{"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":"gpu","dataSources":[{"sourceId":102335,"databundleVersionId":12518947,"isSourceIdPinned":false,"sourceType":"competition"},{"sourceId":556928,"sourceType":"modelInstanceVersion","isSourceIdPinned":false,"modelInstanceId":423519,"modelId":441038},{"sourceId":470587,"sourceType":"modelInstanceVersion","isSourceIdPinned":false,"modelInstanceId":379625,"modelId":398856}],"dockerImageVersionId":31090,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import os\nimport torch\nfrom pathlib import Path\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\nimport numpy as np\nimport torch.nn as nn\nimport torch.nn.functional as F\nimport torch.optim as optim\nfrom torch import fft\nfrom scipy.spatial.transform import Rotation as R\nfrom sklearn.preprocessing import StandardScaler, MinMaxScaler\nfrom collections import defaultdict\nfrom sklearn.utils.class_weight import compute_class_weight\nfrom sklearn.preprocessing import StandardScaler, LabelEncoder\nfrom sklearn.model_selection import StratifiedGroupKFold\nfrom sklearn.metrics import f1_score\nimport random\nimport math\nfrom multiprocessing import freeze_support\n#freeze_support() # for num_workers>0, but still not working on my machine\n\n\nTRAIN = False #True #\n\nroot_dir = Path(\"/kaggle/input/cmi-detect-behavior-with-sensor-data\")\nuniverse_csv_path = Path(\"/kaggle/input/cmi-precompute/pytorch/all/1/tof-1_raw.csv\")\nmodel_dir = Path(\"/kaggle/input/cmi-fold5-tf/pytorch/default/1\")\n\nseed = 0\nbatch_size = 64\nnum_workers = 0 #4\nn_folds = 5\nCUDA0 = \"cuda:0\"\n\n\nmodel_args = {\"imu1_channels\": 128, \"imu2_channels\": 256, \"imu1_dropout\": 0.3, \"imu2_dropout\": 0.25,\n              \"imu1_layers\": 0, \"imu2_layers\": 0,\n              \"thm1_channels\": 32, \"thm2_channels\": 64, \"thm1_dropout\": 0.25, \"thm2_dropout\": 0.2,\n              \"thm1_layers\": 0, \"thm2_layers\": 0,\n              \"tof1_channels\": 256, \"tof2_channels\": 512, \"tof1_dropout\": 0.4, \"tof2_dropout\": 0.3,\n              \"tof1_layers\": 0, \"tof2_layers\": 0,\n              \"lstm_hidden_size\": 128, \"gru_hidden_size\": 128, \"gaussian_noise_rate\": 0.1, \"dense_channels\": 32,\n              \"cls_channels1\": 256, \"cls_dropout1\": 0.2, \"cls_channels2\": 128, \"cls_dropout2\": 0.2,\n              \"target_classes_num\": 8, \"non_target_classes_num\": 10, }\n\n\n\nimu_only = False\n\n\ndef fix_seed(seed=0):\n    random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    os.environ['CUBLAS_WORKSPACE_CONFIG'] = ':4096:8'\n    # NumPy\n    np.random.seed(seed)\n    # PyTorch\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed(seed)\n    torch.cuda.manual_seed_all(seed)  # # when using multiple GPUs\n    # CUDA deterministic mode (may reduce speed)\n    torch.backends.cudnn.deterministic = True\n    torch.backends.cudnn.benchmark = False\n    # Disable GPU atomic operation randomness (PyTorch 2.0+)\n    torch.use_deterministic_algorithms(True, warn_only=True)\n    try:\n        import cv2\n        from transformers import set_seed\n        set_seed(seed)  # override internal randomness\n        cv2.setRNGSeed(seed)\n        print(\"case 2\")\n    except:\n        print(\"case 1\")\n\n\nfix_seed(seed)\n\n\ndef init_dataset():\n    dataset_config = {\n        \"percent\": 99,\n        \"scaler_config\": 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\": False,\n        \"tof_raw\": True,\n        \"tof_mode\": 16,\n        \"save_precompute\": False,\n        \"fold_y\": \"gesture\",\n        \"fold_groups\": \"subject\",\n    }\n\n    dataset = CMIFoldDataset(universe_csv_path, dataset_config, full_dataset_function=CMIFeDataset, n_folds=n_folds, random_seed=seed)\n    dataset.print_fold_stats()\n    return dataset\n\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\n\n#dataset = init_dataset()\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\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\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.use_cols) & set(self.raw_columns)))\n        self.generate_dataset(df)\n\n    def init_feature_names(self, data_path):\n        self.target_gestures = [\n            'Above ear - pull hair',\n            'Cheek - pinch skin',\n            'Eyebrow - pull hair',\n            'Eyelash - pull hair',\n            'Forehead - pull hairline',\n            'Forehead - scratch',\n            'Neck - pinch skin',\n            'Neck - scratch',\n        ]\n        self.non_target_gestures = [\n            'Write name on leg',\n            'Wave hello',\n            'Glasses on/off',\n            'Text on phone',\n            'Write name in air',\n            'Feel around in tray and pull out an object',\n            'Scratch knee/leg skin',\n            'Pull air toward your face',\n            'Drink from bottle/cup',\n            'Pinch knee/leg skin'\n        ]\n\n        self.acc_features = ['acc_mag', 'acc_mag_jerk', 'linear_acc_mag', 'linear_acc_mag_jerk']\n        self.rot_features = ['rot_angle', 'rot_angle_vel', 'angular_vel_x', 'angular_vel_y', 'angular_vel_z',\n                             'angular_distance']\n        self.old_imu_features = [\n            'acc_mag', 'rot_angle', 'acc_mag_jerk', 'rot_angle_vel',\n            'linear_acc_mag', 'linear_acc_mag_jerk',\n            'angular_vel_x', 'angular_vel_y', 'angular_vel_z', 'angular_distance'\n        ]\n\n        self.extra_imu_features = self.config.get(\"imu_feats\", [])\n        self.imu_features = self.extra_imu_features.copy()\n        if self.config.get(\"add_imu_feat_default\", True):\n            if self.config.get(\"old_imu_feat\", True):\n                self.imu_features.extend(self.old_imu_features)\n            else:\n                