{"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\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":"2023-04-17T11:38:35.900686Z","iopub.execute_input":"2023-04-17T11:38:35.901943Z","iopub.status.idle":"2023-04-17T11:38:49.074287Z","shell.execute_reply.started":"2023-04-17T11:38:35.901904Z","shell.execute_reply":"2023-04-17T11:38:49.073251Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from pytorch_lightning.callbacks import ModelCheckpoint, BackboneFinetuning, EarlyStopping\n","metadata":{"execution":{"iopub.status.busy":"2023-04-17T11:38:49.076732Z","iopub.execute_input":"2023-04-17T11:38:49.077731Z","iopub.status.idle":"2023-04-17T11:38:49.085477Z","shell.execute_reply.started":"2023-04-17T11:38:49.077702Z","shell.execute_reply":"2023-04-17T11:38:49.084510Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install -q torchtoolbox timm","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":"2023-04-17T11:38:49.086845Z","iopub.execute_input":"2023-04-17T11:38:49.087997Z","iopub.status.idle":"2023-04-17T11:38:59.666637Z","shell.execute_reply.started":"2023-04-17T11:38:49.087960Z","shell.execute_reply":"2023-04-17T11:38:59.665423Z"},"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 = 20\n    PRECISION = 16    \n    PATIENCE = 8    \n    seed = 64\n    model = \"tf_efficientnet_b1_ns\"\n    pretrained = True            \n    weight_decay = 1e-3\n    use_mixup = True\n    mixup_alpha = 0.6\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    \n    SR = 32000\n    DURATION = 5\n    MAX_READ_SAMPLES = 5\n    LR = 10e-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":"2023-04-17T11:38:59.669580Z","iopub.execute_input":"2023-04-17T11:38:59.669971Z","iopub.status.idle":"2023-04-17T11:38:59.734477Z","shell.execute_reply.started":"2023-04-17T11:38:59.669927Z","shell.execute_reply":"2023-04-17T11:38:59.733418Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pl.seed_everything(Config.seed, workers=True)","metadata":{"execution":{"iopub.status.busy":"2023-04-17T11:38:59.738046Z","iopub.execute_input":"2023-04-17T11:38:59.738391Z","iopub.status.idle":"2023-04-17T11:38:59.755506Z","shell.execute_reply.started":"2023-04-17T11:38:59.738364Z","shell.execute_reply":"2023-04-17T11:38:59.754403Z"},"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":"2023-04-17T11:38:59.758139Z","iopub.execute_input":"2023-04-17T11:38:59.758841Z","iopub.status.idle":"2023-04-17T11:38:59.764844Z","shell.execute_reply.started":"2023-04-17T11:38:59.758805Z","shell.execute_reply":"2023-04-17T11:38:59.763870Z"},"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":"2023-04-17T11:38:59.767135Z","iopub.execute_input":"2023-04-17T11:38:59.767924Z","iopub.status.idle":"2023-04-17T11:38:59.958086Z","shell.execute_reply.started":"2023-04-17T11:38:59.767888Z","shell.execute_reply":"2023-04-17T11:38:59.956966Z"},"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":"2023-04-17T11:38:59.959485Z","iopub.execute_input":"2023-04-17T11:38:59.960343Z","iopub.status.idle":"2023-04-17T11:38:59.970336Z","shell.execute_reply.started":"2023-04-17T11:38:59.960304Z","shell.execute_reply":"2023-04-17T11:38:59.969349Z"},"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":"2023-04-17T11:38:59.971668Z","iopub.execute_input":"2023-04-17T11:38:59.972248Z","iopub.status.idle":"2023-04-17T11:38:59.998451Z","shell.execute_reply.started":"2023-04-17T11:38:59.972210Z","shell.execute_reply":"2023-04-17T11:38:59.997494Z"},"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":"2023-04-17T11:39:00.000398Z","iopub.execute_input":"2023-04-17T11:39:00.000786Z","iopub.status.idle":"2023-04-17T11:39:00.008495Z","shell.execute_reply.started":"2023-04-17T11:39:00.000751Z","shell.execute_reply":"2023-04-17T11:39:00.006922Z"},"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":"2023-04-17T11:39:00.010225Z","iopub.execute_input":"2023-04-17T11:39:00.010675Z","iopub.status.idle":"2023-04-17T11:39:00.018494Z","shell.execute_reply.started":"