{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":102335,"databundleVersionId":12518947,"sourceType":"competition"},{"sourceId":12139340,"sourceType":"datasetVersion","datasetId":7645099},{"sourceId":12293285,"sourceType":"datasetVersion","datasetId":7748073},{"sourceId":12411879,"sourceType":"datasetVersion","datasetId":7827797},{"sourceId":240649816,"sourceType":"kernelVersion"},{"sourceId":246893721,"sourceType":"kernelVersion"},{"sourceId":251413288,"sourceType":"kernelVersion"},{"sourceId":470587,"sourceType":"modelInstanceVersion","modelInstanceId":379625,"modelId":398856},{"sourceId":471764,"sourceType":"modelInstanceVersion","modelInstanceId":380358,"modelId":400086}],"dockerImageVersionId":31090,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import json, joblib, numpy as np\nimport random\nfrom pathlib import Path\nimport warnings \nwarnings.filterwarnings(\"ignore\")\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import StandardScaler, LabelEncoder\nfrom sklearn.utils.class_weight import compute_class_weight\n\nfrom tensorflow.keras.utils import Sequence, to_categorical, pad_sequences\nfrom tensorflow.keras.models import Model, load_model\nfrom tensorflow.keras.layers import (\n    Input, Conv1D, BatchNormalization, Activation, add, MaxPooling1D, Dropout,\n    Bidirectional, LSTM, GlobalAveragePooling1D, Dense, Multiply, Reshape,\n    Lambda, Concatenate, GRU, GaussianNoise\n)\nfrom tensorflow.keras.regularizers import l2\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras.callbacks import EarlyStopping\nfrom tensorflow.keras import backend as K\nimport tensorflow as tf\nimport polars as pl\nfrom sklearn.model_selection import StratifiedGroupKFold\nfrom scipy.spatial.transform import Rotation as R\nimport os\nimport torch\nimport kagglehub\nfrom pathlib import Path\nimport numpy as np\nimport torch.nn as nn\nimport torch.nn.functional as F\nfrom scipy.spatial.transform import Rotation as R\nfrom collections import defaultdict\nfrom torch.utils.data import Dataset, DataLoader, Subset\nfrom tqdm.notebook import tqdm\nfrom torch.amp import autocast\nimport pandas as pd\nimport polars as pl\nfrom sklearn.model_selection import StratifiedKFold\nfrom sklearn.utils.class_weight import compute_class_weight\nfrom sklearn.preprocessing import StandardScaler, LabelEncoder\nfrom transformers import BertConfig, BertModel\n\n\ndef seed_everything(seed):\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    random.seed(seed)\n    np.random.seed(seed)\n    tf.random.set_seed(seed)\n    tf.experimental.numpy.random.seed(seed)\n    os.environ['TF_CUDNN_DETERMINISTIC'] = '1'\n    os.environ['TF_DETERMINISTIC_OPS'] = '1'\n\nseed_everything(seed=42)\n# (Competition metric will only be imported when TRAINing)\nTRAIN = False                     # ← set to True when you want to train\nRAW_DIR = Path(\"/kaggle/input/cmi-detect-behavior-with-sensor-data\")\nPRETRAINED_DIR = Path(\"/kaggle/input/cmi-d-111\")\nEXPORT_DIR = Path(\"./\")                                    # artefacts will be saved here\nBATCH_SIZE = 64\nPAD_PERCENTILE = 95\nLR_INIT = 5e-4\nWD = 3e-3\nMIXUP_ALPHA = 0.4\nEPOCHS = 160\nPATIENCE = 40\n\nprint(\"▶ imports ready · tensorflow\", tf.__version__)\n\n#Tensor Manipulations\ndef time_sum(x):\n    return K.sum(x, axis=1)\n\ndef squeeze_last_axis(x):\n    return tf.squeeze(x, axis=-1)\n\ndef expand_last_axis(x):\n    return tf.expand_dims(x, axis=-1)\n\ndef se_block(x, reduction=8):\n    ch = x.shape[-1]\n    se = GlobalAveragePooling1D()(x)\n    se = Dense(ch // reduction, activation='relu')(se)\n    se = Dense(ch, activation='sigmoid')(se)\n    se = Reshape((1, ch))(se)\n    return Multiply()([x, se])\n\n# Residual CNN Block with SE\ndef residual_se_cnn_block(x, filters, kernel_size, pool_size=2, drop=0.3, wd=1e-4):\n    shortcut = x\n    for _ in range(2):\n        x = Conv1D(filters, kernel_size, padding='same', use_bias=False,\n                   kernel_regularizer=l2(wd))(x)\n        x = BatchNormalization()(x)\n        x = Activation('relu')(x)\n    x = se_block(x)\n    if shortcut.shape[-1] != filters:\n        shortcut = Conv1D(filters, 1, padding='same', use_bias=False,\n                          kernel_regularizer=l2(wd))(shortcut)\n        shortcut = BatchNormalization()(shortcut)\n    x = add([x, shortcut])\n    x = Activation('relu')(x)\n    x = MaxPooling1D(pool_size)(x)\n    x = Dropout(drop)(x)\n    return x\n\ndef attention_layer(inputs):\n    score = Dense(1, activation='tanh')(inputs)\n    score = Lambda(squeeze_last_axis)(score)\n    weights = Activation('softmax')(score)\n    weights = Lambda(expand_last_axis)(weights)\n    context = Multiply()([inputs, weights])\n    context = Lambda(time_sum)(context)\n    return context\n\n# Normalizes and cleans the time series sequence. \n\ndef preprocess_sequence(df_seq: pd.DataFrame, feature_cols: list[str], scaler: StandardScaler):\n    mat = df_seq[feature_cols].ffill().bfill().fillna(0).values\n    return scaler.transform(mat).astype('float32')\n\n# MixUp the data argumentation in order to regularize the neural network. \n\nclass MixupGenerator(Sequence):\n    def __init__(self, X, y, batch_size, alpha=0.2):\n        self.X, self.y = X, y\n        self.batch = batch_size\n        self.alpha = alpha\n        self.indices = np.arange(len(X))\n    def __len__(self):\n        return int(np.ceil(len(self.X) / self.batch))\n    def __getitem__(self, i):\n        idx = self.indices[i*self.batch:(i+1)*self.batch]\n        Xb, yb = self.X[idx], self.y[idx]\n        lam = np.random.beta(self.alpha, self.alpha)\n        perm = np.random.permutation(len(Xb))\n        X_mix = lam * Xb + (1-lam) * Xb[perm]\n        y_mix = lam * yb + (1-lam) * yb[perm]\n        return X_mix, y_mix\n    def on_epoch_end(self):\n        np.random.shuffle(self.indices)\n\n\ndef remove_gravity_from_acc(acc_data, rot_data):\n\n    if isinstance(acc_data, pd.DataFrame):\n        acc_values = acc_data[['acc_x', 'acc_y', 'acc_z']].values\n    else:\n        acc_values = acc_data\n\n    if isinstance(rot_data, pd.DataFrame):\n        quat_values = rot_data[['rot_x', 'rot_y', 'rot_z', 'rot_w']].values\n    else:\n        quat_values = rot_data\n\n    num_samples = acc_values.shape[0]\n    linear_accel = np.zeros_like(acc_values)\n    \n    gravity_world = np.array([0, 0, 9.81])\n\n    for i