{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport torch\nimport os\nimport pytorch_lightning as pl\nfrom torch.utils.data import Dataset, DataLoader\nfrom sklearn import model_selection\nimport torchvision.transforms as transforms\nimport torchvision.io \nimport librosa\nfrom PIL import Image\nimport albumentations as alb\nimport torch.multiprocessing as mp\nimport warnings\nimport random\n\nwarnings.filterwarnings('ignore')","metadata":{"papermill":{"duration":6.667352,"end_time":"2022-04-22T06:00:08.901647","exception":false,"start_time":"2022-04-22T06:00:02.234295","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-05-04T01:13:30.900860Z","iopub.execute_input":"2023-05-04T01:13:30.901430Z","iopub.status.idle":"2023-05-04T01:13:30.908533Z","shell.execute_reply.started":"2023-05-04T01:13:30.901387Z","shell.execute_reply":"2023-05-04T01:13:30.907246Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from pytorch_lightning.callbacks import ModelCheckpoint, BackboneFinetuning, EarlyStopping\n","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:30.913399Z","iopub.execute_input":"2023-05-04T01:13:30.914097Z","iopub.status.idle":"2023-05-04T01:13:30.918781Z","shell.execute_reply.started":"2023-05-04T01:13:30.914067Z","shell.execute_reply":"2023-05-04T01:13:30.917713Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install -q torchtoolbox timm\n","metadata":{"papermill":{"duration":9.48179,"end_time":"2022-04-22T06:00:18.413844","exception":false,"start_time":"2022-04-22T06:00:08.932054","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-05-04T01:13:30.924082Z","iopub.execute_input":"2023-05-04T01:13:30.924826Z","iopub.status.idle":"2023-05-04T01:13:40.937006Z","shell.execute_reply.started":"2023-05-04T01:13:30.924789Z","shell.execute_reply":"2023-05-04T01:13:40.935677Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Config:\n    use_aug = False\n    num_classes = 264\n    batch_size = 64\n    epochs = 12\n    PRECISION = 16    \n    PATIENCE = 8    \n    seed = 2023\n    model = \"tf_efficientnet_b0_ns\"\n    pretrained = True            \n    weight_decay = 1e-3\n    use_mixup = True\n    mixup_alpha = 0.5   \n    DEVICE = torch.device('cuda' if torch.cuda.is_available() else 'cpu')    \n\n    data_root = \"/kaggle/input/birdclef-2023/\"\n    train_images = \"/kaggle/input/split-creating-melspecs-stage-1/specs/train/\"\n    valid_images = \"/kaggle/input/split-creating-melspecs-stage-1/specs/valid/\"\n    train_path = \"/kaggle/input/bc2023-train-val-df/train.csv\"\n    valid_path = \"/kaggle/input/bc2023-train-val-df/valid.csv\"\n    \n    mask_prob = 0.52\n    freq_mask = 20\n    time_mask = 30\n    mixup_prob = 0.65\n    mixup_times = 20\n    mixup_alpha = 0.5\n    \n    SR = 32000\n    DURATION = 5\n    MAX_READ_SAMPLES = 5\n    LR = 5e-4\n    ","metadata":{"papermill":{"duration":0.099568,"end_time":"2022-04-22T06:00:18.542447","exception":false,"start_time":"2022-04-22T06:00:18.442879","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-05-04T01:13:40.940446Z","iopub.execute_input":"2023-05-04T01:13:40.940886Z","iopub.status.idle":"2023-05-04T01:13:40.950464Z","shell.execute_reply.started":"2023-05-04T01:13:40.940830Z","shell.execute_reply":"2023-05-04T01:13:40.948299Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pl.seed_everything(Config.seed, workers=True)","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:40.951732Z","iopub.execute_input":"2023-05-04T01:13:40.952038Z","iopub.status.idle":"2023-05-04T01:13:40.965361Z","shell.execute_reply.started":"2023-05-04T01:13:40.952010Z","shell.execute_reply":"2023-05-04T01:13:40.964124Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def config_to_dict(cfg):\n    return dict((name, getattr(cfg, name)) for name in dir(cfg) if not