self.imu_features.extend(self.acc_features)\n                self.imu_features.extend(self.rot_features)\n        self.er1_fearues = [\"er_x\", \"er_y\", \"er_z\"]\n        self.er2_fearues = ['er_r_xy', 'er_r_xz', 'er_r_yz', 'er_c_xy', 'er_c_xz', 'er_c_yz']\n        self.er_fearues = self.er1_fearues + self.er2_fearues\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        self.raw_columns = pd.read_csv(data_path, nrows=0).columns.tolist()\n        self.imu_acc_cols_base = ['acc_x', 'acc_y', 'acc_z', 'linear_acc_x', 'linear_acc_y',\n                                  'linear_acc_z'] if self.config.get(\"add_raw_acc\", False) else ['linear_acc_x',\n                                                                                                 'linear_acc_y',\n                                                                                                 'linear_acc_z']\n        self.imu_rot_cols_base = ['rot_w', 'rot_x', 'rot_y', 'rot_z']\n        self.imu_cols_base = self.imu_acc_cols_base + self.imu_rot_cols_base\n        self.imu_cols = list()\n        self.imu_channel_keys = defaultdict(list)\n        if self.config.get(\"add_imu_base\", True):\n            self.imu_cols.extend(self.imu_cols_base)\n            self.imu_channel_keys[\"acc\"] = self.imu_acc_cols_base\n            self.imu_channel_keys[\"rot\"] = self.imu_rot_cols_base\n        if self.config.get(\"add_imu_feats\", True):\n            self.imu_cols.extend(self.imu_features)\n            if self.config.get(\"split_imu_feat\", False):\n                if self.config.get(\"old_imu_feat\", True):\n                    assert False, \"split_imu_feat=True and old_imu_feat=True not supported\"\n                self.imu_channel_keys[\"acc_feat\"] = self.acc_features\n                self.imu_channel_keys[\"rot_feat\"] = self.rot_features\n            else:\n                if self.config.get(\"old_imu_feat\", True):\n                    self.imu_channel_keys[\"other\"].extend(self.old_imu_features)\n                else:\n                    self.imu_channel_keys[\"other\"].extend(self.acc_features)\n                    self.imu_channel_keys[\"other\"].extend(self.rot_features)\n        if self.config.get(\"add_imu_er_feats\", False):\n            self.imu_cols.extend(self.er_fearues)\n            if self.config.get(\"split_imu_feat\", False):\n                self.imu_channel_keys[\"er1_feat\"] = self.er1_fearues\n                self.imu_channel_keys[\"er2_feat\"] = self.er2_fearues\n            else:\n                self.imu_channel_keys[\"other\"].extend(self.er1_fearues)\n                self.imu_channel_keys[\"other\"].extend(self.er2_fearues)\n        self.flip_imu_cols = [f\"{col}_flip\" for col in self.imu_cols]\n        self.imu_channel_keys = {k: sorted(v) for k, v in self.imu_channel_keys.items()}\n        self.thm_cols = [c for c in self.raw_columns if c.startswith('thm_')]\n        self.thm_channel_keys = {k: [f\"thm_{k}\"] for k in range(1, 6)}\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']\n                          + [c for c in self.raw_columns if c.startswith('thm_')]\n                          + [f\"tof_{i}_v{p}\" for i in range(1, 6) for p in range(64)])\n        self.use_cols = self.base_cols + self.feature_cols\n        if self.config.get(\"return_flip_imu\", False):\n            self.use_cols.extend(self.flip_imu_cols)\n        self.fold_cols = ['subject', 'sequence_type', 'gesture', 'orientation', 'sequence_id']\n        if self.config.get(\"use_dg\", False):\n            self.dg_cols = ['adult_child', 'age', 'sex', 'handedness', 'shoulder_to_wrist_height', 'elbow_to_wrist_height']\n        self.global_imu_indices = {k: sorted([self.imu_cols.index(feat) for feat in feats]) for k, feats in self.imu_channel_keys.items()}\n        self.global_thm_indices = {k: sorted([self.thm_cols.index(key) for key in self.thm_channel_keys[k]]) for k in range(1, 6)}\n        self.global_tof_indices = {k: sorted([self.tof_cols.index(key) for key in self.tof_channel_keys[k]]) for k in range(1, 6)}\n\n    def generate_tof_feature_names(self):\n        features = list()\n        self.tof_channel_keys = defaultdict(list)\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                self.tof_channel_keys[i].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                    self.tof_channel_keys[i].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                            self.tof_channel_keys[i].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                                self.tof_channel_keys[i].append(f'tof{mode}_{i}_region_{r}_{stat}')\n        return features\n\n    def compute_cross_axis_energy(self, df):\n        axes = ['x', 'y', 'z']\n        features = {}\n        for axis in axes:\n            fft_result = fft(df[f'acc_{axis}'].values)\n            energy = np.sum(np.abs(fft_result) ** 2)\n            features[f\"er_{axis}\"] = energy\n        for i, axis1 in enumerate(axes):\n            for axis2 in axes[i + 1:]:\n                features[f'er_r_{axis1}{axis2}'] = features[f'er_{axis1}'] / (features[f'er_{axis2}'] + 1e-6)\n        for i, axis1 in enumerate(axes):\n            for axis2 in axes[i + 1:]:\n                features[f'er_c_{axis1}{axis2}'] = \\\n                    np.corrcoef(np.abs(fft(df[f'acc_{axis1}'].values)), np.abs(fft(df[f'acc_{axis2}'].values)))[0, 1]\n        return {k: v for k, v in features.items() if k in self.er_fearues}\n\n    def compute_imu_features(self, df):\n        if self.config.get(\"rot_fillna\", False):\n            df['rot_w'] = df['rot_w'].fillna(1)\n            df[['rot_x', 'rot_y', 'rot_z']] = df[['rot_x', 'rot_y', 'rot_z']].fillna(0)\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(\n                