace=0.50)\n    plt.show()\n\n    LIPS_MEAN = np.array([LIPS_MEAN_X, LIPS_MEAN_Y]).T\n    LIPS_STD = np.array([LIPS_STD_X, LIPS_STD_Y]).T\n    \n    return LIPS_MEAN, LIPS_STD\n\nLIPS_MEAN, LIPS_STD = get_lips_mean_std()","metadata":{"execution":{"iopub.status.busy":"2023-08-30T17:02:00.493474Z","iopub.execute_input":"2023-08-30T17:02:00.493906Z","iopub.status.idle":"2023-08-30T17:02:23.828274Z","shell.execute_reply.started":"2023-08-30T17:02:00.493867Z","shell.execute_reply":"2023-08-30T17:02:23.827059Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Feature Statistics - Hands","metadata":{}},{"cell_type":"code","source":"# Verify Normalised to Left Hand Dominant\nP_LEFT_HAND_MEASUREMENTS = (X_train[:,:,LEFT_HAND_IDXS] != 0).sum() / X_train[:,:,LEFT_HAND_IDXS].size / P_DATA_FILLED * 1e4\n# P_RIGHT_HAND_MEASUREMENTS = (X_train[:,:,RIGHT_HAND_IDXS] != 0).sum() / X_train[:,:,RIGHT_HAND_IDXS].size / P_DATA_FILLED * 1e4\nprint(f'P_LEFT_HAND_MEASUREMENTS: {P_LEFT_HAND_MEASUREMENTS:.2f}%')","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:22.428976Z","iopub.execute_input":"2023-08-30T12:19:22.430019Z","iopub.status.idle":"2023-08-30T12:19:31.826242Z","shell.execute_reply.started":"2023-08-30T12:19:22.429980Z","shell.execute_reply":"2023-08-30T12:19:31.824955Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_left_right_hand_mean_std():\n    # LEFT HAND\n    LEFT_HANDS_MEAN_X = np.zeros([LEFT_HAND_IDXS.size], dtype=np.float32)\n    LEFT_HANDS_MEAN_Y = np.zeros([LEFT_HAND_IDXS.size], dtype=np.float32)\n    LEFT_HANDS_STD_X = np.zeros([LEFT_HAND_IDXS.size], dtype=np.float32)\n    LEFT_HANDS_STD_Y = np.zeros([LEFT_HAND_IDXS.size], dtype=np.float32)\n\n    fig, axes = plt.subplots(3, 1, figsize=(15, N_DIMS*6))\n\n    for col, ll in enumerate(tqdm( np.transpose(X_train[:,:,LEFT_HAND_IDXS], [2,3,0,1]).reshape([LEFT_HAND_IDXS.size, N_DIMS, -1]) )):\n        for dim, l in enumerate(ll):\n            v = l[np.nonzero(l)]\n            if dim == 0: # X\n                LEFT_HANDS_MEAN_X[col] = v.mean()\n                LEFT_HANDS_STD_X[col] = v.std()\n            if dim == 1: # Y\n                LEFT_HANDS_MEAN_Y[col] = v.mean()\n                LEFT_HANDS_STD_Y[col] = v.std()\n            # Plot\n            axes[dim].boxplot(v, notch=False, showfliers=False, positions=[col], whis=[5,95])\n\n    for ax, dim_name in zip(axes, DIM_NAMES):\n        ax.set_title(f'Hands {dim_name.upper()} Dimension', size=24)\n        ax.tick_params(axis='x', labelsize=8)\n        ax.grid(axis='y')\n\n    plt.subplots_adjust(hspace=0.50)\n    plt.show()\n\n    LEFT_HANDS_MEAN = np.array([LEFT_HANDS_MEAN_X, LEFT_HANDS_MEAN_Y]).T\n    LEFT_HANDS_STD = np.array([LEFT_HANDS_STD_X, LEFT_HANDS_STD_Y]).T\n    \n    return LEFT_HANDS_MEAN, LEFT_HANDS_STD\n\nLEFT_HANDS_MEAN, LEFT_HANDS_STD = get_left_right_hand_mean_std()","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:31.828061Z","iopub.execute_input":"2023-08-30T12:19:31.830242Z","iopub.status.idle":"2023-08-30T12:19:43.648528Z","shell.execute_reply.started":"2023-08-30T12:19:31.830200Z","shell.execute_reply":"2023-08-30T12:19:43.647466Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Feature Statistics - Pose","metadata":{}},{"cell_type":"code","source":"# Percentage of Lips Measurements\nP_POSE_MEASUREMENTS = (X_train[:,:,POSE_IDXS] != 0).sum() / X_train[:,:,POSE_IDXS].size / P_DATA_FILLED * 1e4\nprint(f'P_POSE_MEASUREMENTS: {P_POSE_MEASUREMENTS:.2f}%')","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:43.656559Z","iopub.execute_input":"2023-08-30T12:19:43.657543Z","iopub.status.idle":"2023-08-30T12:19:46.358826Z","shell.execute_reply.started":"2023-08-30T12:19:43.657484Z","shell.execute_reply":"2023-08-30T12:19:46.357491Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_pose_mean_std():\n    # POSE\n    POSE_MEAN_X = np.zeros([POSE_IDXS.size], dtype=np.float32)\n    POSE_MEAN_Y = np.zeros([POSE_IDXS.size], dtype=np.float32)\n    POSE_STD_X = np.zeros([POSE_IDXS.size], dtype=np.float32)\n    POSE_STD_Y = np.zeros([POSE_IDXS.size], dtype=np.float32)\n\n    fig, axes = plt.subplots(3, 1, figsize=(15, N_DIMS*6))\n\n    for col, ll in enumerate(tqdm( np.transpose(X_train[:,:,POSE_IDXS], [2,3,0,1]).reshape([POSE_IDXS.size, N_DIMS, -1]) )):\n        for dim, l in enumerate(ll):\n            v = l[np.nonzero(l)]\n            if dim == 0: # X\n                POSE_MEAN_X[col] = v.mean()\n                POSE_STD_X[col] = v.std()\n            if dim == 1: # Y\n                POSE_MEAN_Y[col] = v.mean()\n                POSE_STD_Y[col] = v.std()\n\n            axes[dim].boxplot(v, notch=False, showfliers=False, positions=[col], whis=[5,95])\n\n    for ax, dim_name in zip(axes, DIM_NAMES):\n        ax.set_title(f'Pose {dim_name.upper()} Dimension', size=24)\n        ax.tick_params(axis='x', labelsize=8)\n        ax.grid(axis='y')\n\n    plt.subplots_adjust(hspace=0.50)\n    