name.startswith('__'))","metadata":{"papermill":{"duration":0.033041,"end_time":"2022-04-22T06:00:18.664481","exception":false,"start_time":"2022-04-22T06:00:18.63144","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-05-04T01:13:40.968949Z","iopub.execute_input":"2023-05-04T01:13:40.969411Z","iopub.status.idle":"2023-05-04T01:13:40.974702Z","shell.execute_reply.started":"2023-05-04T01:13:40.969375Z","shell.execute_reply":"2023-05-04T01:13:40.973576Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = pd.read_csv(Config.train_path)\ndf_valid = pd.read_csv(Config.valid_path)\ndf_train.head()","metadata":{"papermill":{"duration":58.466679,"end_time":"2022-04-22T06:01:17.158088","exception":false,"start_time":"2022-04-22T06:00:18.691409","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-05-04T01:13:40.976408Z","iopub.execute_input":"2023-05-04T01:13:40.977144Z","iopub.status.idle":"2023-05-04T01:13:41.096226Z","shell.execute_reply.started":"2023-05-04T01:13:40.977096Z","shell.execute_reply":"2023-05-04T01:13:41.095154Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Config.num_classes = len(df_train.primary_label.unique())","metadata":{"papermill":{"duration":0.035353,"end_time":"2022-04-22T06:01:17.283888","exception":false,"start_time":"2022-04-22T06:01:17.248535","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-05-04T01:13:41.097612Z","iopub.execute_input":"2023-05-04T01:13:41.098299Z","iopub.status.idle":"2023-05-04T01:13:41.104923Z","shell.execute_reply.started":"2023-05-04T01:13:41.098259Z","shell.execute_reply":"2023-05-04T01:13:41.103680Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = pd.concat([df_train, pd.get_dummies(df_train['primary_label'])], axis=1)\ndf_valid = pd.concat([df_valid, pd.get_dummies(df_valid['primary_label'])], axis=1)","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:41.106713Z","iopub.execute_input":"2023-05-04T01:13:41.107355Z","iopub.status.idle":"2023-05-04T01:13:41.131789Z","shell.execute_reply.started":"2023-05-04T01:13:41.107150Z","shell.execute_reply":"2023-05-04T01:13:41.130823Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Create & Fill birds with 0 samples in validation","metadata":{}},{"cell_type":"code","source":"birds = list(df_train.primary_label.unique())","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:41.133250Z","iopub.execute_input":"2023-05-04T01:13:41.133670Z","iopub.status.idle":"2023-05-04T01:13:41.141558Z","shell.execute_reply.started":"2023-05-04T01:13:41.133634Z","shell.execute_reply":"2023-05-04T01:13:41.140495Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"missing_birds = list(set(list(df_train.primary_label.unique())).difference(list(df_valid.primary_label.unique())))","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:41.143272Z","iopub.execute_input":"2023-05-04T01:13:41.144146Z","iopub.status.idle":"2023-05-04T01:13:41.151989Z","shell.execute_reply.started":"2023-05-04T01:13:41.144111Z","shell.execute_reply":"2023-05-04T01:13:41.150945Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"non_missing_birds = list(set(list(df_train.primary_label.unique())).difference(missing_birds))","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:41.157172Z","iopub.execute_input":"2023-05-04T01:13:41.157458Z","iopub.status.idle":"2023-05-04T01:13:41.165201Z","shell.execute_reply.started":"2023-05-04T01:13:41.157433Z","shell.execute_reply":"2023-05-04T01:13:41.164210Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(non_missing_birds)","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:41.166624Z","iopub.execute_input":"2023-05-04T01:13:41.166888Z","iopub.status.idle":"2023-05-04T01:13:41.175329Z","shell.execute_reply.started":"2023-05-04T01:13:41.166858Z","shell.execute_reply":"2023-05-04T01:13:41.174019Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_valid[missing_birds] = 0\ndf_valid = df_valid[df_train.columns] ## Fix