pd.DataFrame(linear_accel_group, columns=['linear_acc_x', 'linear_acc_y', 'linear_acc_z'],\n                             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(\n                pd.DataFrame(angular_vel_group, columns=['angular_vel_x', 'angular_vel_y', 'angular_vel_z'],\n                             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(\n                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        return df\n\n    def compute_flip_features(self, df):\n        flip_df = df[['sequence_id', 'acc_x', 'acc_y', 'acc_z', 'rot_x', 'rot_y', 'rot_z', 'rot_w']].copy()\n        flip_df[['acc_x', 'acc_y', 'rot_x', 'rot_y']] *= -1\n        flip_df = self.compute_imu_features(flip_df)\n        for col in flip_df.columns:\n            if col != 'sequence_id':\n                df[f\"{col}_flip\"] = flip_df[col]\n        return df\n\n    def compute_features(self, df):\n        df = self.compute_imu_features(df)\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\n        def _calc_features(group):\n            return pd.DataFrame(self.compute_cross_axis_energy(group), index=[group.index[0]])\n\n        features_df = df.groupby('sequence_id', group_keys=False).apply(_calc_features)\n        df = df.join(features_df, how='left')\n        df[features_df.columns] = df.groupby('sequence_id')[features_df.columns].ffill()\n\n        return df\n\n    def generate_features(self, df):\n        self.le = LabelEncoder()\n        if self.config.get(\"one_neg\", False):\n            neg_other = \"Write name on leg\"\n            df['gesture'] = df['gesture'].apply(lambda x: x if x in self.target_gestures else neg_other)\n        df['gesture_int'] = self.le.fit_transform(df['gesture'])\n        self.class_num = len(self.le.classes_)\n        self.target_ints = np.array([self.le.classes_.tolist().index(name) for name in self.target_gestures])\n        self.non_target_ints = np.array([self.le.classes_.tolist().index(name) for name in self.non_target_gestures])\n\n        if all(c in df.columns for c in self.feature_cols):\n            print(\"Features have precomputed, skip compute.\")\n        else:\n            print(\"Features not precomputed, do compute.\")\n            df = self.compute_features(df)\n\n        if self.config.get(\"return_flip_imu\", False):\n            if all(c in df.columns for c in self.flip_imu_cols):\n                print(\"Flip have precomputed, skip compute.\")\n            else:\n                print(\"Flip not precomputed, do compute.\")\n                df = self.compute_flip_features(df)\n\n        if self.config.get(\"use_dg\", False):\n            dg_df = pd.read_csv(self.config[\"dg_path\"])\n            df = pd.merge(df, dg_df, how='left', on='subject')\n            df['age'] /= 100\n            df['shoulder_to_wrist_height'] = df['shoulder_to_wrist_cm'] / df['height_cm']\n            df['elbow_to_wrist_height'] = df['elbow_to_wrist_cm'] / df['height_cm']\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        print(f\"Max: {max_value}, set nan to {nan_value}\")\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 = list(), list(), list()\n        if self.config.get(\"return_flip_imu\", False): flip_imu_unscaled = list()\n        classes, lens = list(), list()\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        if self.config.get(\"use_dg\", False):\n            self.dg = list()\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            if self.config.get(\"return_flip_imu\", False):\n                flip_imu_data = seq_df[self.flip_imu_cols]\n                if self.config[\"fbfill\"][\"imu\"]:\n                    flip_imu_data = flip_imu_data.ffill().bfill()\n                flip_imu_unscaled.append(flip_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            if self.config.get(\"use_dg\", False):\n                self.dg.append(seq_df[self.dg_cols].iloc[0].values.astype('float32'))\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\n                          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\n            if self.config.get(\"return_flip_imu\", False):\n                flip_x_unscaled = [np.concatenate([flip_imu, thm, tof], axis=1) for flip_imu, thm, tof in\n                                   zip(flip_imu_unscaled, thm_unscaled, tof_unscaled)]\n                flip_x_scaled = [self.x_scaler.transform(x) for x in flip_x_unscaled]\n                flip_x = self.pad(flip_x_scaled, self.imu_cols + self.thm_cols + self.tof_cols)\n                self.flip_imu = flip_x[..., :self.imu_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\n            if self.config.get(\"return_flip_imu\", False):\n                flip_imu_scaled = [self.imu_scaler.transform(x) for x in flip_imu_unscaled]\n                self.flip_imu = self.pad(flip_imu_scaled, self.imu_cols)\n        self.precompute_scaled_nan_values()\n        self.class_ = F.one_hot(torch.from_numpy(np.array(classes)).long(),\n                                num_classes=len(self.le.classes_)).float().numpy()\n        self.binary_class_ = np.isin(np.array(classes), self.target_ints).astype(np.float32)\n        self.class_weight = torch.FloatTensor(\n            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, demographics=None, reverse=False):\n        if self.config.get(\"use_dg\", False):\n            assert demographics is not None, \"Demographics needed\"\n            df_dg = demographics.to_pandas().copy()\n            df_dg['age'] /= 100\n            df_dg['shoulder_to_wrist_height'] = df_dg['shoulder_to_wrist_cm'] / df_dg['height_cm']\n            df_dg['elbow_to_wrist_height'] = df_dg['elbow_to_wrist_cm'] / df_dg['height_cm']\n        df_seq = sequence.to_pandas().copy()\n        