plt.show()\n\n    POSE_MEAN = np.array([POSE_MEAN_X, POSE_MEAN_Y]).T\n    POSE_STD = np.array([POSE_STD_X, POSE_STD_Y]).T\n    \n    return POSE_MEAN, POSE_STD\n\nPOSE_MEAN, POSE_STD = get_pose_mean_std()","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:46.361654Z","iopub.execute_input":"2023-08-30T12:19:46.362186Z","iopub.status.idle":"2023-08-30T12:19:50.314618Z","shell.execute_reply.started":"2023-08-30T12:19:46.362151Z","shell.execute_reply":"2023-08-30T12:19:50.313457Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Samples","metadata":{}},{"cell_type":"code","source":"# Custom sampler to get a batch containing N times all signs\ndef get_train_batch_all_signs(X, y, NON_EMPTY_FRAME_IDXS, n=BATCH_ALL_SIGNS_N):\n    # Arrays to store batch in\n    X_batch = np.zeros([NUM_CLASSES*n, INPUT_SIZE, N_COLS, N_DIMS], dtype=np.float32)\n    y_batch = np.arange(0, NUM_CLASSES, step=1/n, dtype=np.float32).astype(np.int64)\n    non_empty_frame_idxs_batch = np.zeros([NUM_CLASSES*n, INPUT_SIZE], dtype=np.float32)\n    \n    # Dictionary mapping ordinally encoded sign to corresponding sample indices\n    CLASS2IDXS = {}\n    for i in range(NUM_CLASSES):\n        CLASS2IDXS[i] = np.argwhere(y == i).squeeze().astype(np.int32)\n            \n    while True:\n        # Fill batch arrays\n        for i in range(NUM_CLASSES):\n            idxs = np.random.choice(CLASS2IDXS[i], n)\n            X_batch[i*n:(i+1)*n] = X[idxs]\n            non_empty_frame_idxs_batch[i*n:(i+1)*n] = NON_EMPTY_FRAME_IDXS[idxs]\n        \n        yield { 'frames': X_batch, 'non_empty_frame_idxs': non_empty_frame_idxs_batch }, y_batch","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:50.316440Z","iopub.execute_input":"2023-08-30T12:19:50.316858Z","iopub.status.idle":"2023-08-30T12:19:50.327327Z","shell.execute_reply.started":"2023-08-30T12:19:50.316818Z","shell.execute_reply":"2023-08-30T12:19:50.326239Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dummy_dataset = get_train_batch_all_signs(X_train, y_train, NON_EMPTY_FRAME_IDXS_TRAIN)\nX_batch, y_batch = next(dummy_dataset)\n\nfor k, v in X_batch.items():\n    print(f'{k} shape: {v.shape}, dtype: {v.dtype}')\n\n# Batch shape/dtype\nprint(f'y_batch shape: {y_batch.shape}, dtype: {y_batch.dtype}')\n# Verify each batch contains each sign exactly N times\ndisplay(pd.Series(y_batch).value_counts().to_frame('Counts'))","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:50.328770Z","iopub.execute_input":"2023-08-30T12:19:50.329957Z","iopub.status.idle":"2023-08-30T12:19:50.417315Z","shell.execute_reply.started":"2023-08-30T12:19:50.329916Z","shell.execute_reply":"2023-08-30T12:19:50.416189Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Model Config","metadata":{}},{"cell_type":"code","source":"# Epsilon value for layer normalisation\nLAYER_NORM_EPS = 1e-6\n\n# Dense layer units for landmarks\nLIPS_UNITS = 384\nHANDS_UNITS = 384\nPOSE_UNITS = 384\n# final embedding and transformer embedding size\nUNITS = 512\n\n# Transformer\nNUM_BLOCKS = 2\nMLP_RATIO = 2\n\n# Dropout\nEMBEDDING_DROPOUT = 0.00\nMLP_DROPOUT_RATIO = 0.30\nCLASSIFIER_DROPOUT_RATIO = 0.10\n\n# Initiailizers\nINIT_HE_UNIFORM = tf.keras.initializers.he_uniform\nINIT_GLOROT_UNIFORM = tf.keras.initializers.glorot_uniform\nINIT_ZEROS = tf.keras.initializers.constant(0.0)\n# Activations\nGELU = tf.keras.activations.gelu\n\nprint(f'UNITS: {UNITS}')","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:50.418779Z","iopub.execute_input":"2023-08-30T12:19:50.419723Z","iopub.status.idle":"2023-08-30T12:19:50.428642Z","shell.execute_reply.started":"2023-08-30T12:19:50.419679Z","shell.execute_reply":"2023-08-30T12:19:50.427372Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Transformer\n\nNeed to implement transformer from scratch as TFLite does not support the native TF implementation of MultiHeadAttention.","metadata":{}},{"cell_type":"code","source":"# based on: https://stackoverflow.com/questions/67342988/verifying-the-implementation-of-multihead-attention-in-transformer\n# replaced softmax with softmax layer to support masked softmax\ndef scaled_dot_product(q,k,v, softmax, attention_mask):\n    #calculates Q . K(transpose)\n    qkt = tf.matmul(q,k,transpose_b=True)\n    #caculates scaling factor\n    dk = tf.math.sqrt(tf.cast(q.shape[-1],dtype=tf.float32))\n    scaled_qkt = qkt/dk\n    softmax = softmax(scaled_qkt, mask=attention_mask)\n    \n    z = tf.matmul(softmax,v)\n    #shape: (m,Tx,depth), same shape as q,k,v\n    return z\n\nclass MultiHeadAttention(tf.keras.layers.Layer):\n    def __init__(self,d_model,num_of_heads):\n        super(MultiHeadAttention,self).