in range(num_samples):\n        if np.all(np.isnan(quat_values[i])) or np.all(np.isclose(quat_values[i], 0)):\n            linear_accel[i, :] = acc_values[i, :] \n            continue\n\n        try:\n            rotation = R.from_quat(quat_values[i])\n            gravity_sensor_frame = rotation.apply(gravity_world, inverse=True)\n            linear_accel[i, :] = acc_values[i, :] - gravity_sensor_frame\n        except ValueError:\n             linear_accel[i, :] = acc_values[i, :]\n             \n    return linear_accel\n\ndef calculate_angular_velocity_from_quat(rot_data, time_delta=1/200): # Assuming 200Hz sampling rate\n    if isinstance(rot_data, pd.DataFrame):\n        quat_values = rot_data[['rot_x', 'rot_y', 'rot_z', 'rot_w']].values\n    else:\n        quat_values = rot_data\n\n    num_samples = quat_values.shape[0]\n    angular_vel = np.zeros((num_samples, 3))\n\n    for i in range(num_samples - 1):\n        q_t = quat_values[i]\n        q_t_plus_dt = quat_values[i+1]\n\n        if np.all(np.isnan(q_t)) or np.all(np.isclose(q_t, 0)) or \\\n           np.all(np.isnan(q_t_plus_dt)) or np.all(np.isclose(q_t_plus_dt, 0)):\n            continue\n\n        try:\n            rot_t = R.from_quat(q_t)\n            rot_t_plus_dt = R.from_quat(q_t_plus_dt)\n\n            # Calculate the relative rotation\n            delta_rot = rot_t.inv() * rot_t_plus_dt\n            \n            # Convert delta rotation to angular velocity vector\n            # The rotation vector (Euler axis * angle) scaled by 1/dt\n            # is a good approximation for small delta_rot\n            angular_vel[i, :] = delta_rot.as_rotvec() / time_delta\n        except ValueError:\n            # If quaternion is invalid, angular velocity remains zero\n            pass\n            \n    return angular_vel\n    \ndef calculate_angular_distance(rot_data):\n    if isinstance(rot_data, pd.DataFrame):\n        quat_values = rot_data[['rot_x', 'rot_y', 'rot_z', 'rot_w']].values\n    else:\n        quat_values = rot_data\n\n    num_samples = quat_values.shape[0]\n    angular_dist = np.zeros(num_samples)\n\n    for i in range(num_samples - 1):\n        q1 = quat_values[i]\n        q2 = quat_values[i+1]\n\n        if np.all(np.isnan(q1)) or np.all(np.isclose(q1, 0)) or \\\n           np.all(np.isnan(q2)) or np.all(np.isclose(q2, 0)):\n            angular_dist[i] = 0 # Или np.nan, в зависимости от желаемого поведения\n            continue\n        try:\n            # Преобразование кватернионов в объекты Rotation\n            r1 = R.from_quat(q1)\n            r2 = R.from_quat(q2)\n\n            relative_rotation = r1.inv() * r2\n            \n            angle = np.linalg.norm(relative_rotation.as_rotvec())\n            angular_dist[i] = angle\n        except ValueError:\n            angular_dist[i] = 0 \n            pass\n            \n    return angular_dist\n\ndef build_two_branch_model(pad_len, imu_dim, tof_dim, n_classes, wd=1e-4):\n    inp = Input(shape=(pad_len, imu_dim+tof_dim))\n    imu = Lambda(lambda t: t[:, :, :imu_dim])(inp)\n    tof = Lambda(lambda t: t[:, :, imu_dim:])(inp)\n\n    # IMU deep branch\n    x1 = residual_se_cnn_block(imu, 64, 3, drop=0.1, wd=wd)\n    x1 = residual_se_cnn_block(x1, 128, 5, drop=0.1, wd=wd)\n\n    # TOF/Thermal lighter branch\n    x2 = Conv1D(64, 3, padding='same', use_bias=False, kernel_regularizer=l2(wd))(tof)\n    x2 = BatchNormalization()(x2); x2 = Activation('relu')(x2)\n    x2 = MaxPooling1D(2)(x2); x2 = Dropout(0.2)(x2)\n    x2 = Conv1D(128, 3, padding='same', use_bias=False, kernel_regularizer=l2(wd))(x2)\n    x2 = BatchNormalization()(x2); x2 = Activation('relu')(x2)\n    x2 = MaxPooling1D(2)(x2); x2 = Dropout(0.2)(x2)\n\n    merged = Concatenate()([x1, x2])\n\n    xa = Bidirectional(LSTM(128, return_sequences=True, kernel_regularizer=l2(wd)))(merged)\n    xb = Bidirectional(GRU(128, return_sequences=True, kernel_regularizer=l2(wd)))(merged)\n    xc = GaussianNoise(0.09)(merged)\n    xc = Dense(16, activation='elu')(xc)\n    \n    x = Concatenate()([xa, xb, xc])\n    x = Dropout(0.4)(x)\n    x = attention_layer(x)\n\n    for units, drop in [(256, 0.5), (128, 0.3)]:\n        x = Dense(units, use_bias=False, kernel_regularizer=l2(wd))(x)\n        x = BatchNormalization()(x); x = Activation('relu')(x)\n        x = Dropout(drop)(x)\n\n    out = Dense(n_classes, activation='softmax', kernel_regularizer=l2(wd))(x)\n    return Model(inp, out)\n\ntmp_model = build_two_branch_model(127,7,325,18)\nprint(\"▶ INFERENCE MODE – loading artefacts from\", PRETRAINED_DIR)\nfinal_feature_cols = np.load(PRETRAINED_DIR / \"feature_cols.npy\", allow_pickle=True).tolist()\npad_len        = int(np.load(PRETRAINED_DIR / \"sequence_maxlen.npy\"))\nscaler         = joblib.load(PRETRAINED_DIR / \"scaler.pkl\")\ngesture_classes = np.load(PRETRAINED_DIR / \"gesture_classes.npy\", allow_pickle=True)\n\n\ncustom_objs = {\n    'time_sum': time_sum, 'squeeze_last_axis': squeeze_last_axis, 'expand_last_axis': expand_last_axis,\n    'se_block': se_block, 'residual_se_cnn_block': residual_se_cnn_block, 'attention_layer': attention_layer,\n}\n\n# ----------------------------------------------------------------- #\n# Load any Models\n# * is 2 Train Model Load\n# ----------------------------------------------------------------- #\n\nmodels1 = []\nprint(f\"  Loading models for ensemble inference...\")\nfor fold in range(10):\n    MODEL_DIR = \"/kaggle/input/cmi-d-111\"\n    \n    model_path = f\"{MODEL_DIR}/D-111_{fold}.h5\"\n    print(\">>>LoadModel>>>\",model_path)\n    model = load_model(model_path, compile=False, custom_objects=custom_objs)\n    models1.append(model)\nprint(\"-\"*50)\n\nfor fold in range(10):\n    MODEL_DIR = \"/kaggle/input/cmi-d-111\"\n    \n    model_path = f\"{MODEL_DIR}/v0629_{fold}.h5\"\n    print(\">>>LoadModel>>>\",model_path)\n    model = load_model(model_path, compile=False, custom_objects=custom_objs)\n    models1.append(model)\nprint(\"-\"*50)\nprint(f\"[INFO]NumUseModels:{len(models1)}\")\n\ndef predict1(sequence: pl.DataFrame, demographics: pl.DataFrame) -> str:\n    df_seq = sequence.to_pandas()\n    linear_accel = remove_gravity_from_acc(df_seq, df_seq)\n    df_seq['linear_acc_x'], df_seq['linear_acc_y'], df_seq['linear_acc_z'] = linear_accel[:, 0], linear_accel[:, 1], linear_accel[:, 2]\n    df_seq['linear_acc_mag'] = np.sqrt(df_seq['linear_acc_x']**2 + df_seq['linear_acc_y']**2 + df_seq['linear_acc_z']**2)\n    df_seq['linear_acc_mag_jerk'] = df_seq['linear_acc_mag'].diff().fillna(0)\n    angular_vel = calculate_angular_velocity_from_quat(df_seq)\n    df_seq['angular_vel_x'], df_seq['angular_vel_y'], df_seq['angular_vel_z'] = angular_vel[:, 0], angular_vel[:, 1], angular_vel[:, 2]\n    df_seq['angular_distance'] = calculate_angular_distance(df_seq)\n    \n    for i in range(1, 6):\n        pixel_cols = [f\"tof_{i}_v{p}\" for p in range(64)]; tof_data = df_seq[pixel_cols].replace(-1, np.nan)\n        df_seq[f'tof_{i}_mean'], df_seq[f'tof_{i}_std'], df_seq[f'tof_{i}_min'], df_seq[f'tof_{i}_max'] = tof_data.mean(axis=1), tof_data.std(axis=1), tof_data.min(axis=1), tof_data.max(axis=1)\n        \n    mat_unscaled = df_seq[final_feature_cols].ffill().bfill().fillna(0).values.astype('float32')\n    mat_scaled = scaler.transform(mat_unscaled)\n    pad_input = pad_sequences([mat_scaled], maxlen=pad_len, padding='post', truncating='post', dtype='float32')\n    \n    all_preds = [model.predict(pad_input, verbose=0)[0] for model in models1] # 主出力のみ取得\n    avg_pred = np.mean(all_preds, axis=0)\n    return avg_pred\n    # return str(gesture_classes[avg_pred.argmax()])\n\n\n\ndef remove_gravity_from_acc(acc_data, rot_data):\n    if isinstance(acc_data, pd.DataFrame):\n        acc_values = acc_data[['acc_x', 'acc_y', 'acc_z']].values\n    else:\n        acc_values = acc_data\n    if isinstance(rot_data, pd.DataFrame):\n        quat_values = rot_data[['rot_x', 'rot_y', 'rot_z', 'rot_w']].values\n    else:\n        quat_values = rot_data\n    num_samples = acc_values.shape[0]\n    linear_accel = np.zeros_like(acc_values)\n    gravity_world = np.array([0, 0, 9.81])\n    for i in range(num_samples):\n        if np.all(np.isnan(quat_values[i])) or np.all(np.isclose(quat_values[i], 0)):\n            linear_accel[i, :] = acc_values[i, :] \n            continue\n        try:\n            rotation = R.from_quat(quat_values[i])\n            gravity_sensor_frame = rotation.apply(gravity_world, inverse=True)\n            linear_accel[i, :] = acc_values[i, :] - gravity_sensor_frame\n        except ValueError:\n             linear_accel[i, :] = acc_values[i, :]\n    return linear_accel\n\ndef calculate_angular_velocity_from_quat(rot_data, time_delta=1/200): # Assuming 200Hz sampling rate\n    if isinstance(rot_data, pd.DataFrame):\n        quat_values = rot_data[['rot_x', 'rot_y', 'rot_z', 'rot_w']].values\n    else:\n        quat_values = rot_data\n    num_samples = quat_values.shape[0]\n    angular_vel = np.zeros((num_samples, 3))\n    for i in range(num_samples - 1):\n        q_t = quat_values[i]\n        q_t_plus_dt = quat_values[i+1]\n        if np.all(np.isnan(q_t)) or np.all(np.isclose(q_t, 0)) or \\\n           np.all(np.isnan(q_t_plus_dt)) or np.all(np.isclose(q_t_plus_dt, 0)):\n            continue\n        try:\n            rot_t = R.from_quat(q_t)\n            rot_t_plus_dt = R.from_quat(q_t_plus_dt)\n            delta_rot = rot_t.inv() * rot_t_plus_dt\n            angular_vel[i, :] = delta_rot.as_rotvec() / time_delta\n        except ValueError:\n            pass\n    return angular_vel\n\ndef calculate_angular_distance(rot_data):\n    if isinstance(rot_data, pd.DataFrame):\n        quat_values = rot_data[['rot_x', 'rot_y', 'rot_z', 'rot_w']].values\n    else:\n        quat_values = rot_data\n    num_samples = quat_values.shape[0]\n    angular_dist = np.zeros(num_samples)\n    for i in range(num_samples - 1):\n        q1 = quat_values[i]\n        q2 = quat_values[i+1]\n        if np.all(np.isnan(q1)) or np.all(np.isclose(q1, 0)) or \\\n           np.all(np.isnan(q2)) or np.all(np.isclose(q2, 0)):\n            angular_dist[i] = 0\n            continue\n        try:\n            r1 = R.from_quat(q1)\n            r2 = R.from_quat(q2)\n            relative_rotation = r1.inv() * r2\n            angle = np.linalg.norm(relative_rotation.as_rotvec())\n            angular_dist[i] = angle\n        except ValueError:\n            angular_dist[i] = 0 # В случае недействительных кватернионов\n            pass\n    return angular_dist\n\n\nclass CMIFeDataset(Dataset):\n    def __init__(self, data_path, config):\n        self.config = config\n        self.init_feature_names(data_path)\n        df = self.generate_features(pd.read_csv(data_path, usecols=set(self.base_cols+self.feature_cols)))\n        self.generate_dataset(df)\n\n    def init_feature_names(self, data_path):\n        self.imu_engineered_features = [\n            'acc_mag', 'rot_angle',\n            'acc_mag_jerk', 'rot_angle_vel',\n            'linear_acc_mag', 'linear_acc_mag_jerk',\n            'angular_vel_x', 'angular_vel_y', 'angular_vel_z',\n            'angular_distance'\n        ]\n\n        self.tof_mode = self.config.get(\"tof_mode\", \"stats\")\n        self.tof_region_stats = ['mean', 'std', 'min', 'max']\n        self.tof_cols = self.generate_tof_feature_names()\n\n        columns = pd.read_csv(data_path, nrows=0).columns.tolist()\n        imu_cols_base = ['linear_acc_x', 'linear_acc_y', 'linear_acc_z']\n        imu_cols_base.extend([c for c in columns if c.startswith('rot_') and c not in ['rot_angle', 'rot_angle_vel']])\n        self.imu_cols = list(dict.fromkeys(imu_cols_base + self.imu_engineered_features))\n        self.thm_cols = [c for c in columns if c.startswith('thm_')]\n        self.feature_cols = self.imu_cols + self.thm_cols + self.tof_cols\n        self.imu_dim = len(self.imu_cols)\n        self.thm_dim = len(self.thm_cols)\n        self.tof_dim = len(self.tof_cols)\n        self.base_cols = ['acc_x', 'acc_y', 'acc_z',\n                          'rot_x', 'rot_y', 'rot_z', 'rot_w',\n                          'sequence_id', 'subject', \n                          'sequence_type', 'gesture', 'orientation'] + [c for c in columns if c.startswith('thm_')] + [f\"tof_{i}_v{p}\" for i in range(1, 6) for p in range(64)]\n        self.fold_cols = ['subject', 'sequence_type', 'gesture', 'orientation']\n\n    def generate_tof_feature_names(self):\n        features = []\n        if self.config.get(\"tof_raw\", False):\n            for i in range(1, 6):\n                features.extend([f\"tof_{i}_v{p}\" for p in range(64)])\n        for i in range(1, 6):\n            if self.tof_mode != 0:\n                for stat in