if reverse:\n            df_seq[['acc_x', 'acc_y', 'rot_x', 'rot_y']] *= -1\n        if self.config.get(\"rot_fillna\", False):\n            df_seq['rot_w'] = df_seq['rot_w'].fillna(1)\n            df_seq[['rot_x', 'rot_y', 'rot_z']] = df_seq[['rot_x', 'rot_y', 'rot_z']].fillna(0)\n        if not all(c in df_seq.columns for c in self.imu_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(\n                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        ret = [torch.from_numpy(imu).float().unsqueeze(0), torch.from_numpy(thm).float().unsqueeze(0),\n               torch.from_numpy(tof).float().unsqueeze(0)]\n        if self.config.get(\"use_dg\", False):\n            dg = df_dg[self.dg_cols].values.astype('float32')\n            ret.append(torch.from_numpy(dg).float())\n        return ret\n\n    def split5(self, imu, thm, tof):\n        imus = [imu[:, :, self.global_imu_indices[k]] for k in self.global_imu_indices]\n        thms = [thm[:, :, self.global_thm_indices[k]] for k in range(1, 6)]\n        tofs = [tof[:, :, self.global_tof_indices[k]] for k in range(1, 6)]\n        return imus, thms, tofs\n\n    def slide(self, imu, thm, tof, ratio=1.0):\n        def slide_tensor(tensor, nan_value, ratio):\n            b, l, d = tensor.shape\n            length = int(l * ratio)\n            if length > l:\n                pad = torch.full((b, length - l, d), nan_value, device=tensor.device)\n                tensor = torch.cat([tensor, pad], dim=1)\n            elif length < l:\n                tensor = tensor[:, :length, :]\n            return tensor\n\n        return slide_tensor(imu, self.imu_scaled_nan, ratio), slide_tensor(thm, self.thm_scaled_nan, ratio), slide_tensor(tof, self.tof_scaled_nan, ratio)\n\n    def __getitem__(self, idx):\n        ret = [self.imu[idx], self.thm[idx], self.tof[idx], self.class_[idx], self.binary_class_[idx]]\n        if self.config.get(\"return_extra\", False):\n            fold_feat_info = [self.fold_feats[col][idx] for col in self.fold_cols]\n            ret.append((idx, fold_feat_info))\n        if self.config.get(\"use_dg\", False):\n            ret.append(self.dg[idx])\n        if self.config.get(\"return_flip_imu\", False):\n            ret.append(self.flip_imu[idx])\n        return ret\n\n    def __len__(self):\n        return len(self.class_)\n\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.sgkf = StratifiedGroupKFold(n_splits=n_folds, shuffle=True, random_state=random_seed)\n        self.fold_y = np.array(self.full_dataset.fold_feats[config.get(\"fold_y\", \"sequence_type\")])\n        self.fold_groups = np.array(self.full_dataset.fold_feats[config.get(\"fold_groups\", \"subject\")])\n        self.folds = list(self.sgkf.split(X=np.arange(len(self.full_dataset)), y=self.fold_y, groups=self.fold_groups))\n        self.exclude_subjects = set(config.get(\"exclude_subjects\", []))\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        subjects = np.array(self.full_dataset.fold_feats[\"subject\"])\n        train_subjects, valid_subjects = subjects[fold_train_idx], subjects[fold_valid_idx]\n        train_mask, valid_mask = ~np.isin(train_subjects, list(self.exclude_subjects)), ~np.isin(valid_subjects, list(self.exclude_subjects))\n        return Subset(self.full_dataset, np.array(fold_train_idx)[train_mask].tolist()), Subset(self.full_dataset, np.array(fold_valid_idx)[valid_mask].tolist())\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: 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(\"\\nCross-validation fold statistics:\")\n        for fold_idx, (train_idx, val_idx) in enumerate(self.folds):\n            train_subjects = set(self.fold_groups[train_idx])\n            val_subjects = set(self.fold_groups[val_idx])\n            print(f\"\\nFold {fold_idx + 1}:\")\n            print(\"Train subjects:\", train_subjects)\n            print(\"Valid subjects:\", val_subjects)\n\n        self.print_filtered_stats()\n\n    def print_filtered_stats(self):\n        original_counts = defaultdict(int)\n        filtered_counts = defaultdict(int)\n\n        for fold_idx in range(self.n_folds):\n            train_idx, val_idx = self.folds[fold_idx]\n            for idx in train_idx:\n                original_counts['train'] += 1\n            for idx in val_idx:\n                original_counts['valid'] += 1\n            train_set, val_set = self.get_fold_datasets(fold_idx)\n            filtered_counts['train'] += len(train_set)\n            filtered_counts['valid'] += len(val_set)\n\n        print(f\"\\nDataset size changes after excluding subjects {self.exclude_subjects}:\")\n        print(f\"Original train samples: {original_counts['train']}\")\n        print(f\"Filtered train samples: {filtered_counts['train']}\")\n        print(f\"Original valid samples: {original_counts['valid']}\")\n        print(f\"Filtered valid samples: {filtered_counts['valid']}\")\n\n\n#-----------------------------------------------\n\n\nclass PositionalEncoding(nn.Module):\n    def __init__(self, dim, max_len=1024):\n        super().__init__()\n        pe = torch.zeros(max_len, dim)\n        pos = torch.arange(0, max_len).unsqueeze(1)\n        div_term = torch.exp(torch.arange(0, dim, 2) * (-torch.log(torch.tensor(10000.0)) / dim))\n        pe[:, 0::2] = torch.sin(pos * div_term)\n        pe[:, 1::2] = torch.cos(pos * div_term)\n        self.register_buffer('pe', pe.unsqueeze(0))  # [1, max_len, dim]\n\n    def forward(self, x):\n        return x + self.pe[:, :x.size(1)]\n\n\n\nclass TransformerBlock_CL(nn.Module):\n    def __init__(self, dim, heads=8, ff_mult=4, dropout=0.1, depth=1):\n        super().