order","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:41.177029Z","iopub.execute_input":"2023-05-04T01:13:41.177802Z","iopub.status.idle":"2023-05-04T01:13:41.192426Z","shell.execute_reply.started":"2023-05-04T01:13:41.177766Z","shell.execute_reply":"2023-05-04T01:13:41.191531Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df_train.iloc[:,17:]","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:41.193932Z","iopub.execute_input":"2023-05-04T01:13:41.194352Z","iopub.status.idle":"2023-05-04T01:13:41.199616Z","shell.execute_reply.started":"2023-05-04T01:13:41.194314Z","shell.execute_reply":"2023-05-04T01:13:41.198437Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import albumentations as A\ndef get_train_transform():\n    return A.Compose([\n        A.HorizontalFlip(p=0.5),\n        A.OneOf([\n                A.Cutout(max_h_size=5, max_w_size=16),\n                A.CoarseDropout(max_holes=4),\n            ], p=0.5),\n    ])","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:41.201193Z","iopub.execute_input":"2023-05-04T01:13:41.202096Z","iopub.status.idle":"2023-05-04T01:13:41.208697Z","shell.execute_reply.started":"2023-05-04T01:13:41.202061Z","shell.execute_reply":"2023-05-04T01:13:41.207690Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class BirdDataset(torch.utils.data.Dataset):\n\n    def __init__(self, df, sr = Config.SR, duration = Config.DURATION, augmentations = None, train = True):\n\n        self.df = df\n        self.sr = sr \n        self.train = train\n        self.duration = duration\n        self.augmentations = augmentations\n        if train:\n            self.img_dir = Config.train_images\n        else:\n            self.img_dir = Config.valid_images\n\n    def __len__(self):\n        return len(self.df)\n\n    @staticmethod\n    def normalize(image):\n        image = image / 255.0\n        #image = torch.stack([image, image, image])\n        return image\n\n    def __getitem__(self, idx):\n\n        row = self.df.iloc[idx]\n        impath = self.img_dir + f\"{row.filename}.npy\"\n\n        image = np.load(str(impath))[:Config.MAX_READ_SAMPLES]\n        \n        ########## RANDOM SAMPLING ################\n        if self.train:\n            image = image[np.random.choice(len(image))]\n        else:\n            image = image[0]\n            \n        #####################################################################\n        \n        image = torch.tensor(image).float()\n\n        if self.augmentations:\n#             image = self.augmentations(image.unsqueeze(0)).squeeze()\n            image = self.augmentations(image)\n            \n        image.size()\n        \n        image = torch.stack([image, image, image])\n\n        image = self.normalize(image)\n\n\n        return image, torch.tensor(row[17:]).float()\n","metadata":{"papermill":{"duration":0.039034,"end_time":"2022-04-22T06:01:17.350173","exception":false,"start_time":"2022-04-22T06:01:17.311139","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-05-04T01:13:41.210194Z","iopub.execute_input":"2023-05-04T01:13:41.211094Z","iopub.status.idle":"2023-05-04T01:13:41.222885Z","shell.execute_reply.started":"2023-05-04T01:13:41.211058Z","shell.execute_reply":"2023-05-04T01:13:41.222097Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# augment","metadata":{}},{"cell_type":"code","source":"def time_mask(img, param):\n    time_max = img.shape[0]\n    t = random.randint(0, param)\n    t0 = random.randint(0, time_max - t)\n    mask = torch.ones_like(img, device=img.device)\n    mask[t0: t0 + t, :] = 0\n    return img * mask\n\ndef freq_mask(img, param):\n    freq_max = img.shape[1]\n    t = random.randint(0, param)\n    t0 = random.randint(0, freq_max - t)\n    mask = torch.ones_like(img, device=img.device)\n    mask[:, t0: t0 + t] = 0\n    return img * mask\n\ndef my_aug(img):\n    if random.random() < Config.mask_prob:\n        img = time_mask(img, Config.time_mask)\n        img = freq_mask(img, Config.freq_mask)\n    return