__init__()\n        self.d_model = d_model\n        self.num_of_heads = num_of_heads\n        self.depth = d_model//num_of_heads\n        self.wq = [tf.keras.layers.Dense(self.depth) for i in range(num_of_heads)]\n        self.wk = [tf.keras.layers.Dense(self.depth) for i in range(num_of_heads)]\n        self.wv = [tf.keras.layers.Dense(self.depth) for i in range(num_of_heads)]\n        self.wo = tf.keras.layers.Dense(d_model)\n        self.softmax = tf.keras.layers.Softmax()\n        \n    def call(self,x, attention_mask):\n        \n        multi_attn = []\n        for i in range(self.num_of_heads):\n            Q = self.wq[i](x)\n            K = self.wk[i](x)\n            V = self.wv[i](x)\n            multi_attn.append(scaled_dot_product(Q,K,V, self.softmax, attention_mask))\n            \n        multi_head = tf.concat(multi_attn,axis=-1)\n        multi_head_attention = self.wo(multi_head)\n        return multi_head_attention","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:50.430349Z","iopub.execute_input":"2023-08-30T12:19:50.431142Z","iopub.status.idle":"2023-08-30T12:19:50.447915Z","shell.execute_reply.started":"2023-08-30T12:19:50.431101Z","shell.execute_reply":"2023-08-30T12:19:50.446832Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Full Transformer\nclass Transformer(tf.keras.Model):\n    def __init__(self, num_blocks):\n        super(Transformer, self).__init__(name='transformer')\n        self.num_blocks = num_blocks\n    \n    def build(self, input_shape):\n        self.ln_1s = []\n        self.mhas = []\n        self.ln_2s = []\n        self.mlps = []\n        # Make Transformer Blocks\n        for i in range(self.num_blocks):\n            # Multi Head Attention\n            self.mhas.append(MultiHeadAttention(UNITS, 8))\n            # Multi Layer Perception\n            self.mlps.append(tf.keras.Sequential([\n                tf.keras.layers.Dense(UNITS * MLP_RATIO, activation=GELU, kernel_initializer=INIT_GLOROT_UNIFORM),\n                tf.keras.layers.Dropout(MLP_DROPOUT_RATIO),\n                tf.keras.layers.Dense(UNITS, kernel_initializer=INIT_HE_UNIFORM),\n            ]))\n        \n    def call(self, x, attention_mask):\n        # Iterate input over transformer blocks\n        for mha, mlp in zip(self.mhas, self.mlps):\n            x = x + mha(x, attention_mask)\n            x = x + mlp(x)\n    \n        return x","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:50.449373Z","iopub.execute_input":"2023-08-30T12:19:50.449793Z","iopub.status.idle":"2023-08-30T12:19:50.463578Z","shell.execute_reply.started":"2023-08-30T12:19:50.449750Z","shell.execute_reply":"2023-08-30T12:19:50.462558Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Landmark Embedding","metadata":{}},{"cell_type":"code","source":"class LandmarkEmbedding(tf.keras.Model):\n    def __init__(self, units, name):\n        super(LandmarkEmbedding, self).__init__(name=f'{name}_embedding')\n        self.units = units\n        \n    def build(self, input_shape):\n        # Embedding for missing landmark in frame, initizlied with zeros\n        self.empty_embedding = self.add_weight(\n            name=f'{self.name}_empty_embedding',\n            shape=[self.units],\n            initializer=INIT_ZEROS,\n        )\n        # Embedding\n        self.dense = tf.keras.Sequential([\n            tf.keras.layers.Dense(self.units, name=f'{self.name}_dense_1', use_bias=False, kernel_initializer=INIT_GLOROT_UNIFORM),\n            tf.keras.layers.Activation(GELU),\n            tf.keras.layers.Dense(self.units, name=f'{self.name}_dense_2', use_bias=False, kernel_initializer=INIT_HE_UNIFORM),\n        ], name=f'{self.name}_dense')\n\n    def call(self, x):\n        return tf.where(\n                # Checks whether landmark is missing in frame\n                tf.reduce_sum(x, axis=2, keepdims=True) == 0,\n                # If so, the empty embedding is used\n                self.empty_embedding,\n                # Otherwise the landmark data is embedded\n                self.dense(x),\n            )","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:50.465404Z","iopub.execute_input":"2023-08-30T12:19:50.465869Z","iopub.status.idle":"2023-08-30T12:19:50.478991Z","shell.execute_reply.started":"2023-08-30T12:19:50.465829Z","shell.execute_reply":"2023-08-30T12:19:50.477866Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Embedding","metadata":{}},{"cell_type":"code","source":"class Embedding(tf.keras.Model):\n    def __init__(self):\n        super(Embedding, self).