__init__()\n        self.attn = nn.MultiheadAttention(dim, heads, dropout=dropout, batch_first=True)\n        #self.attn = DFattn(dim, heads, dropout=dropout, depth=depth)\n        self.norm1 = nn.LayerNorm(dim)\n        self.ff = nn.Sequential(\n            nn.Linear(dim, dim * ff_mult),\n            nn.GELU(),\n            nn.Dropout(dropout),\n            nn.Linear(dim * ff_mult, dim),\n            nn.Dropout(dropout),\n        )\n        self.norm2 = nn.LayerNorm(dim)\n\n    def forward(self, x):\n        attn_out, _ = self.attn(x, x, x)  # bidirectional: no masking\n        #attn_out = self.attn(x)  # DF_ATTN self\n        x = self.norm1(x + attn_out)\n        ff_out = self.ff(x)\n        x = self.norm2(x + ff_out)\n        return x\n\n\nclass TransformerEncoder_CL(nn.Module): # classic type\n    def __init__(self, input_dim, num_layers=6, heads=8):\n        super().__init__()\n        self.layers = nn.ModuleList([\n            TransformerBlock_CL(input_dim, heads=heads)\n            #TransformerBlock(input_dim, heads=heads, depth=i+1)\n            for i in range(num_layers)\n        ])\n\n    def forward(self, x):  # x: [B, T, D]\n        for layer in self.layers:\n            x = layer(x)\n        return x  # [B, T, D]\n\n\nclass TimeSeriesTransformer_CL(nn.Module):\n    def __init__(self, dim_in, num_layers, heads=8):\n        super().__init__()\n        self.cls_token = nn.Parameter(torch.randn(1, 1, dim_in))\n        self.num_register_tokens = 4\n        self.reg_token = nn.Parameter(torch.randn(1, self.num_register_tokens, dim_in))\n        self.pos_enc = PositionalEncoding(dim_in)\n        self.encoder = TransformerEncoder_CL(dim_in, num_layers, heads=heads)\n\n    def forward(self, x):  # x: [B, T, D]\n        B = x.size(0)\n        cls_tokens = self.cls_token.expand(B, 1, -1)  # [B, 1, D]\n        #reg_tokens = self.reg_token.expand(B, self.num_register_tokens, -1)  # [B, 4, D]\n        x = torch.cat([cls_tokens, x], dim=1)         # [B, T+1, D]\n        #x = torch.cat([x, cls_tokens, reg_tokens], dim=1)         # [B, T+1, D]\n        x = self.pos_enc(x)\n        x = self.encoder(x)\n        #return x[:, 0]  # return CLS token # torch.Size([4, 128])??\n        #return x  # return ENTIRE OUTPUT\n        return x[:, 1:]  # return EXCEPT CLS\n        #return x[:,:-self.num_register_tokens]\n\n#-----------------------------------------------\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\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\n\nclass AttentionLayer(nn.Module):\n    def __init__(self, feature_dim):\n        super().__init__()\n        self.score_fn = nn.Linear(feature_dim, 1, bias=True)\n        self.softmax = nn.Softmax(dim=1)\n\n    def forward(self, x):\n        # x: (B, L, F)\n        score = torch.tanh(self.score_fn(x))  # (B, L, 1)\n        weights = self.softmax(score.squeeze(-1))  # (B, L)\n        weights = weights.unsqueeze(-1)  # (B, L, 1)\n        context = x * weights  # (B, L, F)\n        return context.sum(dim=1)  # (B, F)\n\n\nclass GaussianNoise(nn.Module):\n    \"\"\"Add Gaussian noise to input tensor\"\"\"\n\n    def __init__(self, stddev):\n        super().__init__()\n        self.stddev = stddev\n\n    def forward(self, x):\n        if self.training:\n            noise = torch.randn_like(x) * self.stddev\n            return x + noise\n        return x\n\n\nclass CMIBackbone(nn.Module): # LSTM + GRU + DTF\n    def __init__(self, imu_dim, thm_dim, tof_dim, **kwargs):\n        super().__init__()\n        self.imu_acc_branch = nn.Sequential(\n            self.residual_feature_block(3, kwargs[\"imu1_channels\"], kwargs[\"imu1_layers\"], drop=kwargs[\"imu1_dropout\"]),\n            self.residual_feature_block(kwargs[\"imu1_channels\"], kwargs[\"imu2_channels\"], kwargs[\"imu2_layers\"],\n                                        drop=kwargs[\"imu2_dropout\"])\n        )\n        self.imu_rot_branch = nn.Sequential(\n            self.residual_feature_block(4, kwargs[\"imu1_channels\"], kwargs[\"imu1_layers\"], drop=kwargs[\"imu1_dropout\"]),\n            self.residual_feature_block(kwargs[\"imu1_channels\"], kwargs[\"imu2_channels\"], kwargs[\"imu2_layers\"],\n                                        drop=kwargs[\"imu2_dropout\"])\n        )\n        self.imu_other_branch = nn.Sequential(\n            self.residual_feature_block(imu_dim - 7, kwargs[\"imu1_channels\"], kwargs[\"imu1_layers\"],\n                                        drop=kwargs[\"imu1_dropout\"]),\n            self.residual_feature_block(kwargs[\"imu1_channels\"], kwargs[\"imu2_channels\"], kwargs[\"imu2_layers\"],\n                                        drop=kwargs[\"imu2_dropout\"])\n        )\n\n        self.thm_branch1, self.tof_branch1 = self.init_thm_tof_branch(thm_dim // 5, tof_dim // 5, **kwargs)\n        self.thm_branch2, self.tof_branch2 = self.init_thm_tof_branch(thm_dim // 5, tof_dim // 5, **kwargs)\n        self.thm_branch3, self.tof_branch3 = self.init_thm_tof_branch(thm_dim // 5, tof_dim // 5, **kwargs)\n        self.thm_branch4, self.tof_branch4 = self.init_thm_tof_branch(thm_dim // 5, tof_dim // 5, **kwargs)\n        self.thm_branch5, self.tof_branch5 = self.init_thm_tof_branch(thm_dim // 5, tof_dim // 5, **kwargs)\n\n        self.imu_proj = ResNetSEBlock(in_channels=3 * kwargs[\"imu2_channels\"], out_channels=kwargs[\"imu2_channels\"])\n        self.thm_proj = ResNetSEBlock(in_channels=5 * kwargs[\"thm2_channels\"], out_channels=kwargs[\"thm2_channels\"])\n        self.tof_proj = ResNetSEBlock(in_channels=5 * kwargs[\"tof2_channels\"], out_channels=kwargs[\"tof2_channels\"])\n\n        self.lstm = nn.LSTM(\n            input_size=kwargs['imu2_channels'] + kwargs['thm2_channels'] + kwargs['tof2_channels'],\n            hidden_size=kwargs['lstm_hidden_size'],\n            num_layers=1,\n            batch_first=True,\n            bidirectional=True\n        )\n\n        self.gru = nn.GRU(\n            input_size=kwargs['imu2_channels'] + kwargs['thm2_channels'] + kwargs['tof2_channels'],\n            hidden_size=kwargs['gru_hidden_size'],\n            num_layers=1,\n            batch_first=True,\n            bidirectional=True\n        )\n\n        self.noise = GaussianNoise(kwargs['gaussian_noise_rate'])\n        self.dense = nn.Sequential(\n            nn.Linear(kwargs['imu2_channels'] + kwargs['thm2_channels'] + kwargs['tof2_channels'], kwargs['dense_channels']),\n            nn.ELU()\n        )\n\n        # final_output = self.attn(torch.cat([lstm_out, gru_out, dense_out], dim=-1))\n        #self.dtf = TimeSeriesTransformer((kwargs['lstm_hidden_size'] + kwargs['gru_hidden_size']) * 2 + kwargs['dense_channels'], num_layers=6, heads=8)\n        #self.dtf = TimeSeriesTransformer_CL((kwargs['lstm_hidden_size'] + kwargs['gru_hidden_size']) * 2 + kwargs['dense_channels'], num_layers=6, heads=2)\n\n        #self.featconversion = nn.Linear(54, 53)\n        self.dtf = TimeSeriesTransformer_CL(kwargs['dense_channels'], num_layers=6, heads=2)\n        #print(f\"kwargs['imu2_channels'] + kwargs['thm2_channels'] + kwargs['tof2_channels'] = {kwargs['imu2_channels'] + kwargs['thm2_channels'] + kwargs['tof2_channels']}\")\n        #print(f\"kwargs['(kwargs['lstm_hidden_size'] + kwargs['gru_hidden_size']) * 2 + kwargs['dense_channels'] = {(kwargs['lstm_hidden_size'] + kwargs['gru_hidden_size']) * 2 + kwargs['dense_channels']}\")\n\n        self.attn = AttentionLayer(feature_dim=(kwargs['lstm_hidden_size'] + kwargs['gru_hidden_size']) * 2 + kwargs['dense_channels'] * 2)  # lstm + gru + dense\n\n    def feature_block(self, in_channels, out_channels, num_layers, pool_size=2, drop=0.3):\n        return nn.Sequential(\n            *[ResNetSEBlock(in_channels=in_channels, out_channels=in_channels) for i in range(num_layers)],\n            nn.Conv1d(in_channels, out_channels, kernel_size=3, padding=1, bias=False),\n            nn.BatchNorm1d(out_channels),\n            nn.ReLU(inplace=True),\n            nn.MaxPool1d(pool_size, ceil_mode=True),\n            nn.Dropout(drop)\n        )\n\n    def residual_feature_block(self, in_channels, out_channels, num_layers, pool_size=2, drop=0.3):\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=1e-4),\n            nn.MaxPool1d(pool_size, ceil_mode=True),\n            nn.Dropout(drop)\n        )\n\n    def init_thm_tof_branch(self, thm_dim, tof_dim, **kwargs):\n        thm_branch = nn.Sequential(\n            self.feature_block(thm_dim, kwargs[\"thm1_channels\"], kwargs[\"thm1_layers\"], drop=kwargs[\"thm1_dropout\"]),\n            self.feature_block(kwargs[\"thm1_channels\"], kwargs[\"thm2_channels\"], kwargs[\"thm2_layers\"],\n                               drop=kwargs[\"thm2_dropout\"]),\n        )\n        tof_branch = nn.Sequential(\n            self.feature_block(tof_dim, kwargs[\"tof1_channels\"], kwargs[\"tof1_layers\"], drop=kwargs[\"tof1_dropout\"]),\n            self.feature_block(kwargs[\"tof1_channels\"], kwargs[\"tof2_channels\"], kwargs[\"tof2_layers\"],\n                               drop=kwargs[\"tof2_dropout\"]),\n        )\n        return thm_branch, tof_branch\n\n    def forward(self, imus, thms, tofs):\n        #print(imus)\n        imu_acc, imu_rot, imu_other = imus\n        imu_acc_feat = self.imu_acc_branch(imu_acc.permute(0, 2, 1))\n        imu_rot_feat = self.imu_rot_branch(imu_rot.permute(0, 2, 1))\n        imu_other_feat = self.imu_other_branch(imu_other.permute(0, 2, 1))\n        imu_feat = self.imu_proj(torch.cat([imu_acc_feat, imu_rot_feat, imu_other_feat], dim=1))\n\n        thm1, thm2, thm3, thm4, thm5 = thms\n        tof1, tof2, tof3, tof4, tof5 = tofs\n\n        thm1_feat = self.thm_branch1(thm1.permute(0, 2, 1))\n        thm2_feat = self.thm_branch2(thm2.permute(0, 2, 1))\n        thm3_feat = self.thm_branch3(thm3.permute(0, 2, 1))\n        thm4_feat = self.thm_branch4(thm4.permute(0, 2, 1))\n        thm5_feat = self.thm_branch5(thm5.permute(0, 2, 1))\n        thm_feat = self.thm_proj(torch.cat([thm1_feat, thm2_feat, thm3_feat, thm4_feat, thm5_feat], dim=1))\n\n        tof1_feat = self.tof_branch1(tof1.permute(0, 2, 1))\n        tof2_feat = self.tof_branch2(tof2.permute(0, 2, 1))\n        tof3_feat = self.tof_branch3(tof3.permute(0, 2, 1))\n        tof4_feat = self.tof_branch4(tof4.permute(0, 2, 1))\n        tof5_feat = self.tof_branch5(tof5.permute(0, 2, 1))\n        tof_feat = self.tof_proj(torch.cat([tof1_feat, tof2_feat, tof3_feat, tof4_feat, tof5_feat], dim=1))\n\n        feat = torch.cat([imu_feat, thm_feat, tof_feat], dim=1).permute(0, 2, 1)\n\n        lstm_out, _ = self.lstm(feat)\n        gru_out, _ = self.gru(feat)\n        dense_out = self.dense(self.noise(feat))\n\n        tf_out = self.dtf(dense_out)\n\n        #print(f\"shapes : {feat.shape},{lstm_out.shape},{gru_out.shape},{dense_out.shape}\")\n        # shapes : torch.Size([64, 53, 832]),torch.Size([64, 53, 256]),torch.Size([64, 53, 256]),torch.Size([64, 53, 32])\n\n        #tf_out = self.featconversion(dense_out.transpose(-1,-2)).transpose(-1,-2)\n\n        #dtf_out = self.dtf(torch.cat([lstm_out, gru_out, dense_out], dim=-1))\n        final_output = self.attn(torch.cat([lstm_out, gru_out, dense_out, tf_out], dim=-1))\n        #final_output = self.attn(dtf_out)\n\n        return final_output\n        #return self.attn(torch.cat([lstm_out, gru_out, dense_out], dim=-1))\n\n\nclass CMIModel(nn.Module):\n    def __init__(self, target_classes_num, non_target_classes_num, **kwargs):\n        super().