2023-04-17T11:39:00.010634Z","shell.execute_reply":"2023-04-17T11:39:00.017305Z"},"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":"2023-04-17T11:39:00.020456Z","iopub.execute_input":"2023-04-17T11:39:00.020805Z","iopub.status.idle":"2023-04-17T11:39:00.030214Z","shell.execute_reply.started":"2023-04-17T11:39:00.020771Z","shell.execute_reply":"2023-04-17T11:39:00.028945Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(non_missing_birds)","metadata":{"execution":{"iopub.status.busy":"2023-04-17T11:39:00.032341Z","iopub.execute_input":"2023-04-17T11:39:00.032746Z","iopub.status.idle":"2023-04-17T11:39:00.040810Z","shell.execute_reply.started":"2023-04-17T11:39:00.032710Z","shell.execute_reply":"2023-04-17T11:39:00.039604Z"},"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":"2023-04-17T11:39:00.047036Z","iopub.execute_input":"2023-04-17T11:39:00.047334Z","iopub.status.idle":"2023-04-17T11:39:00.063228Z","shell.execute_reply.started":"2023-04-17T11:39:00.047309Z","shell.execute_reply":"2023-04-17T11:39:00.062094Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df_train.iloc[:,17:]","metadata":{"execution":{"iopub.status.busy":"2023-04-17T11:39:00.064470Z","iopub.execute_input":"2023-04-17T11:39:00.064892Z","iopub.status.idle":"2023-04-17T11:39:00.069766Z","shell.execute_reply.started":"2023-04-17T11:39:00.064851Z","shell.execute_reply":"2023-04-17T11:39:00.068714Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import albumentations as A\nfrom torchtoolbox.transform import Cutout\ndef get_train_transform():\n    return A.Compose([\n        Cutout()\n    ])","metadata":{"execution":{"iopub.status.busy":"2023-04-17T11:39:00.071490Z","iopub.execute_input":"2023-04-17T11:39:00.072337Z","iopub.status.idle":"2023-04-17T11:39:00.091895Z","shell.execute_reply.started":"2023-04-17T11:39:00.072299Z","shell.execute_reply":"2023-04-17T11:39:00.090394Z"},"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            \n        image.size()\n        \n        image = torch.stack([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":"2023-04-17T11:39:00.093574Z","iopub.execute_input":"2023-04-17T11:39:00.093960Z","iopub.status.idle":"2023-04-17T11:39:00.105580Z","shell.execute_reply.started":"2023-04-17T11:39:00.093922Z","shell.execute_reply":"2023-04-17T11:39:00.104277Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_fold_dls(df_train, df_valid, aug=None):\n\n    ds_train = BirdDataset(\n        df_train, \n        sr = Config.SR,\n        duration = Config.DURATION,\n        augmentations = 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 = 0)    \n    dl_val = DataLoader(ds_val, batch_size=Config.batch_size, num_workers = 0)\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":"2023-04-17T11:39:00.107475Z","iopub.execute_input":"2023-04-17T11:39:00.107874Z","iopub.status.idle":"2023-04-17T11:39:00.116145Z","shell.execute_reply.started":"2023-04-17T11:39:00.107836Z","shell.execute_reply":"2023-04-17T11:39:00.114847Z"},"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":"2023-04-17T11:39:00.117986Z","iopub.execute_input":"2023-04-17T11:39:00.119522Z","iopub.status.idle":"2023-04-17T11:39:00.128961Z","shell.execute_reply.started":"2023-04-17T11:39:00.119389Z","shell.execute_reply":"2023-04-17T11:39:00.127506Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"aug = get_train_transform()\ndl_train, dl_val, ds_train, ds_val = get_fold_dls(df_train, df_valid)\nshow_batch(ds_val, 8, 2, 