self.tof_region_stats:\n                    features.append(f'tof_{i}_{stat}')\n                if self.tof_mode > 1:\n                    for r in range(self.tof_mode):\n                        for stat in self.tof_region_stats:\n                            features.append(f'tof{self.tof_mode}_{i}_region_{r}_{stat}')\n                if self.tof_mode == -1:\n                    for mode in [2, 4, 8, 16, 32]:\n                        for r in range(mode):\n                            for stat in self.tof_region_stats:\n                                features.append(f'tof{mode}_{i}_region_{r}_{stat}')\n        return features\n\n    def compute_features(self, df):\n        df['acc_mag'] = np.sqrt(df['acc_x']**2 + df['acc_y']**2 + df['acc_z']**2)\n        df['rot_angle'] = 2 * np.arccos(df['rot_w'].clip(-1, 1))\n        df['acc_mag_jerk'] = df.groupby('sequence_id')['acc_mag'].diff().fillna(0)\n        df['rot_angle_vel'] = df.groupby('sequence_id')['rot_angle'].diff().fillna(0)\n            \n        linear_accel_list = []\n        for _, group in df.groupby('sequence_id'):\n            acc_data_group = group[['acc_x', 'acc_y', 'acc_z']]\n            rot_data_group = group[['rot_x', 'rot_y', 'rot_z', 'rot_w']]\n            linear_accel_group = remove_gravity_from_acc(acc_data_group, rot_data_group)\n            linear_accel_list.append(pd.DataFrame(linear_accel_group, columns=['linear_acc_x', 'linear_acc_y', 'linear_acc_z'], index=group.index))\n        df_linear_accel = pd.concat(linear_accel_list)\n        df = pd.concat([df, df_linear_accel], axis=1)\n        df['linear_acc_mag'] = np.sqrt(df['linear_acc_x']**2 + df['linear_acc_y']**2 + df['linear_acc_z']**2)\n        df['linear_acc_mag_jerk'] = df.groupby('sequence_id')['linear_acc_mag'].diff().fillna(0)\n    \n        angular_vel_list = []\n        for _, group in df.groupby('sequence_id'):\n            rot_data_group = group[['rot_x', 'rot_y', 'rot_z', 'rot_w']]\n            angular_vel_group = calculate_angular_velocity_from_quat(rot_data_group)\n            angular_vel_list.append(pd.DataFrame(angular_vel_group, columns=['angular_vel_x', 'angular_vel_y', 'angular_vel_z'], index=group.index))\n        df_angular_vel = pd.concat(angular_vel_list)\n        df = pd.concat([df, df_angular_vel], axis=1)\n    \n        angular_distance_list = []\n        for _, group in df.groupby('sequence_id'):\n            rot_data_group = group[['rot_x', 'rot_y', 'rot_z', 'rot_w']]\n            angular_dist_group = calculate_angular_distance(rot_data_group)\n            angular_distance_list.append(pd.DataFrame(angular_dist_group, columns=['angular_distance'], index=group.index))\n        df_angular_distance = pd.concat(angular_distance_list)\n        df = pd.concat([df, df_angular_distance], axis=1)\n\n        if self.tof_mode != 0:\n            new_columns = {}\n            for i in range(1, 6):\n                pixel_cols = [f\"tof_{i}_v{p}\" for p in range(64)]\n                tof_data = df[pixel_cols].replace(-1, np.nan)\n                new_columns.update({\n                    f'tof_{i}_mean': tof_data.mean(axis=1),\n                    f'tof_{i}_std': tof_data.std(axis=1),\n                    f'tof_{i}_min': tof_data.min(axis=1),\n                    f'tof_{i}_max': tof_data.max(axis=1)\n                })\n                if self.tof_mode > 1:\n                    region_size = 64 // self.tof_mode\n                    for r in range(self.tof_mode):\n                        region_data = tof_data.iloc[:, r*region_size : (r+1)*region_size]\n                        new_columns.update({\n                            f'tof{self.tof_mode}_{i}_region_{r}_mean': region_data.mean(axis=1),\n                            f'tof{self.tof_mode}_{i}_region_{r}_std': region_data.std(axis=1),\n                            f'tof{self.tof_mode}_{i}_region_{r}_min': region_data.min(axis=1),\n                            f'tof{self.tof_mode}_{i}_region_{r}_max': region_data.max(axis=1)\n                        })\n                if self.tof_mode == -1:\n                    for mode in [2, 4, 8, 16, 32]:\n                        region_size = 64 // mode\n                        for r in range(mode):\n                            region_data = tof_data.iloc[:, r*region_size : (r+1)*region_size]\n                            new_columns.update({\n                                f'tof{mode}_{i}_region_{r}_mean': region_data.mean(axis=1),\n                                f'tof{mode}_{i}_region_{r}_std': region_data.std(axis=1),\n                                f'tof{mode}_{i}_region_{r}_min': region_data.min(axis=1),\n                                f'tof{mode}_{i}_region_{r}_max': region_data.max(axis=1)\n                            })\n            df = pd.concat([df, pd.DataFrame(new_columns)], axis=1)\n        return df\n        \n    def generate_features(self, df):\n        self.le = LabelEncoder()\n        df['gesture_int'] = self.le.fit_transform(df['gesture'])\n        self.class_num = len(self.le.classes_)\n        \n        if all(c in df.columns for c in self.imu_engineered_features) and all(c in df.columns for c in self.tof_cols):\n            print(\"Have precomputed, skip compute.\")\n        else:\n            print(\"Not precomputed, do compute.\")\n            df = self.compute_features(df)\n\n        if self.config.get(\"save_precompute\", False):\n            df.to_csv(self.config.get(\"save_filename\", \"train.csv\"))\n        return df\n\n    def scale(self, data_unscaled):\n        scaler_function = self.config.get(\"scaler_function\", StandardScaler())\n        scaler = scaler_function.fit(np.concatenate(data_unscaled, axis=0))\n        return [scaler.transform(x) for x in data_unscaled], scaler\n\n    def pad(self, data_scaled, cols):\n        pad_data = np.zeros((len(data_scaled), self.pad_len, len(cols)), dtype='float32')\n        for i, seq in enumerate(data_scaled):\n            seq_len = min(len(seq), self.pad_len)\n            pad_data[i, :seq_len] = seq[:seq_len]\n        return pad_data\n\n    def get_nan_value(self, data, ratio):\n        max_value = data.max().max()\n        nan_value = -max_value * ratio\n        return nan_value\n\n    def generate_dataset(self, df):\n        seq_gp = df.groupby('sequence_id') \n        imu_unscaled, thm_unscaled, tof_unscaled = [], [], []\n        classes, lens = [], []\n        self.imu_nan_value = self.get_nan_value(df[self.imu_cols], self.config[\"nan_ratio\"][\"imu\"])\n        self.thm_nan_value = self.get_nan_value(df[self.thm_cols], self.config[\"nan_ratio\"][\"thm\"])\n        self.tof_nan_value = self.get_nan_value(df[self.tof_cols], self.config[\"nan_ratio\"][\"tof\"])\n\n        self.fold_feats = defaultdict(list)\n        for seq_id, seq_df in seq_gp:\n            imu_data = seq_df[self.imu_cols]\n            if self.config[\"fbfill\"][\"imu\"]:\n                imu_data = imu_data.ffill().bfill()\n            imu_unscaled.append(imu_data.fillna(self.imu_nan_value).values.astype('float32'))\n\n            thm_data = seq_df[self.thm_cols]\n            if self.config[\"fbfill\"][\"thm\"]:\n                thm_data = thm_data.ffill().bfill()\n            thm_unscaled.append(thm_data.fillna(self.thm_nan_value).values.astype('float32'))\n\n            tof_data = seq_df[self.tof_cols]\n            if self.config[\"fbfill\"][\"tof\"]:\n                tof_data = tof_data.ffill().bfill()\n            tof_unscaled.append(tof_data.fillna(self.tof_nan_value).values.astype('float32'))\n            \n            classes.append(seq_df['gesture_int'].iloc[0])\n            lens.append(len(imu_data))\n\n            for col in self.fold_cols:\n                self.fold_feats[col].append(seq_df[col].iloc[0])\n            \n        self.dataset_indices = classes\n        self.pad_len = int(np.percentile(lens, self.config.get(\"percent\", 95)))\n        if self.config.get(\"one_scale\", True):\n            x_unscaled = [np.concatenate([imu, thm, tof], axis=1) for imu, thm, tof in zip(imu_unscaled, thm_unscaled, tof_unscaled)]\n            x_scaled, self.x_scaler = self.scale(x_unscaled)\n            x = self.pad(x_scaled, self.imu_cols+self.thm_cols+self.tof_cols)\n            self.imu = x[..., :self.imu_dim]\n            self.thm = x[..., self.imu_dim:self.imu_dim+self.thm_dim]\n            self.tof = x[..., self.imu_dim+self.thm_dim:self.imu_dim+self.thm_dim+self.tof_dim]\n        else:\n            imu_scaled, self.imu_scaler = self.scale(imu_unscaled)\n            thm_scaled, self.thm_scaler = self.scale(thm_unscaled)\n            tof_scaled, self.tof_scaler = self.scale(tof_unscaled)\n            self.imu = self.pad(imu_scaled, self.imu_cols)\n            self.thm = self.pad(thm_scaled, self.thm_cols)\n            self.tof = self.pad(tof_scaled, self.tof_cols)\n        self.precompute_scaled_nan_values()\n        self.class_ = F.one_hot(torch.from_numpy(np.array(classes)).long(), num_classes=len(self.le.classes_)).float().numpy()\n        self.class_weight = torch.FloatTensor(compute_class_weight('balanced', classes=np.arange(len(self.le.classes_)), y=classes))\n\n    def precompute_scaled_nan_values(self):\n        dummy_df = pd.DataFrame(\n            np.array([[self.imu_nan_value]*len(self.imu_cols) + \n                     [self.thm_nan_value]*len(self.thm_cols) +\n                     [self.tof_nan_value]*len(self.tof_cols)]),\n            columns=self.imu_cols + self.thm_cols + self.tof_cols\n        )\n        \n        if self.config.get(\"one_scale\", True):\n            scaled = self.x_scaler.transform(dummy_df)\n            self.imu_scaled_nan = scaled[0, :self.imu_dim].mean()\n            self.thm_scaled_nan = scaled[0, self.imu_dim:self.imu_dim+self.thm_dim].mean()\n            self.tof_scaled_nan = scaled[0, self.imu_dim+self.thm_dim:self.imu_dim+self.thm_dim+self.tof_dim].mean()\n        else:\n            self.imu_scaled_nan = self.imu_scaler.transform(dummy_df[self.imu_cols])[0].mean()\n            self.thm_scaled_nan = self.thm_scaler.transform(dummy_df[self.thm_cols])[0].mean()\n            self.tof_scaled_nan = self.tof_scaler.transform(dummy_df[self.tof_cols])[0].mean()\n\n    def get_scaled_nan_tensors(self, imu, thm, tof):\n        return torch.full(imu.shape, self.imu_scaled_nan, device=imu.device), \\\n            torch.full(thm.shape, self.thm_scaled_nan, device=thm.device), \\\n            torch.full(tof.shape, self.tof_scaled_nan, device=tof.device)\n\n    def inference_process(self, sequence):\n        df_seq = sequence.to_pandas().copy()\n        if not all(c in df_seq.columns for c in self.imu_engineered_features):\n            df_seq['acc_mag'] = np.sqrt(df_seq['acc_x']**2 + df_seq['acc_y']**2 + df_seq['acc_z']**2)\n            df_seq['rot_angle'] = 2 * np.arccos(df_seq['rot_w'].clip(-1, 1))\n            df_seq['acc_mag_jerk'] = df_seq['acc_mag'].diff().fillna(0)\n            df_seq['rot_angle_vel'] = df_seq['rot_angle'].diff().fillna(0)\n            if all(col in df_seq.columns for col in ['acc_x', 'acc_y', 'acc_z', 'rot_x', 'rot_y', 'rot_z', 'rot_w']):\n                linear_accel = remove_gravity_from_acc(\n                    df_seq[['acc_x', 'acc_y', 'acc_z']], \n                    df_seq[['rot_x', 'rot_y', 'rot_z', 'rot_w']]\n                )\n                df_seq[['linear_acc_x', 'linear_acc_y', 'linear_acc_z']] = linear_accel\n            else:\n                df_seq['linear_acc_x'] = df_seq.get('acc_x', 0)\n                df_seq['linear_acc_y'] = df_seq.get('acc_y', 0)\n                df_seq['linear_acc_z'] = df_seq.get('acc_z', 0)\n            df_seq['linear_acc_mag'] = np.sqrt(df_seq['linear_acc_x']**2 + df_seq['linear_acc_y']**2 + df_seq['linear_acc_z']**2)\n            df_seq['linear_acc_mag_jerk'] = df_seq['linear_acc_mag'].diff().fillna(0)\n            if all(col in df_seq.columns for col in ['rot_x', 'rot_y', 'rot_z', 'rot_w']):\n                angular_vel = calculate_angular_velocity_from_quat(df_seq[['rot_x', 'rot_y', 'rot_z', 'rot_w']])\n                df_seq[['angular_vel_x', 'angular_vel_y', 'angular_vel_z']] = angular_vel\n            else:\n                df_seq[['angular_vel_x', 'angular_vel_y', 'angular_vel_z']] = 0\n            if all(col in df_seq.columns for col in ['rot_x', 'rot_y', 'rot_z', 'rot_w']):\n                df_seq['angular_distance'] = calculate_angular_distance(df_seq[['rot_x', 'rot_y', 'rot_z', 'rot_w']])\n            else:\n                df_seq['angular_distance'] = 0\n\n        if self.tof_mode != 0:\n            new_columns = {} \n            for i in range(1, 6):\n                pixel_cols = [f\"tof_{i}_v{p}\" for p in range(64)]\n                tof_data = df_seq[pixel_cols].replace(-1, np.nan)\n                