__init__()\n        self.backbone = CMIBackbone(dataset.imu_dim, dataset.thm_dim, dataset.tof_dim, **kwargs)\n        self.target_classifier = nn.Sequential(\n            nn.Linear((kwargs['lstm_hidden_size'] + kwargs['gru_hidden_size']) * 2 + kwargs['dense_channels'] * 2, kwargs[\"cls_channels1\"]),\n            nn.BatchNorm1d(kwargs[\"cls_channels1\"]),\n            nn.ReLU(),\n            nn.Dropout(kwargs[\"cls_dropout1\"]),\n            nn.Linear(kwargs[\"cls_channels1\"], kwargs[\"cls_channels2\"]),\n            nn.BatchNorm1d(kwargs[\"cls_channels2\"]),\n            nn.ReLU(),\n            nn.Dropout(kwargs[\"cls_dropout2\"]),\n            nn.Linear(kwargs[\"cls_channels2\"], target_classes_num)\n        )\n        self.non_target_classifier = nn.Sequential(\n            nn.Linear((kwargs['lstm_hidden_size'] + kwargs['gru_hidden_size']) * 2 + kwargs['dense_channels'] * 2, kwargs[\"cls_channels1\"]),\n            nn.BatchNorm1d(kwargs[\"cls_channels1\"]),\n            nn.ReLU(),\n            nn.Dropout(kwargs[\"cls_dropout1\"]),\n            nn.Linear(kwargs[\"cls_channels1\"], kwargs[\"cls_channels2\"]),\n            nn.BatchNorm1d(kwargs[\"cls_channels2\"]),\n            nn.ReLU(),\n            nn.Dropout(kwargs[\"cls_dropout2\"]),\n            nn.Linear(kwargs[\"cls_channels2\"], non_target_classes_num)\n        )\n\n    def forward(self, imu, thm, tof):\n        feat = self.backbone(imu, thm, tof)\n        targets_y = self.target_classifier(feat)\n        non_targets_y = self.non_target_classifier(feat)\n        return torch.cat([targets_y, non_targets_y], dim=1)\n\n\ndef replace(k):\n    k = k.replace(\"_orig_mod.\", \"\")\n    return k\n\n# ---------------------------\n# METRICS\nclass ParticipantVisibleError(Exception):\n    \"\"\"Errors raised here will be shown directly to the competitor.\"\"\"\n    pass\n\n\nclass Metric:\n    def __init__(self):\n        self.target_gestures = [\n            'Above ear - pull hair',\n            'Cheek - pinch skin',\n            'Eyebrow - pull hair',\n            'Eyelash - pull hair',\n            'Forehead - pull hairline',\n            'Forehead - scratch',\n            'Neck - pinch skin',\n            'Neck - scratch',\n        ]\n        self.non_target_gestures = [\n            'Write name on leg',\n            'Wave hello',\n            'Glasses on/off',\n            'Text on phone',\n            'Write name in air',\n            'Feel around in tray and pull out an object',\n            'Scratch knee/leg skin',\n            'Pull air toward your face',\n            'Drink from bottle/cup',\n            'Pinch knee/leg skin'\n        ]\n        self.all_classes = self.target_gestures + self.non_target_gestures\n        self.gts = dict()\n        self.preds = dict()\n        self.gts_p = dict()\n        self.preds_p = dict()\n        self.auto_idx = 0\n        self.auto_idx_p = 0\n\n    def add(self, gts, preds, ids=None):\n        if ids is None:\n            ids = range(self.auto_idx, self.auto_idx + len(gts))\n            self.auto_idx += len(gts)\n        for gt, pred, id_ in zip(gts, preds, ids):\n            if torch.is_tensor(id_):\n                id_ = id_.item()\n            self.gts[id_] = gt\n            self.preds[id_] = pred\n\n    def add_p(self, gts_p, preds_p, ids=None):\n        if ids is None:\n            ids = range(self.auto_idx_p, self.auto_idx_p + len(gts_p))\n            self.auto_idx_p += len(gts_p)\n        for gt_p, pred_p, id_ in zip(gts_p, preds_p, ids):\n            if torch.is_tensor(id_):\n                id_ = id_.item()\n            self.gts_p[id_] = gt_p\n            self.preds_p[id_] = pred_p\n\n    def merge_p(self, *metrics):\n        for metric in metrics:\n            assert set(self.gts_p.keys()) == set(metric.gts_p.keys()), \"GT not same, plz check\"\n            for id_ in self.gts_p.keys():\n                assert np.allclose(self.gts_p[id_], metric.gts_p[id_]), f\"GT values not same for ID {id_}\"\n\n        all_ids = list(self.preds_p.keys())\n        num_classes = len(next(iter(self.preds_p.values())))\n        combined = np.zeros((len(metrics) + 1, len(all_ids), num_classes))\n        for i, id_ in enumerate(all_ids):\n            combined[0, i] = self.preds_p[id_]\n        for m_idx, metric in enumerate(metrics, 1):\n            for i, id_ in enumerate(all_ids):\n                combined[m_idx, i] = metric.preds_p[id_]\n        avg_preds = combined.mean(axis=0)\n        for i, id_ in enumerate(all_ids):\n            self.preds_p[id_] = avg_preds[i].tolist()\n\n    def apply_weight(self, weight):\n        all_preds = np.array(list(self.preds_p.values()))\n        weighted = all_preds * weight\n        for id_, pred in zip(self.preds_p.keys(), weighted):\n            self.preds_p[id_] = pred.tolist()\n\n    def merge_vote(self, *metrics):\n        for metric in metrics:\n            assert set(self.gts.keys()) == set(metric.gts.keys()), \"GT IDs not same, please check\"\n            for id_ in self.gts.keys():\n                assert self.gts[id_] == metric.gts[id_], f\"GT values not same for ID {id_}\"\n\n        id_to_preds = defaultdict(list)\n        for metric in [self] + list(metrics):\n            id_to_preds.update(metric.preds)\n        vote_results = {}\n        for id_, preds in id_to_preds.items():\n            from collections import Counter\n            counts = Counter(preds)\n            max_count = max(counts.values())\n            candidates = [k for k, v in counts.items() if v == max_count]\n            vote_results[id_] = candidates[0] if len(candidates) == 1 else preds[0]\n        self.preds.update(vote_results)\n\n    def clear(self):\n        self.gts.clear()\n        self.preds.clear()\n        self.gts_p.clear()\n        self.preds_p.clear()\n        self.auto_idx = 0\n        self.auto_idx_p = 0\n\n    def score(self):\n        sorted_ids = sorted(self.gts.keys())\n        gts_list = [self.gts[id_] for id_ in sorted_ids]\n        