img","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:41.224028Z","iopub.execute_input":"2023-05-04T01:13:41.225079Z","iopub.status.idle":"2023-05-04T01:13:41.233938Z","shell.execute_reply.started":"2023-05-04T01:13:41.225033Z","shell.execute_reply":"2023-05-04T01:13:41.233131Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_fold_dls(df_train, df_valid):\n\n    ds_train = BirdDataset(\n        df_train, \n        sr = Config.SR,\n        duration = Config.DURATION,\n        augmentations = my_aug,\n        train = True\n    )\n    ds_val = BirdDataset(\n        df_valid, \n        sr = Config.SR,\n        duration = Config.DURATION,\n        augmentations = None,\n        train = False\n    )\n    dl_train = DataLoader(ds_train, batch_size=Config.batch_size , shuffle=True, num_workers = 2)    \n    dl_val = DataLoader(ds_val, batch_size=Config.batch_size, num_workers = 2)\n    return dl_train, dl_val, ds_train, ds_val","metadata":{"papermill":{"duration":0.036289,"end_time":"2022-04-22T06:01:17.539606","exception":false,"start_time":"2022-04-22T06:01:17.503317","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-05-04T01:13:41.235228Z","iopub.execute_input":"2023-05-04T01:13:41.236143Z","iopub.status.idle":"2023-05-04T01:13:41.245166Z","shell.execute_reply.started":"2023-05-04T01:13:41.236103Z","shell.execute_reply":"2023-05-04T01:13:41.244461Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def show_batch(img_ds, num_items, num_rows, num_cols, predict_arr=None):\n    fig = plt.figure(figsize=(12, 6))    \n    img_index = np.random.randint(0, len(img_ds)-1, num_items)\n    for index, img_index in enumerate(img_index):  # list first 9 images\n        img, lb = img_ds[img_index]        \n        ax = fig.add_subplot(num_rows, num_cols, index + 1, xticks=[], yticks=[])\n        if isinstance(img, torch.Tensor):\n            img = img.detach().numpy()\n        if isinstance(img, np.ndarray):\n            img = img.transpose(1, 2, 0)\n            ax.imshow(img)        \n            \n        title = f\"Spec\"\n        ax.set_title(title)  ","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:41.246379Z","iopub.execute_input":"2023-05-04T01:13:41.247339Z","iopub.status.idle":"2023-05-04T01:13:41.256036Z","shell.execute_reply.started":"2023-05-04T01:13:41.247302Z","shell.execute_reply":"2023-05-04T01:13:41.255095Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dl_train, dl_val, ds_train, ds_val = get_fold_dls(df_train, df_valid)\nshow_batch(ds_val, 8, 2, 4)\n# print(ds_train[2][0].shape)","metadata":{"papermill":{"duration":0.584852,"end_time":"2022-04-22T06:01:18.338238","exception":false,"start_time":"2022-04-22T06:01:17.753386","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-05-04T01:13:41.257571Z","iopub.execute_input":"2023-05-04T01:13:41.258538Z","iopub.status.idle":"2023-05-04T01:13:41.770043Z","shell.execute_reply.started":"2023-05-04T01:13:41.258368Z","shell.execute_reply":"2023-05-04T01:13:41.769122Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from torch.optim.lr_scheduler import CosineAnnealingLR, CosineAnnealingWarmRestarts, ReduceLROnPlateau, OneCycleLR\n\ndef get_optimizer(lr, params):\n    model_optimizer = torch.optim.Adam(\n            filter(lambda p: p.requires_grad, params), \n            lr=lr,\n            weight_decay=Config.weight_decay\n        )\n    interval = \"epoch\"\n    \n    lr_scheduler = CosineAnnealingWarmRestarts(\n                            model_optimizer, \n                            T_0=Config.epochs, \n                            T_mult=1, \n                            eta_min=1e-6, \n                            last_epoch=-1\n                        )\n\n    return {\n        \"optimizer\": model_optimizer, \n        \"lr_scheduler\": {\n            \"scheduler\": lr_scheduler,\n            \"interval\": interval,\n            \"monitor\": \"val_loss\",\n            \"frequency\": 1\n        }\n    }","metadata":{"papermill":{"duration":0.048043,"end_time":"2022-04-22T06:01:22.109544","exception":false,"start_time":"2022-04-22T06:01:22.061501","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-05-04T01:13:41.771754Z","iopub.execute_input":"2023-05-04T01:13:41.772400Z","iopub.status.idle":"2023-05-04T01:13:41.780812Z","shell.execute_reply.started":"2023-05-04T01:13:41.772363Z","shell.execute_reply":"2023-05-04T01:13:41.779568Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from torchtoolbox.tools import mixup_data, mixup_criterion\nimport torch.nn as nn\nfrom torch.nn.functional import cross_entropy\nimport torchmetrics\nimport timm","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:41.783409Z","iopub.execute_input":"2023-05-04T01:13:41.783880Z","iopub.status.idle":"2023-05-04T01:13:42.013381Z","shell.execute_reply.started":"2023-05-04T01:13:41.783843Z","shell.execute_reply":"2023-05-04T01:13:42.012354Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import sklearn.metrics\n\ndef padded_cmap(solution, submission, padding_factor=5):\n    solution = solution#.drop(['row_id'], axis=1, errors='ignore')\n    submission = submission#.drop(['row_id'], axis=1, errors='ignore')\n    new_rows = []\n    for i in range(padding_factor):\n        new_rows.append([1 for i in range(len(solution.columns))])\n    new_rows = pd.DataFrame(new_rows)\n    new_rows.columns = solution.columns\n    padded_solution = pd.concat([solution, new_rows]).reset_index(drop=True).copy()\n    padded_submission = pd.concat([submission, new_rows]).reset_index(drop=True).copy()\n    score = sklearn.metrics.average_precision_score(\n        padded_solution.values,\n        padded_submission.values,\n        average='macro',\n    )\n    return score\n\ndef map_score(solution, submission):\n    solution = solution#.drop(['row_id'], axis=1, errors='ignore')\n    submission = submission#.drop(['row_id'], axis=1, errors='ignore')\n    score = sklearn.metrics.average_precision_score(\n        solution.values,\n        submission.values,\n        average='micro',\n    )\n    return score","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:42.015155Z","iopub.execute_input":"2023-05-04T01:13:42.015562Z","iopub.status.idle":"2023-05-04T01:13:42.024359Z","shell.execute_reply.started":"2023-05-04T01:13:42.015514Z","shell.execute_reply":"2023-05-04T01:13:42.023186Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dummy = df_valid[birds].copy()\ndummy[birds] = np.random.rand(dummy.shape[0],dummy.shape[1])","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:42.027907Z","iopub.execute_input":"2023-05-04T01:13:42.030704Z","iopub.status.idle":"2023-05-04T01:13:42.159749Z","shell.execute_reply.started":"2023-05-04T01:13:42.030533Z","shell.execute_reply":"2023-05-04T01:13:42.158232Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"padded_cmap(df_valid[birds], dummy[birds], padding_factor = 5)","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:42.161558Z","iopub.execute_input":"2023-05-04T01:13:42.162355Z","iopub.status.idle":"2023-05-04T01:13:43.143870Z","shell.execute_reply.started":"2023-05-04T01:13:42.162309Z","shell.execute_reply":"2023-05-04T01:13:43.142675Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"padded_cmap(df_valid[birds], dummy[birds], padding_factor = 1)","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:43.145580Z","iopub.execute_input":"2023-05-04T01:13:43.146045Z","iopub.status.idle":"2023-05-04T01:13:43.831366Z","shell.execute_reply.started":"2023-05-04T01:13:43.146005Z","shell.execute_reply":"2023-05-04T01:13:43.830227Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"map_score(df_valid[birds], dummy[birds])","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:43.833018Z","iopub.execute_input":"2023-05-04T01:13:43.833505Z","iopub.status.idle":"2023-05-04T01:13:44.091935Z","shell.execute_reply.started":"2023-05-04T01:13:43.833467Z","shell.execute_reply":"2023-05-04T01:13:44.089708Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class BirdClefModel(pl.LightningModule):\n    def __init__(self, model_name=Config.model, num_classes = Config.num_classes, pretrained = Config.pretrained):\n        super().