__init__()\n        \n    def get_diffs(self, l):\n        S = l.shape[2]\n        other = tf.expand_dims(l, 3)\n        other = tf.repeat(other, S, axis=3)\n        other = tf.transpose(other, [0,1,3,2])\n        diffs = tf.expand_dims(l, 3) - other\n        diffs = tf.reshape(diffs, [-1, INPUT_SIZE, S*S])\n        return diffs\n\n    def build(self, input_shape):\n        # Positional Embedding, initialized with zeros\n        self.positional_embedding = tf.keras.layers.Embedding(INPUT_SIZE+1, UNITS, embeddings_initializer=INIT_ZEROS)\n        # Embedding layer for Landmarks\n        self.lips_embedding = LandmarkEmbedding(LIPS_UNITS, 'lips')\n        self.left_hand_embedding = LandmarkEmbedding(HANDS_UNITS, 'left_hand')\n        self.pose_embedding = LandmarkEmbedding(POSE_UNITS, 'pose')\n        # Landmark Weights\n        self.landmark_weights = tf.Variable(tf.zeros([3], dtype=tf.float32), name='landmark_weights')\n        # Fully Connected Layers for combined landmarks\n        self.fc = tf.keras.Sequential([\n            tf.keras.layers.Dense(UNITS, name='fully_connected_1', use_bias=False, kernel_initializer=INIT_GLOROT_UNIFORM),\n            tf.keras.layers.Activation(GELU),\n            tf.keras.layers.Dense(UNITS, name='fully_connected_2', use_bias=False, kernel_initializer=INIT_HE_UNIFORM),\n        ], name='fc')\n\n\n    def call(self, lips0, left_hand0, pose0, non_empty_frame_idxs, training=False):\n        # Lips\n        lips_embedding = self.lips_embedding(lips0)\n        # Left Hand\n        left_hand_embedding = self.left_hand_embedding(left_hand0)\n        # Pose\n        pose_embedding = self.pose_embedding(pose0)\n        # Merge Embeddings of all landmarks with mean pooling\n        x = tf.stack((\n            lips_embedding, left_hand_embedding, pose_embedding,\n        ), axis=3)\n        x = x * tf.nn.softmax(self.landmark_weights)\n        x = tf.reduce_sum(x, axis=3)\n        # Fully Connected Layers\n        x = self.fc(x)\n        # Add Positional Embedding\n        max_frame_idxs = tf.clip_by_value(\n                tf.reduce_max(non_empty_frame_idxs, axis=1, keepdims=True),\n                1,\n                np.PINF,\n            )\n        normalised_non_empty_frame_idxs = tf.where(\n            tf.math.equal(non_empty_frame_idxs, -1.0),\n            INPUT_SIZE,\n            tf.cast(\n                non_empty_frame_idxs / max_frame_idxs * INPUT_SIZE,\n                tf.int32,\n            ),\n        )\n        x = x + self.positional_embedding(normalised_non_empty_frame_idxs)\n        \n        return x","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:50.482779Z","iopub.execute_input":"2023-08-30T12:19:50.483206Z","iopub.status.idle":"2023-08-30T12:19:50.501977Z","shell.execute_reply.started":"2023-08-30T12:19:50.483177Z","shell.execute_reply":"2023-08-30T12:19:50.500020Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Augmentation","metadata":{}},{"cell_type":"code","source":"# Not used, adds random X/y translation to input on samples level\nclass Augmentation(tf.keras.layers.Layer):\n    def __init__(self, noise_std):\n        super(Augmentation, self).__init__()\n        self.noise_std = noise_std\n    \n    def add_noise(self, t):\n        B = tf.shape(t)[0]\n        return tf.where(\n            t == 0.0,\n            0.0,\n            t + tf.random.normal([B,1,1,tf.shape(t)[3]], 0, self.noise_std),\n        )\n    \n    def call(self, lips0, left_hand0, pose0, training=False):\n        if training:\n            # Lips\n            lips0 = self.add_noise(lips0)\n            # Left Hand\n            left_hand0 = self.add_noise(left_hand0)\n            # Pose\n            pose0 = self.add_noise(pose0)\n        \n        return lips0, left_hand0, pose0","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:50.503830Z","iopub.execute_input":"2023-08-30T12:19:50.504253Z","iopub.status.idle":"2023-08-30T12:19:50.516806Z","shell.execute_reply.started":"2023-08-30T12:19:50.504159Z","shell.execute_reply":"2023-08-30T12:19:50.515634Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Sparse Categorical Crossentropy With Label Smoothing","metadata":{}},{"cell_type":"code","source":"# source:: https://stackoverflow.com/questions/60689185/label-smoothing-for-sparse-categorical-crossentropy\ndef scce_with_ls(y_true, y_pred):\n    # One Hot Encode Sparsely Encoded Target Sign\n    y_true = tf.cast(y_true, tf.int32)\n    y_true = tf.one_hot(y_true, NUM_CLASSES, axis=1)\n    y_true = tf.squeeze(y_true, axis=2)\n    # Categorical Crossentropy with native label smoothing support\n    return tf.keras.losses.categorical_crossentropy(y_true, y_pred, label_smoothing=0.25)","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:50.518660Z","iopub.execute_input":"2023-08-30T12:19:50.519098Z","iopub.status.idle":"2023-08-30T12:19:50.531114Z","shell.execute_reply.started":"2023-08-30T12:19:50.519058Z","shell.execute_reply":"2023-08-30T12:19:50.530008Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Model","metadata":{}},{"cell_type":"code","source":"def get_model():\n    # Inputs\n    frames = tf.keras.layers.Input([INPUT_SIZE, N_COLS, N_DIMS], dtype=tf.float32, name='frames')\n    non_empty_frame_idxs = tf.keras.layers.Input([INPUT_SIZE], dtype=tf.float32, name='non_empty_frame_idxs')\n    # Padding Mask\n    mask0 = tf.cast(tf.math.not_equal(non_empty_frame_idxs, -1), tf.float32)\n    mask0 = tf.expand_dims(mask0, axis=2)\n    # Random Frame Masking\n    mask = tf.where(\n        (tf.random.uniform(tf.shape(mask0)) > 0.25) & tf.math.not_equal(mask0, 0.0),\n        1.0,\n        0.0,\n    )\n    # Correct Samples Which are all masked now...