preds_list = [self.preds[id_] for id_ in sorted_ids]\n        gts_pd = pd.Series(gts_list)\n        preds_pd = pd.Series(preds_list)\n        y_true_bin = gts_pd.isin(self.target_gestures).values\n        y_pred_bin = preds_pd.isin(self.target_gestures).values\n        f1_binary = f1_score(y_true_bin, y_pred_bin, pos_label=True, zero_division=0, average='binary')\n        y_true_mc = gts_pd.apply(lambda x: x if x in self.target_gestures else 'non_target')\n        y_pred_mc = preds_pd.apply(lambda x: x if x in self.target_gestures else 'non_target')\n        f1_macro = f1_score(y_true_mc, y_pred_mc, average='macro', zero_division=0)\n        return 0.5 * f1_binary + 0.5 * f1_macro\n\n    def acc(self):\n        sorted_ids = sorted(self.gts.keys())\n        gts = np.array([self.gts[id_] for id_ in sorted_ids])\n        preds = np.array([self.preds[id_] for id_ in sorted_ids])\n        return np.sum(preds == gts) / len(gts)\n\n    def score_p(self, classes):\n        sorted_ids = sorted(self.gts_p.keys())\n        gts_list = [classes[np.argmax(self.gts_p[id_])] for id_ in sorted_ids]\n        preds_list = [classes[np.argmax(self.preds_p[id_])] for id_ in sorted_ids]\n        gts_pd = pd.Series(gts_list)\n        preds_pd = pd.Series(preds_list)\n        y_true_bin = gts_pd.isin(self.target_gestures).values\n        y_pred_bin = preds_pd.isin(self.target_gestures).values\n        f1_binary = f1_score(y_true_bin, y_pred_bin, pos_label=True, zero_division=0, average='binary')\n        y_true_mc = gts_pd.apply(lambda x: x if x in self.target_gestures else 'non_target').values\n        y_pred_mc = preds_pd.apply(lambda x: x if x in self.target_gestures else 'non_target').values\n        f1_macro = f1_score(y_true_mc, y_pred_mc, average='macro', zero_division=0)\n        return 0.5 * f1_binary + 0.5 * f1_macro\n\n    def calculate_hierarchical_f1(self, sol: pd.DataFrame, sub: pd.DataFrame) -> float:\n        # Validate gestures\n        invalid_types = {i for i in sub['gesture'].unique() if i not in self.all_classes}\n        if invalid_types:\n            raise ParticipantVisibleError(f\"Invalid gesture values in submission: {invalid_types}\")\n\n        # Compute binary F1 (Target vs Non-Target)\n        y_true_bin = sol['gesture'].isin(self.target_gestures).values\n        y_pred_bin = sub['gesture'].isin(self.target_gestures).values\n        f1_binary = f1_score(\n            y_true_bin,\n            y_pred_bin,\n            pos_label=True,\n            zero_division=0,\n            average='binary'\n        )\n\n        # Build multi-class labels for gestures\n        y_true_mc = sol['gesture'].apply(lambda x: x if x in self.target_gestures else 'non_target')\n        y_pred_mc = sub['gesture'].apply(lambda x: x if x in self.target_gestures else 'non_target')\n\n        # Compute macro F1 over all gesture classes\n        f1_macro = f1_score(\n            y_true_mc,\n            y_pred_mc,\n            average='macro',\n            zero_division=0\n        )\n\n        # return 0.5 * f1_binary + 0.5 * f1_macro\n        return f1_binary, f1_macro\n\n\n# ---------------------------\n\ndef to_cuda(*tensors):\n    return [tensor.to(CUDA0) for tensor in tensors]\n\n\ndef inference(model, imu, thm, tof):\n    imus, thms, tofs = dataset.full_dataset.split5(imu, thm, tof)\n    with autocast(device_type='cuda', dtype=torch.bfloat16):\n        pred_y = model(imus, thms, tofs)\n    return pred_y\n\n\ndef valid(model, valid_bar):\n    with torch.no_grad():\n        for imu, thm, tof, y, b in valid_bar:\n            imu, thm, tof, y = to_cuda(imu, thm, tof, y)\n            pred_y = inference(model, imu, thm, tof)\n            metric.add(dataset.le.classes_[y.argmax(dim=1).cpu()], dataset.le.classes_[pred_y.argmax(dim=1).cpu()])\n            _, thm, tof = dataset.full_dataset.get_scaled_nan_tensors(imu, thm, tof)\n            pred_y = inference(model, imu, thm, tof)\n            imu_only_metric.add(dataset.le.classes_[y.argmax(dim=1).cpu()], dataset.le.classes_[pred_y.argmax(dim=1).cpu()])\n\n\n\n# ---------------------------\n\n\nif not TRAIN:\n    dataset = init_dataset()\n    metric = Metric()\n    imu_only_metric = Metric()\n\n    model_function = CMIModel\n    model_dicts = [\n        {\n            \"model_function\": model_function,\n            \"model_args\": model_args,\n            \"model_path\": model_dir / f\"model_fold{fold}.pt\",\n        } for fold in range(n_folds)\n    ]\n    models = list()\n\n    for 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 = {replace(k): v for k, v in torch.load(model_path).items()}\n        model.load_state_dict(state_dict)\n        model = model.eval()\n        models.append(model)\n\n\nprint(\"DONE!\")\n\n\ndef avg_predict(models, imu, thm, tof):\n    outputs = []\n    with autocast(device_type='cuda', dtype=torch.bfloat16):\n        for model in models:\n            pred_y = inference(model, imu, thm, tof)\n            outputs.append(pred_y)\n    return torch.mean(torch.stack(outputs), dim=0)\n\n\ndef predict(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        if imu_only:\n            _, thm, tof = dataset.full_dataset.get_scaled_nan_tensors(imu, thm, tof)\n        pred_y = avg_predict(models, imu, thm, tof)\n    return dataset.le.classes_[pred_y.argmax(dim=1).cpu()]\n\n\nimport kaggle_evaluation.cmi_inference_server\n\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    )","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-09-02T23:02:35.795322Z","iopub.execute_input":"2025-09-02T23:02:35.795658Z","iopub.status.idle":"2025-09-02T23:05:09.498374Z","shell.execute_reply.started":"2025-09-02T23:02:35.795634Z","shell.execute_reply":"2025-09-02T23:05:09.497684Z"}},"outputs":[],"execution_count":null}]}