__init__()\n        self.num_classes = num_classes\n\n        self.backbone = timm.create_model(model_name, pretrained=pretrained)\n\n        if 'res' in model_name:\n            self.in_features = self.backbone.fc.in_features\n            self.backbone.fc = nn.Linear(self.in_features, num_classes)\n        elif 'dense' in model_name:\n            self.in_features = self.backbone.classifier.in_features\n            self.backbone.classifier = nn.Linear(self.in_features, num_classes)\n        elif 'efficientnet' in model_name:\n            self.in_features = self.backbone.classifier.in_features\n            self.backbone.classifier = nn.Sequential(\n                nn.Linear(self.in_features, num_classes)\n            )\n        \n        self.loss_function = nn.BCEWithLogitsLoss() \n\n    def forward(self,images):\n        logits = self.backbone(images)\n        return logits\n        \n    def configure_optimizers(self):\n        return get_optimizer(lr=Config.LR, params=self.parameters())\n\n    def train_with_mixup(self, X, y):\n        X, y_a, y_b, lam = mixup_data(X, y, alpha=Config.mixup_alpha)\n        y_pred = self(X)\n        loss_mixup = mixup_criterion(cross_entropy, y_pred, y_a, y_b, lam)\n        return loss_mixup\n\n    def training_step(self, batch, batch_idx):\n        image, target = batch        \n        if Config.use_mixup:\n            loss = self.train_with_mixup(image, target)\n        else:\n            y_pred = self(image)\n            loss = self.loss_function(y_pred,target)\n\n        self.log(\"train_loss\", loss, on_step=True, on_epoch=True, prog_bar=True)\n        return loss        \n\n    def validation_step(self, batch, batch_idx):\n        image, target = batch     \n        y_pred = self(image)\n        val_loss = self.loss_function(y_pred, target)\n        self.log(\"val_loss\", val_loss, on_step=True, on_epoch=True, logger=True, prog_bar=True)\n        \n        return {\"val_loss\": val_loss, \"logits\": y_pred, \"targets\": target}\n    \n    def train_dataloader(self):\n        return self._train_dataloader \n    \n    def validation_dataloader(self):\n        return self._validation_dataloader\n    \n    def validation_epoch_end(self,outputs):\n        avg_loss = torch.stack([x['val_loss'] for x in outputs]).mean()\n        output_val = torch.cat([x['logits'] for x in outputs],dim=0).sigmoid().cpu().detach().numpy()\n        target_val = torch.cat([x['targets'] for x in outputs],dim=0).cpu().detach().numpy()\n        \n        # print(output_val.shape)\n        val_df = pd.DataFrame(target_val, columns = birds)\n        pred_df = pd.DataFrame(output_val, columns = birds)\n        \n        avg_score = padded_cmap(val_df, pred_df, padding_factor = 5)\n        avg_score2 = padded_cmap(val_df, pred_df, padding_factor = 3)\n        avg_score3 = sklearn.metrics.label_ranking_average_precision_score(target_val,output_val)\n        \n#         competition_metrics(output_val,target_val)\n        print(f'epoch {self.current_epoch} validation loss {avg_loss}')\n        print(f'epoch {self.current_epoch} validation C-MAP score pad 5 {avg_score}')\n        print(f'epoch {self.current_epoch} validation C-MAP score pad 3 {avg_score2}')\n        print(f'epoch {self.current_epoch} validation AP score {avg_score3}')\n        \n        \n        val_df.to_pickle('val_df.pkl')\n        pred_df.to_pickle('pred_df.pkl')\n        \n        \n        return {'val_loss': avg_loss,'val_cmap':avg_score}\n    \n    \n    \n    ","metadata":{"papermill":{"duration":0.156714,"end_time":"2022-04-22T06:01:22.301564","exception":false,"start_time":"2022-04-22T06:01:22.14485","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-05-04T01:13:44.094132Z","iopub.execute_input":"2023-05-04T01:13:44.094617Z","iopub.status.idle":"2023-05-04T01:13:44.113647Z","shell.execute_reply.started":"2023-05-04T01:13:44.094577Z","shell.execute_reply":"2023-05-04T01:13:44.112389Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from pytorch_lightning.loggers import WandbLogger\nimport gc\n\ndef run_training():\n    print(f\"Running training...