4)","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":"2023-04-17T11:39:00.130828Z","iopub.execute_input":"2023-04-17T11:39:00.131635Z","iopub.status.idle":"2023-04-17T11:39:00.865782Z","shell.execute_reply.started":"2023-04-17T11:39:00.131597Z","shell.execute_reply":"2023-04-17T11:39:00.864834Z"},"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.AdamW(\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":"2023-04-17T11:39:00.866871Z","iopub.execute_input":"2023-04-17T11:39:00.867229Z","iopub.status.idle":"2023-04-17T11:39:00.876445Z","shell.execute_reply.started":"2023-04-17T11:39:00.867178Z","shell.execute_reply":"2023-04-17T11:39:00.875201Z"},"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":"2023-04-17T11:39:00.878593Z","iopub.execute_input":"2023-04-17T11:39:00.879515Z","iopub.status.idle":"2023-04-17T11:39:01.101890Z","shell.execute_reply.started":"2023-04-17T11:39:00.879476Z","shell.execute_reply":"2023-04-17T11:39:01.100833Z"},"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":"2023-04-17T11:39:01.103706Z","iopub.execute_input":"2023-04-17T11:39:01.104133Z","iopub.status.idle":"2023-04-17T11:39:01.113325Z","shell.execute_reply.started":"2023-04-17T11:39:01.104093Z","shell.execute_reply":"2023-04-17T11:39:01.112213Z"},"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":"2023-04-17T11:39:01.114934Z","iopub.execute_input":"2023-04-17T11:39:01.115884Z","iopub.status.idle":"2023-04-17T11:39:01.184500Z","shell.execute_reply.started":"2023-04-17T11:39:01.115846Z","shell.execute_reply":"2023-04-17T11:39:01.183493Z"},"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":"2023-04-17T11:39:01.185946Z","iopub.execute_input":"2023-04-17T11:39:01.186423Z","iopub.status.idle":"2023-04-17T11:39:02.153864Z","shell.execute_reply.started":"2023-04-17T11:39:01.186387Z","shell.execute_reply":"2023-04-17T11:39:02.152879Z"},"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":"2023-04-17T11:39:02.155561Z","iopub.execute_input":"2023-04-17T11:39:02.155952Z","iopub.status.idle":"2023-04-17T11:39:02.832083Z","shell.execute_reply.started":"2023-04-17T11:39:02.155914Z","shell.execute_reply":"2023-04-17T11:39:02.830945Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"map_score(df_valid[birds], dummy[birds])","metadata":{"execution":{"iopub.status.busy":"2023-04-17T11:39:02.833655Z","iopub.execute_input":"2023-04-17T11:39:02.834633Z","iopub.status.idle":"2023-04-17T11:39:03.063398Z","shell.execute_reply.started":"2023-04-17T11:39:02.834601Z","shell.execute_reply":"2023-04-17T11:39:03.062417Z"},"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, in_chans=1)\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":"2023-04-17T11:40:13.303440Z","iopub.execute_input":"2023-04-17T11:40:13.303981Z","iopub.status.idle":"2023-04-17T11:40:13.323626Z","shell.execute_reply.started":"2023-04-17T11:40:13.303945Z","shell.execute_reply":"2023-04-17T11:40:13.322315Z"},"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":"2023-04-17T11:40:13.811014Z","iopub.execute_input":"2023-04-17T11:40:13.811787Z","iopub.status.idle":"2023-04-17T11:40:13.820626Z","shell.execute_reply.started":"2023-04-17T11:40:13.811734Z","shell.execute_reply":"2023-04-17T11:40:13.819465Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"run_training()","metadata":{"execution":{"iopub.status.busy":"2023-04-17T11:40:14.058898Z","iopub.execute_input":"2023-04-17T11:40:14.059234Z"},"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":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"true.sum(axis=1)","metadata":{"execution":{"iopub.status.busy":"2023-04-17T11:39:12.924621Z","iopub.status.idle":"2023-04-17T11:39:12.925482Z","shell.execute_reply.started":"2023-04-17T11:39:12.925231Z","shell.execute_reply":"2023-04-17T11:39:12.925258Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pred.sum(axis=1)","metadata":{"execution":{"iopub.status.busy":"2023-04-17T11:39:12.927232Z","iopub.status.idle":"2023-04-17T11:39:12.928053Z","shell.execute_reply.started":"2023-04-17T11:39:12.927770Z","shell.execute_reply":"2023-04-17T11:39:12.927799Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"padded_cmap(true, pred, padding_factor = 5)","metadata":{"execution":{"iopub.status.busy":"2023-04-17T11:39:12.930090Z","iopub.status.idle":"2023-04-17T11:39:12.930583Z","shell.execute_reply.started":"2023-04-17T11:39:12.930329Z","shell.execute_reply":"2023-04-17T11:39:12.930356Z"},"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":[]}]}