{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":40277,"databundleVersionId":4725531,"sourceType":"competition"},{"sourceId":4133932,"sourceType":"datasetVersion","datasetId":2442142},{"sourceId":10659762,"sourceType":"datasetVersion","datasetId":6601212}],"dockerImageVersionId":30840,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import os\nimport sys\nsys.path.append('/kaggle/input/timm-0-6-9/pytorch-image-models-master')\nimport glob\nimport numpy as np\nimport pandas as pd\nimport random\nimport math\nimport gc\nimport cv2\nfrom tqdm import tqdm\nimport time\nfrom functools import lru_cache\nimport torch\nfrom torch import nn\nfrom torch.nn import functional as F\nfrom torch.utils.data import Dataset, DataLoader\nfrom torch.cuda.amp import autocast, GradScaler\nimport timm\nimport albumentations as A\nfrom albumentations.pytorch import ToTensorV2\nimport matplotlib.pyplot as plt\nfrom sklearn.metrics import matthews_corrcoef","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T04:39:40.321605Z","iopub.execute_input":"2025-02-03T04:39:40.321966Z","iopub.status.idle":"2025-02-03T04:39:51.486560Z","shell.execute_reply.started":"2025-02-03T04:39:40.321935Z","shell.execute_reply":"2025-02-03T04:39:51.485517Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"CFG = {\n    'seed': 42,\n    'model': 'resnet50',\n    'img_size': 256,\n    'epochs': 10,\n    'train_bs': 100, \n    'valid_bs': 64,\n    'lr': 1e-3, \n    'weight_decay': 1e-6,\n    'num_workers': 4\n}","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T04:40:35.959199Z","iopub.execute_input":"2025-02-03T04:40:35.959549Z","iopub.status.idle":"2025-02-03T04:40:35.963939Z","shell.execute_reply.started":"2025-02-03T04:40:35.959521Z","shell.execute_reply":"2025-02-03T04:40:35.962921Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def seed_everything(seed):\n    random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed(seed)\n    torch.cuda.manual_seed_all(seed)\n    torch.backends.cudnn.deterministic = True\n    torch.backends.cudnn.benchmark = False\n\nseed_everything(CFG['seed'])\ndevice = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\ndef expand_contact_id(df):\n    \"\"\"\n    Splits out contact_id into seperate columns.\n    \"\"\"\n    df[\"game_play\"] = df[\"contact_id\"].str[:12]\n    df[\"step\"] = df[\"contact_id\"].str.split(\"_\").str[-3].astype(\"int\")\n    df[\"nfl_player_id_1\"] = df[\"contact_id\"].str.split(\"_\").str[-2]\n    df[\"nfl_player_id_2\"] = df[\"contact_id\"].str.split(\"_\").str[-1]\n    return df\n\nlabels = expand_contact_id(pd.read_csv(\"/kaggle/input/nfl-player-contact-detection/sample_submission.csv\"))\n\ntest_tracking = pd.read_csv(\"/kaggle/input/nfl-player-contact-detection/test_player_tracking.csv\")\n\ntest_helmets = pd.read_csv(\"/kaggle/input/nfl-player-contact-detection/test_baseline_helmets.csv\")\n\ntest_video_metadata = pd.read_csv(\"/kaggle/input/nfl-player-contact-detection/test_video_metadata.csv\")\n!mkdir -p ../work/frames\n\nfor video in tqdm(test_helmets.video.unique()):\n    if 'Endzone2' not in video:\n        !ffmpeg -i /kaggle/input/nfl-player-contact-detection/test/{video} -q:v 2 -f image2 /kaggle/work/frames/{video}_%04d.jpg -hide_banner -loglevel error","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T04:40:38.703935Z","iopub.execute_input":"2025-02-03T04:40:38.704245Z","iopub.status.idle":"2025-02-03T04:41:05.591830Z","shell.execute_reply.started":"2025-02-03T04:40:38.704222Z","shell.execute_reply":"2025-02-03T04:41:05.590921Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def