\n    mask = tf.where(\n        tf.math.equal(tf.reduce_sum(mask, axis=[1,2], keepdims=True), 0.0),\n        mask0,\n        mask,\n    )\n    \n    \n    \"\"\"\n        left_hand: 468:489\n        pose: 489:522\n        right_hand: 522:543\n    \"\"\"\n    x = frames\n    x = tf.slice(x, [0,0,0,0], [-1,INPUT_SIZE, N_COLS, 2])\n    # LIPS\n    lips = tf.slice(x, [0,0,LIPS_START,0], [-1,INPUT_SIZE, 40, 2])\n    lips = tf.where(\n            tf.math.equal(lips, 0.0),\n            0.0,\n            (lips - LIPS_MEAN) / LIPS_STD,\n        )\n    # LEFT HAND\n    left_hand = tf.slice(x, [0,0,40,0], [-1,INPUT_SIZE, 21, 2])\n    left_hand = tf.where(\n            tf.math.equal(left_hand, 0.0),\n            0.0,\n            (left_hand - LEFT_HANDS_MEAN) / LEFT_HANDS_STD,\n        )\n    # POSE\n    pose = tf.slice(x, [0,0,61,0], [-1,INPUT_SIZE, 5, 2])\n    pose = tf.where(\n            tf.math.equal(pose, 0.0),\n            0.0,\n            (pose - POSE_MEAN) / POSE_STD,\n        )\n    \n    # Flatten\n    lips = tf.reshape(lips, [-1, INPUT_SIZE, 40*2])\n    left_hand = tf.reshape(left_hand, [-1, INPUT_SIZE, 21*2])\n    pose = tf.reshape(pose, [-1, INPUT_SIZE, 5*2])\n        \n    # Embedding\n    x = Embedding()(lips, left_hand, pose, non_empty_frame_idxs)\n    \n    # Encoder Transformer Blocks\n    x = Transformer(NUM_BLOCKS)(x, mask)\n    \n    # Pooling\n    x = tf.reduce_sum(x * mask, axis=1) / tf.reduce_sum(mask, axis=1)\n    # Classifier Dropout\n    x = tf.keras.layers.Dropout(CLASSIFIER_DROPOUT_RATIO)(x)\n    # Classification Layer\n    x = tf.keras.layers.Dense(NUM_CLASSES, activation=tf.keras.activations.softmax, kernel_initializer=INIT_GLOROT_UNIFORM)(x)\n    \n    outputs = x\n    \n    # Create Tensorflow Model\n    model = tf.keras.models.Model(inputs=[frames, non_empty_frame_idxs], outputs=outputs)\n    \n    # Sparse Categorical Cross Entropy With Label Smoothing\n    loss = scce_with_ls\n    \n    # Adam Optimizer with weight decay\n    optimizer = tfa.optimizers.AdamW(learning_rate=1e-3, weight_decay=1e-5, clipnorm=1.0)\n    \n    # TopK Metrics\n    metrics = [\n        tf.keras.metrics.SparseCategoricalAccuracy(name='acc'),\n        tf.keras.metrics.SparseTopKCategoricalAccuracy(k=5, name='top_5_acc'),\n        tf.keras.metrics.SparseTopKCategoricalAccuracy(k=10, name='top_10_acc'),\n    ]\n    \n    model.compile(loss=loss, optimizer=optimizer, metrics=metrics)\n    \n    return model","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:50.534947Z","iopub.execute_input":"2023-08-30T12:19:50.535289Z","iopub.status.idle":"2023-08-30T12:19:50.558777Z","shell.execute_reply.started":"2023-08-30T12:19:50.535260Z","shell.execute_reply":"2023-08-30T12:19:50.557655Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"tf.keras.backend.clear_session()\n\nmodel = get_model()","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:50.560542Z","iopub.execute_input":"2023-08-30T12:19:50.561085Z","iopub.status.idle":"2023-08-30T12:19:53.284347Z","shell.execute_reply.started":"2023-08-30T12:19:50.561025Z","shell.execute_reply":"2023-08-30T12:19:53.283255Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Plot model summary\nmodel.summary(expand_nested=True)","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:53.286558Z","iopub.execute_input":"2023-08-30T12:19:53.287195Z","iopub.status.idle":"2023-08-30T12:19:53.465430Z","shell.execute_reply.started":"2023-08-30T12:19:53.287153Z","shell.execute_reply":"2023-08-30T12:19:53.464600Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"tf.keras.utils.plot_model(model, show_shapes=True, show_dtype=True, show_layer_names=True, expand_nested=True, show_layer_activations=True)","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:53.466892Z","iopub.execute_input":"2023-08-30T12:19:53.467253Z","iopub.status.idle":"2023-08-30T12:19:54.543108Z","shell.execute_reply.started":"2023-08-30T12:19:53.467214Z","shell.execute_reply":"2023-08-30T12:19:54.541638Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# No NaN Predictions","metadata":{}},{"cell_type":"code","source":"if not PREPROCESS_DATA and TRAIN_MODEL:\n    y_pred = model.predict_on_batch(X_batch).flatten()\n\n    print(f'# NaN Values In Prediction: {np.isnan(y_pred).sum()}')","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:54.545522Z","iopub.execute_input":"2023-08-30T12:19:54.546260Z","iopub.status.idle":"2023-08-30T12:19:57.943425Z","shell.execute_reply.started":"2023-08-30T12:19:54.546216Z","shell.execute_reply":"2023-08-30T12:19:57.942251Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Weight Initialization","metadata":{}},{"cell_type":"code","source":"if not PREPROCESS_DATA and TRAIN_MODEL:\n    plt.figure(figsize=(12,5))\n    