\")\n    logger = None\n    \n    \n    dl_train, dl_val, ds_train, ds_val = get_fold_dls(df_train, df_valid)\n    \n    audio_model = BirdClefModel()\n\n    early_stop_callback = EarlyStopping(monitor=\"val_loss\", min_delta=0.00, patience=Config.PATIENCE, verbose= True, mode=\"min\")\n    checkpoint_callback = ModelCheckpoint(monitor='val_loss',\n                                          dirpath= \"/kaggle/working/exp1/\",\n                                      save_top_k=1,\n                                      save_last= True,\n                                      save_weights_only=True,\n                                      filename= f'./{Config.model}_loss',\n                                      verbose= True,\n                                      mode='min')\n    \n    callbacks_to_use = [checkpoint_callback,early_stop_callback]\n\n\n    trainer = pl.Trainer(\n        gpus=1,\n        val_check_interval=0.5,\n        deterministic=True,\n        max_epochs=Config.epochs,\n        logger=logger,\n        auto_lr_find=False,    \n        callbacks=callbacks_to_use,\n        precision=Config.PRECISION, accelerator=\"gpu\" \n    )\n\n    print(\"Running trainer.fit\")\n    trainer.fit(audio_model, train_dataloaders = dl_train, val_dataloaders = dl_val)                \n\n    gc.collect()\n    torch.cuda.empty_cache()\n","metadata":{"papermill":{"duration":0.052364,"end_time":"2022-04-22T06:01:22.708806","exception":false,"start_time":"2022-04-22T06:01:22.656442","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2023-05-04T01:13:44.120433Z","iopub.execute_input":"2023-05-04T01:13:44.120987Z","iopub.status.idle":"2023-05-04T01:13:44.130708Z","shell.execute_reply.started":"2023-05-04T01:13:44.120958Z","shell.execute_reply":"2023-05-04T01:13:44.129296Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"run_training()","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:13:44.131860Z","iopub.execute_input":"2023-05-04T01:13:44.132149Z","iopub.status.idle":"2023-05-04T01:23:20.176627Z","shell.execute_reply.started":"2023-05-04T01:13:44.132123Z","shell.execute_reply":"2023-05-04T01:23:20.175462Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pred = pd.read_pickle('/kaggle/working/pred_df.pkl')\ntrue = pd.read_pickle('/kaggle/working/val_df.pkl')","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:23:20.178519Z","iopub.execute_input":"2023-05-04T01:23:20.178871Z","iopub.status.idle":"2023-05-04T01:23:20.195692Z","shell.execute_reply.started":"2023-05-04T01:23:20.178835Z","shell.execute_reply":"2023-05-04T01:23:20.194728Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"true.sum(axis=1)","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:23:20.197308Z","iopub.execute_input":"2023-05-04T01:23:20.197723Z","iopub.status.idle":"2023-05-04T01:23:20.212121Z","shell.execute_reply.started":"2023-05-04T01:23:20.197685Z","shell.execute_reply":"2023-05-04T01:23:20.211227Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pred.sum(axis=1)","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:23:20.213520Z","iopub.execute_input":"2023-05-04T01:23:20.214021Z","iopub.status.idle":"2023-05-04T01:23:20.231637Z","shell.execute_reply.started":"2023-05-04T01:23:20.213981Z","shell.execute_reply":"2023-05-04T01:23:20.230241Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"padded_cmap(true, pred, padding_factor = 5)\n","metadata":{"execution":{"iopub.status.busy":"2023-05-04T01:23:20.233091Z","iopub.execute_input":"2023-05-04T01:23:20.233543Z","iopub.status.idle":"2023-05-04T01:23:21.189731Z","shell.execute_reply.started":"2023-05-04T01:23:20.233503Z","shell.execute_reply":"2023-05-04T01:23:21.188527Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}