new_columns.update({\n                    f'tof_{i}_mean': tof_data.mean(axis=1),\n                    f'tof_{i}_std': tof_data.std(axis=1),\n                    f'tof_{i}_min': tof_data.min(axis=1),\n                    f'tof_{i}_max': tof_data.max(axis=1)\n                })\n                if self.tof_mode > 1:\n                    region_size = 64 // self.tof_mode\n                    for r in range(self.tof_mode):\n                        region_data = tof_data.iloc[:, r*region_size : (r+1)*region_size]\n                        new_columns.update({\n                            f'tof{self.tof_mode}_{i}_region_{r}_mean': region_data.mean(axis=1),\n                            f'tof{self.tof_mode}_{i}_region_{r}_std': region_data.std(axis=1),\n                            f'tof{self.tof_mode}_{i}_region_{r}_min': region_data.min(axis=1),\n                            f'tof{self.tof_mode}_{i}_region_{r}_max': region_data.max(axis=1)\n                        })\n                if self.tof_mode == -1:\n                    for mode in [2, 4, 8, 16, 32]:\n                        region_size = 64 // mode\n                        for r in range(mode):\n                            region_data = tof_data.iloc[:, r*region_size : (r+1)*region_size]\n                            new_columns.update({\n                                f'tof{mode}_{i}_region_{r}_mean': region_data.mean(axis=1),\n                                f'tof{mode}_{i}_region_{r}_std': region_data.std(axis=1),\n                                f'tof{mode}_{i}_region_{r}_min': region_data.min(axis=1),\n                                f'tof{mode}_{i}_region_{r}_max': region_data.max(axis=1)\n                            })\n            df_seq = pd.concat([df_seq, pd.DataFrame(new_columns)], axis=1)\n        \n        imu_unscaled = df_seq[self.imu_cols]\n        if self.config[\"fbfill\"][\"imu\"]:\n            imu_unscaled = imu_unscaled.ffill().bfill()\n        imu_unscaled = imu_unscaled.fillna(self.imu_nan_value).values.astype('float32')\n\n        thm_unscaled = df_seq[self.thm_cols]\n        if self.config[\"fbfill\"][\"thm\"]:\n            thm_unscaled = thm_unscaled.ffill().bfill()\n        thm_unscaled = thm_unscaled.fillna(self.thm_nan_value).values.astype('float32')\n\n        tof_unscaled = df_seq[self.tof_cols]\n        if self.config[\"fbfill\"][\"tof\"]:\n            tof_unscaled = tof_unscaled.ffill().bfill()\n        tof_unscaled = tof_unscaled.fillna(self.tof_nan_value).values.astype('float32')\n        \n        if self.config.get(\"one_scale\", True):\n            x_unscaled = np.concatenate([imu_unscaled, thm_unscaled, tof_unscaled], axis=1)\n            x_scaled = self.x_scaler.transform(x_unscaled)\n            imu_scaled = x_scaled[..., :self.imu_dim]\n            thm_scaled = x_scaled[..., self.imu_dim:self.imu_dim+self.thm_dim]\n            tof_scaled = x_scaled[..., self.imu_dim+self.thm_dim:self.imu_dim+self.thm_dim+self.tof_dim]\n        else:\n            imu_scaled = self.imu_scaler.transform(imu_unscaled)\n            thm_scaled = self.thm_scaler.transform(thm_unscaled)\n            tof_scaled = self.tof_scaler.transform(tof_unscaled)\n\n        combined = np.concatenate([imu_scaled, thm_scaled, tof_scaled], axis=1)\n        padded = np.zeros((self.pad_len, combined.shape[1]), dtype='float32')\n        seq_len = min(combined.shape[0], self.pad_len)\n        padded[:seq_len] = combined[:seq_len]\n        imu = padded[..., :self.imu_dim]\n        thm = padded[..., self.imu_dim:self.imu_dim+self.thm_dim]\n        tof = padded[..., self.imu_dim+self.thm_dim:self.imu_dim+self.thm_dim+self.tof_dim]\n        \n        return torch.from_numpy(imu).float().unsqueeze(0), torch.from_numpy(thm).float().unsqueeze(0), torch.from_numpy(tof).float().unsqueeze(0)\n\n    def __getitem__(self, idx):\n        return self.imu[idx], self.thm[idx], self.tof[idx], self.class_[idx]\n\n    def __len__(self):\n        return len(self.class_)\n\nclass CMIFoldDataset:\n    def __init__(self, data_path, config, full_dataset_function, n_folds=5, random_seed=0):\n        self.full_dataset = full_dataset_function(data_path=data_path, config=config)\n        self.imu_dim = self.full_dataset.imu_dim\n        self.thm_dim = self.full_dataset.thm_dim\n        self.tof_dim = self.full_dataset.tof_dim\n        self.le = self.full_dataset.le\n        self.class_names = self.full_dataset.le.classes_\n        self.class_weight = self.full_dataset.class_weight\n        self.n_folds = n_folds\n        self.skf = StratifiedKFold(n_splits=n_folds, shuffle=True, random_state=random_seed)\n        self.folds = list(self.skf.split(np.arange(len(self.full_dataset)), np.array(self.full_dataset.dataset_indices)))\n    \n    def get_fold_datasets(self, fold_idx):\n        if self.folds is None or fold_idx >= self.n_folds:\n            return None, None\n        fold_train_idx, fold_valid_idx = self.folds[fold_idx]\n        return Subset(self.full_dataset, fold_train_idx), Subset(self.full_dataset, fold_valid_idx)\n\n    def print_fold_stats(self):\n        def get_label_counts(subset):\n            counts = {name: 0 for name in self.class_names}\n            if subset is None:\n                return counts\n            for idx in subset.indices:\n                label_idx = self.full_dataset.dataset_indices[idx]\n                counts[self.class_names[label_idx]] += 1\n            return counts\n        \n        print(\"\\n交叉验证折叠统计:\")\n        for fold_idx in range(self.n_folds):\n            train_fold, valid_fold = self.get_fold_datasets(fold_idx)\n            train_counts = get_label_counts(train_fold)\n            valid_counts = get_label_counts(valid_fold)\n                \n            print(f\"\\nFold {fold_idx + 1}:\")\n            print(f\"{'类别':<50} {'训练集':<10} {'验证集':<10}\")\n            for name in self.class_names:\n                print(f\"{name:<50} {train_counts[name]:<10} {valid_counts[name]:<10}\")\n\n\nclass SEBlock(nn.Module):\n    def __init__(self, channels, reduction = 8):\n        super().