plt.title(f'Softmax Output Initialized Model | µ={y_pred.mean():.3f}, σ={y_pred.std():.3f}', pad=25)\n    pd.Series(y_pred).plot(kind='hist', bins=128, label='Class Probability')\n    plt.xlim(0, max(y_pred) * 1.1)\n    plt.vlines([1 / NUM_CLASSES], 0, plt.ylim()[1], color='red', label=f'Random Guessing Baseline 1/NUM_CLASSES={1 / NUM_CLASSES:.3f}')\n    plt.grid()\n    plt.legend()\n    plt.show()","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:57.945844Z","iopub.execute_input":"2023-08-30T12:19:57.946575Z","iopub.status.idle":"2023-08-30T12:19:58.560166Z","shell.execute_reply.started":"2023-08-30T12:19:57.946530Z","shell.execute_reply":"2023-08-30T12:19:58.558165Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Learning Rate Scheduler","metadata":{}},{"cell_type":"code","source":"def lrfn(current_step, num_warmup_steps, lr_max, num_cycles=0.50, num_training_steps=N_EPOCHS):\n    \n    if current_step < num_warmup_steps:\n        if WARMUP_METHOD == 'log':\n            return lr_max * 0.10 ** (num_warmup_steps - current_step)\n        else:\n            return lr_max * 2 ** -(num_warmup_steps - current_step)\n    else:\n        progress = float(current_step - num_warmup_steps) / float(max(1, num_training_steps - num_warmup_steps))\n\n        return max(0.0, 0.5 * (1.0 + math.cos(math.pi * float(num_cycles) * 2.0 * progress))) * lr_max","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:58.562035Z","iopub.execute_input":"2023-08-30T12:19:58.562798Z","iopub.status.idle":"2023-08-30T12:19:58.571753Z","shell.execute_reply.started":"2023-08-30T12:19:58.562755Z","shell.execute_reply":"2023-08-30T12:19:58.570594Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def plot_lr_schedule(lr_schedule, epochs):\n    fig = plt.figure(figsize=(20, 10))\n    plt.plot([None] + lr_schedule + [None])\n    # X Labels\n    x = np.arange(1, epochs + 1)\n    x_axis_labels = [i if epochs <= 40 or i % 5 == 0 or i == 1 else None for i in range(1, epochs + 1)]\n    plt.xlim([1, epochs])\n    plt.xticks(x, x_axis_labels) # set tick step to 1 and let x axis start at 1\n    \n    # Increase y-limit for better readability\n    plt.ylim([0, max(lr_schedule) * 1.1])\n    \n    # Title\n    schedule_info = f'start: {lr_schedule[0]:.1E}, max: {max(lr_schedule):.1E}, final: {lr_schedule[-1]:.1E}'\n    plt.title(f'Step Learning Rate Schedule, {schedule_info}', size=18, pad=12)\n    \n    # Plot Learning Rates\n    for x, val in enumerate(lr_schedule):\n        if epochs <= 40 or x % 5 == 0 or x is epochs - 1:\n            if x < len(lr_schedule) - 1:\n                if lr_schedule[x - 1] < val:\n                    ha = 'right'\n                else:\n                    ha = 'left'\n            elif x == 0:\n                ha = 'right'\n            else:\n                ha = 'left'\n            plt.plot(x + 1, val, 'o', color='black');\n            offset_y = (max(lr_schedule) - min(lr_schedule)) * 0.02\n            plt.annotate(f'{val:.1E}', xy=(x + 1, val + offset_y), size=12, ha=ha)\n    \n    plt.xlabel('Epoch', size=16, labelpad=5)\n    plt.ylabel('Learning Rate', size=16, labelpad=5)\n    plt.grid()\n    plt.show()\n\n# Learning rate for encoder\nLR_SCHEDULE = [lrfn(step, num_warmup_steps=N_WARMUP_EPOCHS, lr_max=LR_MAX, num_cycles=0.50) for step in range(N_EPOCHS)]\n# Plot Learning Rate Schedule\nplot_lr_schedule(LR_SCHEDULE, epochs=N_EPOCHS)\n# Learning Rate Callback\nlr_callback = tf.keras.callbacks.LearningRateScheduler(lambda step: LR_SCHEDULE[step], verbose=1)","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:58.573329Z","iopub.execute_input":"2023-08-30T12:19:58.573818Z","iopub.status.idle":"2023-08-30T12:19:59.359322Z","shell.execute_reply.started":"2023-08-30T12:19:58.573764Z","shell.execute_reply":"2023-08-30T12:19:59.358274Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Weight Decay Callback","metadata":{}},{"cell_type":"code","source":"# Custom callback to update weight decay with learning rate\nclass WeightDecayCallback(tf.keras.callbacks.Callback):\n    def __init__(self, wd_ratio=WD_RATIO):\n        self.step_counter = 0\n        self.wd_ratio = wd_ratio\n    \n    def on_epoch_begin(self, epoch, logs=None):\n        model.optimizer.weight_decay = model.optimizer.learning_rate * self.wd_ratio\n        print(f'learning rate: {model.optimizer.learning_rate.numpy():.2e}, weight decay: {model.optimizer.weight_decay.numpy():.2e}')","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:59.361134Z","iopub.execute_input":"2023-08-30T12:19:59.361897Z","iopub.status.idle":"2023-08-30T12:19:59.369681Z","shell.execute_reply.started":"2023-08-30T12:19:59.361854Z","shell.execute_reply":"2023-08-30T12:19:59.368566Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Performance Benchmark","metadata":{}},{"cell_type":"code","source":"%%timeit -n 100\nif TRAIN_MODEL:\n    # Verify model prediction is <<<100ms\n    model.predict_on_batch({ 'frames': X_train[:1], 'non_empty_frame_idxs': NON_EMPTY_FRAME_IDXS_TRAIN[:1] })\n    pass","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:19:59.371350Z","iopub.execute_input":"2023-08-30T12:19:59.371752Z","iopub.status.idle":"2023-08-30T12:20:12.449353Z","shell.execute_reply.started":"2023-08-30T12:19:59.371705Z","shell.execute_reply":"2023-08-30T12:20:12.448189Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Training","metadata":{}},{"cell_type":"code","source":"if USE_VAL:\n    # Verify Validation Dataset Covers All Signs\n    print(f'# Unique Signs in Validation Set: {pd.Series(y_val).nunique()}')\n    # Value Counts\n    display(pd.Series(y_val).value_counts().to_frame('Count').iloc[[1,2,3,-3,-2,-1]])","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:20:12.450842Z","iopub.execute_input":"2023-08-30T12:20:12.451482Z","iopub.status.idle":"2023-08-30T12:20:12.459433Z","shell.execute_reply.started":"2023-08-30T12:20:12.451434Z","shell.execute_reply":"2023-08-30T12:20:12.458268Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Evaluate Initialzied Model","metadata":{}},{"cell_type":"code","source":"# Sanity Check\nif TRAIN_MODEL and USE_VAL:\n    _ = model.evaluate(*validation_data, verbose=2)","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:20:12.461325Z","iopub.execute_input":"2023-08-30T12:20:12.462172Z","iopub.status.idle":"2023-08-30T12:20:12.471023Z","shell.execute_reply.started":"2023-08-30T12:20:12.462132Z","shell.execute_reply":"2023-08-30T12:20:12.469970Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Train","metadata":{}},{"cell_type":"code","source":"if TRAIN_MODEL:\n    # Clear all models in GPU\n    tf.keras.backend.clear_session()\n\n    # Get new fresh model\n    model = get_model()\n    \n    # Sanity Check\n    model.summary()\n\n    # Actual Training\n    history = model.fit(\n            x=get_train_batch_all_signs(X_train, y_train, NON_EMPTY_FRAME_IDXS_TRAIN),\n            steps_per_epoch=len(X_train) // (NUM_CLASSES * BATCH_ALL_SIGNS_N),\n            epochs=N_EPOCHS,\n            # Only used for validation data since training data is a generator\n            batch_size=BATCH_SIZE,\n            validation_data=validation_data,\n            callbacks=[\n                lr_callback,\n                WeightDecayCallback(),\n            ],\n            verbose = VERBOSE,\n        )","metadata":{"execution":{"iopub.status.busy":"2023-08-30T12:20:12.474608Z","iopub.execute_input":"2023-08-30T12:20:12.475366Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Save Model Weights\nmodel.save_weights('model.h5')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if USE_VAL:\n    # Validation Predictions\n    y_val_pred = model.predict({ 'frames': X_val, 'non_empty_frame_idxs': NON_EMPTY_FRAME_IDXS_VAL }, verbose=2).argmax(axis=1)\n    # Label\n    labels = [ORD2SIGN.get(i).replace(' ', '_') for i in range(NUM_CLASSES)]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Landmark Attention Weights","metadata":{}},{"cell_type":"code","source":"# Landmark Weights\nfor w in model.get_layer('embedding').weights:\n    if 'landmark_weights' in w.name:\n        weights = scipy.special.softmax(w)\n\nlandmarks = ['lips_embedding', 'left_hand_embedding', 'pose_embedding']\n\nfor w, lm in zip(weights, landmarks):\n    print(f'{lm} weight: {(w*100):.1f}%')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Classification Report","metadata":{}},{"cell_type":"code","source":"def print_classification_report():\n    # Classification report for all signs\n    classification_report = sklearn.metrics.classification_report(\n            y_val,\n            y_val_pred,\n            target_names=labels,\n            output_dict=True,\n        )\n    # Round Data for better readability\n    classification_report = pd.DataFrame(classification_report).T\n    classification_report = classification_report.round(2)\n    classification_report = classification_report.astype({\n            'support': np.uint16,\n        })\n    # Add signs\n    classification_report['sign'] = [e if e in SIGN2ORD else -1 for e in classification_report.index]\n    classification_report['sign_ord'] = classification_report['sign'].apply(SIGN2ORD.get).fillna(-1).astype(np.int16)\n    # Sort on F1-score\n    classification_report = pd.concat((\n        classification_report.head(NUM_CLASSES).sort_values('f1-score', ascending=False),\n        classification_report.tail(3),\n    ))\n\n    pd.options.display.max_rows = 999\n    display(classification_report)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if USE_VAL:\n    print_classification_report()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Training History","metadata":{}},{"cell_type":"code","source":"def plot_history_metric(metric, f_best=np.argmax, ylim=None, yscale=None, yticks=None):\n    plt.figure(figsize=(20, 