create_features(df, tr_tracking, merge_col=\"step\", use_cols=[\"x_position\", \"y_position\"]):\n    output_cols = []\n    df_combo = (\n        df.astype({\"nfl_player_id_1\": \"str\"})\n        .merge(\n            tr_tracking.astype({\"nfl_player_id\": \"str\"})[\n                [\"game_play\", merge_col, \"nfl_player_id\",] + use_cols\n            ],\n            left_on=[\"game_play\", merge_col, \"nfl_player_id_1\"],\n            right_on=[\"game_play\", merge_col, \"nfl_player_id\"],\n            how=\"left\",\n        )\n        .rename(columns={c: c+\"_1\" for c in use_cols})\n        .drop(\"nfl_player_id\", axis=1)\n        .merge(\n            tr_tracking.astype({\"nfl_player_id\": \"str\"})[\n                [\"game_play\", merge_col, \"nfl_player_id\"] + use_cols\n            ],\n            left_on=[\"game_play\", merge_col, \"nfl_player_id_2\"],\n            right_on=[\"game_play\", merge_col, \"nfl_player_id\"],\n            how=\"left\",\n        )\n        .drop(\"nfl_player_id\", axis=1)\n        .rename(columns={c: c+\"_2\" for c in use_cols})\n        .sort_values([\"game_play\", merge_col, \"nfl_player_id_1\", \"nfl_player_id_2\"])\n        .reset_index(drop=True)\n    )\n    output_cols += [c+\"_1\" for c in use_cols]\n    output_cols += [c+\"_2\" for c in use_cols]\n    \n    if (\"x_position\" in use_cols) & (\"y_position\" in use_cols):\n        index = df_combo['x_position_2'].notnull()\n        \n        distance_arr = np.full(len(index), np.nan)\n        tmp_distance_arr = np.sqrt(\n            np.square(df_combo.loc[index, \"x_position_1\"] - df_combo.loc[index, \"x_position_2\"])\n            + np.square(df_combo.loc[index, \"y_position_1\"]- df_combo.loc[index, \"y_position_2\"])\n        )\n        \n        distance_arr[index] = tmp_distance_arr\n        df_combo['distance'] = distance_arr\n        output_cols += [\"distance\"]\n        \n    df_combo['G_flug'] = (df_combo['nfl_player_id_2']==\"G\")\n    output_cols += [\"G_flug\"]\n    return df_combo, output_cols\n\n\nuse_cols = [\n    'x_position', 'y_position', 'speed', 'distance',\n    'direction', 'orientation', 'acceleration', 'sa'\n]\n\ntest, feature_cols = create_features(labels, test_tracking, use_cols=use_cols)\ntest\ntest_filtered = test.query('not distance>2').reset_index(drop=True)\ntest_filtered['frame'] = (test_filtered['step']/10*59.94+5*59.94).astype('int')+1\ntest_filtered\ndel test, labels, test_tracking\ngc.collect()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T04:41:34.959790Z","iopub.execute_input":"2025-02-03T04:41:34.960128Z","iopub.status.idle":"2025-02-03T04:41:35.474435Z","shell.execute_reply.started":"2025-02-03T04:41:34.960099Z","shell.execute_reply":"2025-02-03T04:41:35.473646Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_aug = A.Compose([\n    A.HorizontalFlip(p=0.5),\n    A.ShiftScaleRotate(p=0.5),\n    A.RandomBrightnessContrast(brightness_limit=(-0.1, 0.1), contrast_limit=(-0.1, 0.1), p=0.5),\n    A.Normalize(mean=[0.], std=[1.]),\n    ToTensorV2()\n])\n\nvalid_aug = A.Compose([\n    A.Normalize(mean=[0.], std=[1.]),\n    ToTensorV2()\n])\nvideo2helmets = {}\ntest_helmets_new = test_helmets.set_index('video')\nfor video in tqdm(test_helmets.video.unique()):\n    video2helmets[video] = test_helmets_new.loc[video].reset_index(drop=True)\n    \ndel test_helmets, test_helmets_new\ngc.collect()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T04:41:41.433466Z","iopub.execute_input":"2025-02-03T04:41:41.433912Z","iopub.status.idle":"2025-02-03T04:41:41.696784Z","shell.execute_reply.started":"2025-02-03T04:41:41.433875Z","shell.execute_reply":"2025-02-03T04:41:41.695852Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"video2frames = {}\n\nfor game_play in tqdm(test_video_metadata.game_play.unique()):\n    for view in ['Endzone', 'Sideline']:\n        video = game_play + f'_{view}.mp4'\n        video2frames[video] = max(list(map(lambda x:int(x.split('_')[-1].split('.')