{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","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":251413288,"sourceType":"kernelVersion"},{"sourceId":260655310,"sourceType":"kernelVersion"},{"sourceId":470587,"sourceType":"modelInstanceVersion","modelInstanceId":379625,"modelId":398856},{"sourceId":517084,"sourceType":"modelInstanceVersion","modelInstanceId":407853,"modelId":400086}],"dockerImageVersionId":31041,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Import","metadata":{}},{"cell_type":"code","source":"import os\nimport torch\nimport kagglehub\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\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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-09-22T07:23:34.591762Z","iopub.execute_input":"2025-09-22T07:23:34.591995Z","iopub.status.idle":"2025-09-22T07:23:40.815240Z","shell.execute_reply.started":"2025-09-22T07:23:34.591970Z","shell.execute_reply":"2025-09-22T07:23:40.814619Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Dataset\nCompared to last notebook I release, change skf to sgkf and set percent=99.","metadata":{}},{"cell_type":"code","source":"def 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","metadata":{"trusted":true,"_kg_hide-input":true,"execution":{"iopub.status.busy":"2025-09-22T07:23:43.944333Z","iopub.execute_input":"2025-09-22T07:23:43.945090Z","iopub.status.idle":"2025-09-22T07:23:43.957322Z","shell.execute_reply.started":"2025-09-22T07:23:43.945063Z","shell.execute_reply":"2025-09-22T07:23:43.956480Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class 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', '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', 'linear_acc_z'] if self.config.get(\"add_raw_acc\", False) else ['linear_acc_x', 'linear_acc_y', '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'] + [c for c in self.raw_columns if c.startswith('thm_')] + [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}'] = 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(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        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        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 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 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(), 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(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(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), 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        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_)","metadata":{"trusted":true,"jupyter":{"source_hidden":true},"_kg_hide-input":true,"execution":{"iopub.status.busy":"2025-09-22T07:23:47.094163Z","iopub.execute_input":"2025-09-22T07:23:47.094882Z","iopub.status.idle":"2025-09-22T07:23:47.171963Z","shell.execute_reply.started":"2025-09-22T07:23:47.094857Z","shell.execute_reply":"2025-09-22T07:23:47.171362Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class 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: 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(\"\\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            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        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(\"训练集受试者:\", train_subjects)\n            print(\"验证集受试者:\", 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\"\\n排除subject {self.exclude_subjects} 后的数据量变化:\")\n        print(f\"原始训练集样本: {original_counts['train']}\")\n        print(f\"过滤后训练集样本: {filtered_counts['train']}\")\n        print(f\"原始验证集样本: {original_counts['valid']}\") \n        print(f\"过滤后验证集样本: {filtered_counts['valid']}\")","metadata":{"trusted":true,"jupyter":{"source_hidden":true},"_kg_hide-input":true,"execution":{"iopub.status.busy":"2025-09-22T07:23:48.473092Z","iopub.execute_input":"2025-09-22T07:23:48.473359Z","iopub.status.idle":"2025-09-22T07:23:48.486350Z","shell.execute_reply.started":"2025-09-22T07:23:48.473340Z","shell.execute_reply":"2025-09-22T07:23:48.485476Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Model\nMain changes here. The idea is: the dataset has many nan values, but count of nans is not the same in different sensors.\n\nFor example, in thm data, the count of nans for thm1-thm5:\n\n(6987, 7638, 6472, 6224, 33286)\n\nSo I consider it's not good to just combine all thm data and return thm_feat. Instead, make every thm sensor has its own feature layer and combine it at last.