__init__()\n        self.fc1 = nn.Linear(channels, channels // reduction, bias=True)\n        self.fc2 = nn.Linear(channels // reduction, channels, bias=True)\n        self.sigmoid = nn.Sigmoid()\n\n    def forward(self, x):\n        # x: (B, C, L)\n        se = F.adaptive_avg_pool1d(x, 1).squeeze(-1)      # -> (B, C)\n        se = F.relu(self.fc1(se), inplace=True)          # -> (B, C//r)\n        se = self.sigmoid(self.fc2(se)).unsqueeze(-1)    # -> (B, C, 1)\n        return x * se                \n\nclass ResNetSEBlock(nn.Module):\n    def __init__(self, in_channels, out_channels, wd = 1e-4):\n        super().__init__()\n        self.conv1 = nn.Conv1d(in_channels, out_channels,\n                               kernel_size=3, padding=1, bias=False)\n        self.bn1 = nn.BatchNorm1d(out_channels)\n        self.conv2 = nn.Conv1d(out_channels, out_channels,\n                               kernel_size=3, padding=1, bias=False)\n        self.bn2 = nn.BatchNorm1d(out_channels)\n        # SE\n        self.se = SEBlock(out_channels)\n        \n        if in_channels != out_channels:\n            self.shortcut = nn.Sequential(\n                nn.Conv1d(in_channels, out_channels, kernel_size=1,\n                          padding=0, bias=False),\n                nn.BatchNorm1d(out_channels)\n            )\n        else:\n            self.shortcut = nn.Identity()\n\n        self.relu = nn.ReLU(inplace=True)\n\n    def forward(self, x) :\n        identity = self.shortcut(x)              # (B, out, L)\n        out = self.relu(self.bn1(self.conv1(x)))\n        out = self.bn2(self.conv2(out))\n        out = self.se(out)                       # (B, out, L)\n        out = out + identity\n        return self.relu(out)\n\nclass CMIModel(nn.Module):\n    def __init__(self, imu_dim, thm_dim, tof_dim, n_classes, **kwargs):\n        super().__init__()\n        self.imu_branch = nn.Sequential(\n            self.residual_se_cnn_block(imu_dim, kwargs[\"imu1_channels\"], kwargs[\"imu1_layers\"],\n                                       drop=kwargs[\"imu1_dropout\"]),\n            self.residual_se_cnn_block(kwargs[\"imu1_channels\"], kwargs[\"feat_dim\"], kwargs[\"imu2_layers\"],\n                                       drop=kwargs[\"imu2_dropout\"])\n        )\n\n        self.thm_branch = nn.Sequential(\n            nn.Conv1d(thm_dim, kwargs[\"thm1_channels\"], kernel_size=3, padding=1, bias=False),\n            nn.BatchNorm1d(kwargs[\"thm1_channels\"]),\n            nn.ReLU(inplace=True),\n            nn.MaxPool1d(2, ceil_mode=True),\n            nn.Dropout(kwargs[\"thm1_dropout\"]),\n            \n            nn.Conv1d(kwargs[\"thm1_channels\"], kwargs[\"feat_dim\"], kernel_size=3, padding=1, bias=False),\n            nn.BatchNorm1d(kwargs[\"feat_dim\"]),\n            nn.ReLU(inplace=True),\n            nn.MaxPool1d(2, ceil_mode=True),\n            nn.Dropout(kwargs[\"thm2_dropout\"])\n        )\n        \n        self.tof_branch = nn.Sequential(\n            nn.Conv1d(tof_dim, kwargs[\"tof1_channels\"], kernel_size=3, padding=1, bias=False),\n            nn.BatchNorm1d(kwargs[\"tof1_channels\"]),\n            nn.ReLU(inplace=True),\n            nn.MaxPool1d(2, ceil_mode=True),\n            nn.Dropout(kwargs[\"tof1_dropout\"]),\n            \n            nn.Conv1d(kwargs[\"tof1_channels\"], kwargs[\"feat_dim\"], kernel_size=3, padding=1, bias=False),\n            nn.BatchNorm1d(kwargs[\"feat_dim\"]),\n            nn.ReLU(inplace=True),\n            nn.MaxPool1d(2, ceil_mode=True),\n            nn.Dropout(kwargs[\"tof2_dropout\"])\n        )\n\n        self.cls_token = nn.Parameter(torch.zeros(1, 1, kwargs[\"feat_dim\"]))\n        self.bert = BertModel(BertConfig(\n            hidden_size=kwargs[\"feat_dim\"],\n            num_hidden_layers=kwargs[\"bert_layers\"],\n            num_attention_heads=kwargs[\"bert_heads\"],\n            intermediate_size=kwargs[\"feat_dim\"]*4\n        ))\n        \n        self.classifier = nn.Sequential(\n            nn.Linear(kwargs[\"feat_dim\"], kwargs[\"cls1_channels\"], bias=False),\n            nn.BatchNorm1d(kwargs[\"cls1_channels\"]),\n            nn.ReLU(inplace=True),\n            nn.Dropout(kwargs[\"cls1_dropout\"]),\n            nn.Linear(kwargs[\"cls1_channels\"], kwargs[\"cls2_channels\"], bias=False),\n            nn.BatchNorm1d(kwargs[\"cls2_channels\"]),\n            nn.ReLU(inplace=True),\n            nn.Dropout(kwargs[\"cls2_dropout\"]),\n            nn.Linear(kwargs[\"cls2_channels\"], n_classes)\n        )\n    \n    def residual_se_cnn_block(self, in_channels, out_channels, num_layers, pool_size=2, drop=0.3, wd=1e-4):\n        return nn.Sequential(\n            *[ResNetSEBlock(in_channels=in_channels, out_channels=in_channels) for i in range(num_layers)],\n            ResNetSEBlock(in_channels, out_channels, wd=wd),\n            nn.MaxPool1d(pool_size),\n            nn.Dropout(drop)\n        )\n    \n    def forward(self, imu, thm, tof):\n        imu_feat = self.imu_branch(imu.permute(0, 2, 1))\n        thm_feat = self.thm_branch(thm.permute(0, 2, 1))\n        tof_feat = self.tof_branch(tof.permute(0, 2, 1))\n        \n        bert_input = torch.cat([imu_feat, thm_feat, tof_feat], dim=-1).permute(0, 2, 1)\n        cls_token = self.cls_token.expand(bert_input.size(0), -1, -1)  # (B,1,H)\n        bert_input = torch.cat([cls_token, bert_input], dim=1)  # (B,T+1,H)\n        outputs = self.bert(inputs_embeds=bert_input)\n        pred_cls = outputs.last_hidden_state[:, 0, :]\n\n        return self.classifier(pred_cls)\n\n\nCUDA0 = \"cuda:0\"\nseed = 0\nbatch_size = 64\nnum_workers = 4\nn_folds = 5\n\nuniverse_csv_path = Path(\"/kaggle/input/cmi-precompute/pytorch/all/1/tof-1_raw.csv\")\n\ndeterministic = kagglehub.package_import('wasupandceacar/deterministic').deterministic\ndeterministic.init_all(seed)\ndef init_dataset():\n    dataset_config = {\n        \"percent\": 95,\n        \"scaler_function\": StandardScaler(),\n        \"nan_ratio\": {\n            \"imu\": 0,\n            \"thm\": 0,\n            \"tof\": 0,\n        },\n        \"fbfill\": {\n            \"imu\": True,\n            \"thm\": True,\n            \"tof\": True,\n        },\n        \"one_scale\": True,\n        \"tof_raw\": True,\n        \"tof_mode\": 16,\n        \"save_precompute\": False,\n    }\n    dataset = CMIFoldDataset(universe_csv_path, dataset_config,\n                             n_folds=n_folds, random_seed=seed, full_dataset_function=CMIFeDataset)\n    dataset.print_fold_stats()\n    return dataset\n\ndef get_fold_dataset(dataset, fold):\n    _, valid_dataset = dataset.get_fold_datasets(fold)\n    valid_loader = DataLoader(valid_dataset, batch_size=batch_size, num_workers=num_workers, shuffle=False)\n    return valid_loader\n\ndataset = init_dataset()\n\nmodel_function = CMIModel\nmodel_args = {\"feat_dim\": 500,\n              \"imu1_channels\": 219, \"imu1_dropout\": 0.2946731587132302, \"imu2_dropout\": 0.2697745571929592,\n              \"imu1_weight_decay\": 0.0014824054650601245, \"imu2_weight_decay\": 0.002742543773142381,\n              \"imu1_layers\": 0, \"imu2_layers\": 0,\n              \"thm1_channels\": 82, \"thm1_dropout\": 0.2641274454844602, \"thm2_dropout\": 0.302896343020985, \n              \"tof1_channels\": 82, \"tof1_dropout\": 0.2641274454844602, \"tof2_dropout\": 0.3028963430209852, \n              \"bert_layers\": 8, \"bert_heads\": 10,\n              \"cls1_channels\": 937, \"cls2_channels\": 303, \"cls1_dropout\": 0.2281834512100508, \"cls2_dropout\": 0.22502521933558461}\nmodel_args.update({\n    \"imu_dim\": dataset.full_dataset.imu_dim, \n    \"thm_dim\": dataset.full_dataset.thm_dim,\n    \"tof_dim\": dataset.full_dataset.tof_dim,\n    \"n_classes\": dataset.full_dataset.class_num})\nmodel_dir = Path(\"/kaggle/input/cmi-models-public/pytorch/train_fold_model05_tof16_raw/1\")\n\nmodel_dicts = [\n    {\n        \"model_function\": model_function,\n        \"model_args\": model_args,\n        \"model_path\": model_dir / f\"fold{fold}/best_ema.pt\",\n    } for fold in range(n_folds)\n]\n\nmodels2 = list()\nfor model_dict in model_dicts:\n    model_function = model_dict[\"model_function\"]\n    model_args = model_dict[\"model_args\"]\n    model_path = model_dict[\"model_path\"]\n    model = model_function(**model_args).to(CUDA0)\n    state_dict = {k.replace(\"_orig_mod.\", \"\"): v for k, v in torch.load(model_path).items()}\n    model.load_state_dict(state_dict)\n    model = model.eval()\n    models2.append(model)\n\n\nmetric_package = kagglehub.package_import('wasupandceacar/cmi-metric')\n\nmetric = metric_package.Metric()\nimu_only_metric = metric_package.Metric()\n\ndef to_cuda(*tensors):\n    return [tensor.to(CUDA0) for tensor in tensors]\n\ndef predict_valid(model, imu, thm, tof):\n    pred = model(imu, thm, tof)\n    return pred\n\ndef valid(model, valid_bar):\n    with torch.no_grad():\n        for imu, thm, tof, y in valid_bar:\n            imu, thm, tof, y = to_cuda(imu, thm, tof, y)\n            with autocast(device_type='cuda', dtype=torch.bfloat16): \n                logits = predict_valid(model, imu, thm, tof)\n            metric.add(dataset.le.classes_[y.argmax(dim=1).cpu()], dataset.le.classes_[logits.argmax(dim=1).cpu()])\n            _, thm, tof = dataset.full_dataset.get_scaled_nan_tensors(imu, thm, tof)\n            with autocast(device_type='cuda', dtype=torch.bfloat16): \n                logits = model(imu, thm, tof)\n            imu_only_metric.add(dataset.le.classes_[y.argmax(dim=1).cpu()], dataset.le.classes_[logits.argmax(dim=1).cpu()])\n\n# for fold, model in enumerate(models2):\n#     valid_loader = get_fold_dataset(dataset, fold)\n#     valid_bar = tqdm(valid_loader, desc=f\"Valid\", position=0, leave=False)\n#     valid(model, valid_bar)\n\n# print(f\"\"\"\n# Normal score: {metric.score()}\n# IMU only score: {imu_only_metric.score()}\n# \"\"\")\n\ndef avg_predict(models, imu, thm, tof):\n    outputs = []\n    with autocast(device_type='cuda'):\n        for model in models:\n            logits = model(imu, thm, tof)\n        outputs.append(logits)\n    return torch.mean(torch.stack(outputs), dim=0)\n\ndef predict2(sequence: pl.DataFrame, demographics: pl.DataFrame) -> str:\n    imu, thm, tof = dataset.full_dataset.inference_process(sequence)\n    with torch.no_grad():\n        imu, thm, tof = to_cuda(imu, thm, tof)\n        logits = avg_predict(models2, imu, thm, tof)\n        probabilities = F.softmax(logits, dim=1).cpu().numpy()\n    return probabilities # logits.cpu().numpy()\n    # return dataset.le.classes_[logits.argmax(dim=1).cpu()]\n\ndef predict(sequence, demographics):\n    pred1 = predict1(sequence, demographics)\n    pred2 = predict2(sequence, demographics)\n    \n    preds = []\n    \n    for _1,_2 in zip(pred1,pred2):\n        pred = []\n        for p1,p2 in zip(_1,_2):\n            if p1 < p2:\n                pred.append(p1*0.60 + p2*0.40)\n            elif p1 > p2:\n                pred.append(p1*0.60 + p2*0.40)\n            else: # p1==p2\n                pred.append(p1*0.58 + p2*0.42)\n        preds.append(pred)\n                \n    avg_pred = np.array(preds)\n    \n    return dataset.le.classes_[avg_pred.argmax()]\n\n\n# option.3 -------original data from copy-------- LB = ?\n\ndef predict(sequence, demographics):\n    pred1 = predict1(sequence, demographics)\n    pred2 = predict2(sequence, demographics)\n    \n    preds = []\n    \n    for _1,_2 in zip(pred1,pred2):\n        pred = []\n        for p1,p2 in zip(_1,_2):\n            if p1 < p2:\n                pred.append(p1*0.60 + p2*0.40)\n            elif p1 > p2:\n                pred.append(p1*0.60 + p2*0.40)\n            else: # p1==p2\n                pred.append(p1*0.62 + p2*0.38)\n        preds.append(pred)\n                \n    avg_pred = np.array(preds)\n    \n    return dataset.le.classes_[avg_pred.argmax()]\n\nimport warnings\nwarnings.simplefilter(\"ignore\")\n\nimport kaggle_evaluation.cmi_inference_server\ninference_server = kaggle_evaluation.cmi_inference_server.CMIInferenceServer(predict)\n\nif os.getenv('KAGGLE_IS_COMPETITION_RERUN'):\n    inference_server.serve()\nelse:\n    inference_server.run_local_gateway(\n        data_paths=(\n            '/kaggle/input/cmi-detect-behavior-with-sensor-data/test.csv',\n            '/kaggle/input/cmi-detect-behavior-with-sensor-data/test_demographics.csv',\n        )\n    )\n\nif not os.getenv('KAGGLE_IS_COMPETITION_RERUN'):\n    print(pd.read_parquet(\"submission.parquet\"))","metadata":{"_uuid":"ce7454ad-b4eb-4fac-9b37-9c3e580dd6cd","_cell_guid":"e28baf78-1483-43c8-99c6-79fa005c6ee0","trusted":true,"collapsed":false,"execution":{"iopub.status.busy":"2025-07-29T06:40:56.455252Z","iopub.execute_input":"2025-07-29T06:40:56.455940Z","iopub.status.idle":"2025-07-29T06:44:35.662441Z","shell.execute_reply.started":"2025-07-29T06:40:56.455913Z","shell.execute_reply":"2025-07-29T06:44:35.661643Z"},"jupyter":{"outputs_hidden":false}},"outputs":[],"execution_count":null}]}