[0]), \\\n                                           glob.glob(f'/kaggle/work/frames/{video}*'))))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T04:41:44.008692Z","iopub.execute_input":"2025-02-03T04:41:44.008977Z","iopub.status.idle":"2025-02-03T04:41:44.047620Z","shell.execute_reply.started":"2025-02-03T04:41:44.008956Z","shell.execute_reply":"2025-02-03T04:41:44.046580Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class MyDataset(Dataset):\n    def __init__(self, df, aug=valid_aug, mode='train'):\n        self.df = df\n        self.frame = df.frame.values\n        self.feature = df[feature_cols].fillna(-1).values\n        self.players = df[['nfl_player_id_1','nfl_player_id_2']].values\n        self.game_play = df.game_play.values\n        self.aug = aug\n        self.mode = mode\n        \n    def __len__(self):\n        return len(self.df)\n    \n    # @lru_cache(1024)\n    # def read_img(self, path):\n    #     return cv2.imread(path, 0)\n   \n    def __getitem__(self, idx):   \n        window = 24\n        frame = self.frame[idx]\n        \n        if self.mode == 'train':\n            frame = frame + random.randint(-6, 6)\n\n        players = []\n        for p in self.players[idx]:\n            if p == 'G':\n                players.append(p)\n            else:\n                players.append(int(p))\n        \n        imgs = []\n        for view in ['Endzone', 'Sideline']:\n            video = self.game_play[idx] + f'_{view}.mp4'\n\n            tmp = video2helmets[video]\n#             tmp = tmp.query('@frame-@window<=frame<=@frame+@window')\n            tmp[tmp['frame'].between(frame-window, frame+window)]\n            tmp = tmp[tmp.nfl_player_id.isin(players)]#.sort_values(['nfl_player_id', 'frame'])\n            tmp_frames = tmp.frame.values\n            tmp = tmp.groupby('frame')[['left','width','top','height']].mean()\n#0.002s\n\n            bboxes = []\n            for f in range(frame-window, frame+window+1, 1):\n                if f in tmp_frames:\n                    x, w, y, h = tmp.loc[f][['left','width','top','height']]\n                    bboxes.append([x, w, y, h])\n                else:\n                    bboxes.append([np.nan, np.nan, np.nan, np.nan])\n            bboxes = pd.DataFrame(bboxes).interpolate(limit_direction='both').values\n            bboxes = bboxes[::4]\n\n            if bboxes.sum() > 0:\n                flag = 1\n            else:\n                flag = 0\n#0.03s\n                    \n            for i, f in enumerate(range(frame-window, frame+window+1, 4)):\n                img_new = np.zeros((256, 256), dtype=np.float32)\n\n                if flag == 1 and f <= video2frames[video]:\n                    img = cv2.imread(f'/kaggle/work/frames/{video}_{f:04d}.jpg', 0)\n\n                    x, w, y, h = bboxes[i]\n\n                    img = img[int(y+h/2)-128:int(y+h/2)+128,int(x+w/2)-128:int(x+w/2)+128].copy()\n                    img_new[:img.shape[0], :img.shape[1]] = img\n                    \n                imgs.append(img_new)\n#0.06s\n                \n        feature = np.float32(self.feature[idx])\n\n        img = np.array(imgs).transpose(1, 2, 0)    \n        img = self.aug(image=img)[\"image\"]\n        label = np.float32(self.df.contact.values[idx])\n\n        return img, feature, label\nimg, feature, label = MyDataset(test_filtered, valid_aug, 'test')[0]\nplt.imshow(img.permute(1,2,0)[:,:,7])\nplt.show()\nimg.shape, feature, label\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T04:41:46.533460Z","iopub.execute_input":"2025-02-03T04:41:46.533764Z","iopub.status.idle":"2025-02-03T04:41:47.042223Z","shell.execute_reply.started":"2025-02-03T04:41:46.533744Z","shell.execute_reply":"2025-02-03T04:41:47.041234Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class Model(nn.Module):\n    def __init__(self):\n        super(Model, self).__init__()\n        self.backbone = timm.create_model(CFG['model'], pretrained=False, num_classes=500, in_chans=13)\n        self.mlp = nn.Sequential(\n            nn.Linear(18, 64),\n            nn.LayerNorm(64),\n            nn.ReLU(),\n            nn.Dropout(0.2),\n            # nn.Linear(64, 64),\n            # nn.LayerNorm(64),\n            # nn.ReLU(),\n            # nn.Dropout(0.2)\n        )\n        self.fc = nn.Linear(64+500*2, 1)\n\n    def forward(self, img, feature):\n        b, c, h, w = img.shape\n        img = img.reshape(b*2, c//2, h, w)\n        img = self.backbone(img).reshape(b, -1)\n        feature = self.mlp(feature)\n        y = self.fc(torch.cat([img, feature], dim=1))\n        return y\ntest_set = MyDataset(test_filtered, valid_aug, 'test')\ntest_loader = DataLoader(test_set, batch_size=CFG['valid_bs'], shuffle=False, num_workers=CFG['num_workers'], pin_memory=True)\n\nmodel = Model().to(device)\nmodel = torch.load('/kaggle/input/best-weight/best_model (1).pt')\n\nmodel.eval()\n    \ny_pred = []\nwith torch.no_grad():\n    tk = tqdm(test_loader, total=len(test_loader))\n    for step, batch in enumerate(tk):\n        if(step % 4 != 3):\n            img, feature, label = [x.to(device) for x in batch]\n            output1 = model(img, feature).squeeze(-1)\n            output2 = model(img.flip(-1), feature).squeeze(-1)\n            \n            y_pred.extend(0.2*(output1.sigmoid().cpu().numpy()) + 0.8*(output2.sigmoid().cpu().numpy()))\n        else:\n            img, feature, label = [x.to(device) for x in batch]\n            output = model(img.flip(-1), feature).squeeze(-1)\n            y_pred.extend(output.sigmoid().cpu().numpy())    \n\ny_pred = np.array(y_pred)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T04:41:51.401556Z","iopub.execute_input":"2025-02-03T04:41:51.401867Z","iopub.status.idle":"2025-02-03T04:50:04.657823Z","shell.execute_reply.started":"2025-02-03T04:41:51.401842Z","shell.execute_reply":"2025-02-03T04:50:04.656708Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"th = 0.29\n\ntest_filtered['contact'] = (y_pred >= th).astype('int')\n\nsub = pd.read_csv('/kaggle/input/nfl-player-contact-detection/sample_submission.csv')\n\nsub = sub.drop(\"contact\", axis=1).merge(test_filtered[['contact_id', 'contact']], how='left', on='contact_id')\nsub['contact'] = sub['contact'].fillna(0).astype('int')\n\nsub[[\"contact_id\", \"contact\"]].to_csv(\"submission.csv\", index=False)\n\nsub.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T04:55:08.247417Z","iopub.execute_input":"2025-02-03T04:55:08.247905Z","iopub.status.idle":"2025-02-03T04:55:08.423776Z","shell.execute_reply.started":"2025-02-03T04:55:08.247862Z","shell.execute_reply":"2025-02-03T04:55:08.422784Z"}},"outputs":[],"execution_count":null}]}