\n\nImu and tof data have same condition in nan counts. For imu, acc has no nan but rot does have. For tof, almost same as thm but a little different. Also mention that thm5 and tof5 have obviously more nans than other sensors.","metadata":{}},{"cell_type":"code","source":"class 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 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\nclass GaussianNoise(nn.Module):\n    \"\"\"Add Gaussian noise to input tensor\"\"\"\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","metadata":{"trusted":true,"jupyter":{"source_hidden":true},"_kg_hide-input":true,"execution":{"iopub.status.busy":"2025-09-22T07:23:51.874526Z","iopub.execute_input":"2025-09-22T07:23:51.874902Z","iopub.status.idle":"2025-09-22T07:23:51.885321Z","shell.execute_reply.started":"2025-09-22T07:23:51.874878Z","shell.execute_reply":"2025-09-22T07:23:51.884653Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class CMIBackbone(nn.Module):\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\"], 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\"], 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\"], drop=kwargs[\"imu1_dropout\"]),\n            self.residual_feature_block(kwargs[\"imu1_channels\"], kwargs[\"imu2_channels\"], kwargs[\"imu2_layers\"], 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        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        self.attn = AttentionLayer(feature_dim=(kwargs['lstm_hidden_size']+kwargs['gru_hidden_size'])*2+kwargs['dense_channels'])  # 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\"], 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\"], drop=kwargs[\"tof2_dropout\"]),\n        )\n        return thm_branch, tof_branch\n    \n    def forward(self, imus, thms, tofs):\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        lstm_out, _ = self.lstm(feat)\n        gru_out, _ = self.gru(feat)\n        dense_out = self.dense(self.noise(feat))\n        \n        return self.attn(torch.cat([lstm_out, gru_out, dense_out], dim=-1))","metadata":{"trusted":true,"_kg_hide-input":true,"execution":{"iopub.status.busy":"2025-09-22T07:23:54.675046Z","iopub.execute_input":"2025-09-22T07:23:54.675747Z","iopub.status.idle":"2025-09-22T07:23:54.693033Z","shell.execute_reply.started":"2025-09-22T07:23:54.675706Z","shell.execute_reply":"2025-09-22T07:23:54.692292Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Settings","metadata":{}},{"cell_type":"code","source":"CUDA0 = \"cuda:0\"\nseed = 0\nbatch_size = 64\nnum_workers = 4\nn_folds = 5\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\")\n\nimu_only = False\n\ndeterministic = kagglehub.package_import('wasupandceacar/deterministic').deterministic\ndeterministic.init_all(seed)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-22T07:23:58.829594Z","iopub.execute_input":"2025-09-22T07:23:58.830355Z","iopub.status.idle":"2025-09-22T07:24:13.378595Z","shell.execute_reply.started":"2025-09-22T07:23:58.830320Z","shell.execute_reply":"2025-09-22T07:24:13.377739Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def 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\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()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-22T07:24:13.379921Z","iopub.execute_input":"2025-09-22T07:24:13.380505Z","iopub.status.idle":"2025-09-22T07:26:55.376657Z","shell.execute_reply.started":"2025-09-22T07:24:13.380483Z","shell.execute_reply":"2025-09-22T07:26:55.375903Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class 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'], 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'], 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\nmodel_function = CMIModel\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,}\nmodel_dir = Path(\"/kaggle/input/cmi-models-public/pytorch/base04/1\")\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\ndef replace(k):\n    k = k.replace(\"_orig_mod.\", \"\")\n    return k\n\nmodels = 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 = {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)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-22T07:26:55.377967Z","iopub.execute_input":"2025-09-22T07:26:55.378285Z","iopub.status.idle":"2025-09-22T07:27:01.229587Z","shell.execute_reply.started":"2025-09-22T07:26:55.378263Z","shell.execute_reply":"2025-09-22T07:27:01.228682Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Valid","metadata":{}},{"cell_type":"code","source":"metric_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 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\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\nfor fold, model in enumerate(models):\n    valid_loader = get_fold_dataset(dataset, fold)\n    valid_bar = tqdm(valid_loader, desc=f\"Valid\", leave=False)\n    valid(model, valid_bar)\n\nprint(f\"\"\"\nNormal score: {metric.score()}\nIMU only score: {imu_only_metric.score()}\n\"\"\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-09-22T07:27:01.230962Z","iopub.execute_input":"2025-09-22T07:27:01.231212Z","iopub.status.idle":"2025-09-22T07:30:35.957216Z","shell.execute_reply.started":"2025-09-22T07:27:01.231194Z","shell.execute_reply":"2025-09-22T07:30:35.956460Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Submit","metadata":{}},{"cell_type":"code","source":"def 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\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\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":{"trusted":true,"execution":{"iopub.status.busy":"2025-08-11T18:10:11.434715Z","iopub.execute_input":"2025-08-11T18:10:11.435036Z","iopub.status.idle":"2025-08-11T18:10:13.765355Z","shell.execute_reply.started":"2025-08-11T18:10:11.435009Z","shell.execute_reply":"2025-08-11T18:10:13.764736Z"}},"outputs":[],"execution_count":null}]}