10))\n    \n    values = history.history[metric]\n    N_EPOCHS = len(values)\n    val = 'val' in ''.join(history.history.keys())\n    # Epoch Ticks\n    if N_EPOCHS <= 20:\n        x = np.arange(1, N_EPOCHS + 1)\n    else:\n        x = [1, 5] + [10 + 5 * idx for idx in range((N_EPOCHS - 10) // 5 + 1)]\n\n    x_ticks = np.arange(1, N_EPOCHS+1)\n\n    # Validation\n    if val:\n        val_values = history.history[f'val_{metric}']\n        val_argmin = f_best(val_values)\n        plt.plot(x_ticks, val_values, label=f'val')\n\n    # summarize history for accuracy\n    plt.plot(x_ticks, values, label=f'train')\n    argmin = f_best(values)\n    plt.scatter(argmin + 1, values[argmin], color='red', s=75, marker='o', label=f'train_best')\n    if val:\n        plt.scatter(val_argmin + 1, val_values[val_argmin], color='purple', s=75, marker='o', label=f'val_best')\n\n    plt.title(f'Model {metric}', fontsize=24, pad=10)\n    plt.ylabel(metric, fontsize=20, labelpad=10)\n\n    if ylim:\n        plt.ylim(ylim)\n\n    if yscale is not None:\n        plt.yscale(yscale)\n        \n    if yticks is not None:\n        plt.yticks(yticks, fontsize=16)\n\n    plt.xlabel('epoch', fontsize=20, labelpad=10)        \n    plt.tick_params(axis='x', labelsize=8)\n    plt.xticks(x, fontsize=16) # set tick step to 1 and let x axis start at 1\n    plt.yticks(fontsize=16)\n    \n    plt.legend(prop={'size': 10})\n    plt.grid()\n    plt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if TRAIN_MODEL:\n    plot_history_metric('loss', f_best=np.argmin)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if TRAIN_MODEL:\n    plot_history_metric('acc', ylim=[0,1], yticks=np.arange(0.0, 1.1, 0.1))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if TRAIN_MODEL:\n    plot_history_metric('top_5_acc', ylim=[0,1], yticks=np.arange(0.0, 1.1, 0.1))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if TRAIN_MODEL:\n    plot_history_metric('top_10_acc', ylim=[0,1], yticks=np.arange(0.0, 1.1, 0.1))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Submission\n\nSubmission code loosley based on [this notebook](https://www.kaggle.com/code/dschettler8845/gislr-learn-eda-baseline#baseline) by [Darien Schettler\n](https://www.kaggle.com/dschettler8845)","metadata":{}},{"cell_type":"code","source":"# TFLite model for submission\nclass TFLiteModel(tf.Module):\n    def __init__(self, model):\n        super(TFLiteModel, self).__init__()\n\n        # Load the feature generation and main models\n        self.preprocess_layer = preprocess_layer\n        self.model = model\n    \n    @tf.function(input_signature=[tf.TensorSpec(shape=[None, N_ROWS, N_DIMS], dtype=tf.float32, name='inputs')])\n    def __call__(self, inputs):\n        # Preprocess Data\n        x, non_empty_frame_idxs = self.preprocess_layer(inputs)\n        # Add Batch Dimension\n        x = tf.expand_dims(x, axis=0)\n        non_empty_frame_idxs = tf.expand_dims(non_empty_frame_idxs, axis=0)\n        # Make Prediction\n        outputs = self.model({ 'frames': x, 'non_empty_frame_idxs': non_empty_frame_idxs })\n        # Squeeze Output 1x250 -> 250\n        outputs = tf.squeeze(outputs, axis=0)\n\n        # Return a dictionary with the output tensor\n        return {'outputs': outputs}\n\n# Define TF Lite Model\ntflite_keras_model = TFLiteModel(model)\n\n# Sanity Check\ndemo_raw_data = load_relevant_data_subset(train['file_path'].values[5])\nprint(f'demo_raw_data shape: {demo_raw_data.shape}, dtype: {demo_raw_data.dtype}')\ndemo_output = tflite_keras_model(demo_raw_data)[\"outputs\"]\nprint(f'demo_output shape: {demo_output.shape}, dtype: {demo_output.dtype}')\ndemo_prediction = demo_output.numpy().argmax()\nprint(f'demo_prediction: {demo_prediction}, correct: {train.iloc[0][\"sign_ord\"]}')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Create Model Converter\nkeras_model_converter = tf.lite.TFLiteConverter.from_keras_model(tflite_keras_model)\n# Convert Model\ntflite_model = keras_model_converter.convert()\n# Write Model\nwith open('/kaggle/working/model.tflite', 'wb') as f:\n    f.write(tflite_model)\n    \n# Zip Model\n!zip submission.zip /kaggle/working/model.tflite","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Verify TFLite model can be loaded and used for prediction\n!pip install tflite-runtime\nimport tflite_runtime.interpreter as tflite\n\ninterpreter = tflite.Interpreter(\"/kaggle/working/model.tflite\")\nfound_signatures = list(interpreter.get_signature_list().keys())\nprediction_fn = interpreter.get_signature_runner(\"serving_default\")\n\noutput = prediction_fn(inputs=demo_raw_data)\nsign = output['outputs'].argmax()\n\nprint(\"PRED : \", ORD2SIGN.get(sign), f'[{sign}]')\nprint(\"TRUE : \", train.sign.values[0], f'[{train.sign_ord.values[0]}]')","metadata":{"trusted":true},"execution_count":null,"outputs":[]}],"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"}}