{"cells":[{"metadata":{},"cell_type":"markdown","source":"## Dependencies"},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install ../input/timm-pytorch-image-models/pytorch-image-models-master/\n!pip install ../input/torchlibrosa/torchlibrosa-0.0.5-py3-none-any.whl","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Libraries"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import cv2\nimport audioread\nimport logging\nimport os\nimport random\nimport time\nimport warnings\n\nimport librosa\nimport numpy as np\nimport pandas as pd\nimport soundfile as sf\nimport timm\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nimport torch.utils.data as torchdata\n\nfrom contextlib import contextmanager\nfrom pathlib import Path\nfrom typing import Optional\n\nfrom albumentations.core.transforms_interface import ImageOnlyTransform\nfrom torchlibrosa.stft import LogmelFilterBank, Spectrogram\nfrom torchlibrosa.augmentation import SpecAugmentation\nfrom tqdm import tqdm","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Utilities"},{"metadata":{"trusted":true},"cell_type":"code","source":"def set_seed(seed: int = 42):\n    random.seed(seed)\n    np.random.seed(seed)\n    os.environ[\"PYTHONHASHSEED\"] = str(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed(seed)  # type: ignore\n    torch.backends.cudnn.deterministic = True  # type: ignore\n    torch.backends.cudnn.benchmark = True  # type: ignore\n    \n    \ndef get_logger(out_file=None):\n    logger = logging.getLogger()\n    formatter = logging.Formatter(\"%(asctime)s - %(levelname)s - %(message)s\")\n    logger.handlers = []\n    logger.setLevel(logging.INFO)\n\n    handler = logging.StreamHandler()\n    handler.setFormatter(formatter)\n    handler.setLevel(logging.INFO)\n    logger.addHandler(handler)\n\n    if out_file is not None:\n        fh = logging.FileHandler(out_file)\n        fh.setFormatter(formatter)\n        fh.setLevel(logging.INFO)\n        logger.addHandler(fh)\n    logger.info(\"logger set up\")\n    return logger\n    \n    \n@contextmanager\ndef timer(name: str, logger: Optional[logging.Logger] = None):\n    t0 = time.time()\n    msg = f\"[{name}] start\"\n    if logger is None:\n        print(msg)\n    else:\n        logger.info(msg)\n    yield\n\n    msg = f\"[{name}] done in {time.time() - t0:.2f} s\"\n    if logger is None:\n        print(msg)\n    else:\n        logger.info(msg)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"logger = get_logger(\"main.log\")\nset_seed(1213)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Config"},{"metadata":{"trusted":true},"cell_type":"code","source":"class CFG:\n    ######################\n    # Globals #\n    ######################\n    seed = 1213\n    epochs = 35\n    train = True\n    folds = [0]\n    img_size = 224\n    main_metric = \"epoch_f1_at_05\"\n    minimize_metric = False\n\n    ######################\n    # Data #\n    ######################\n    train_datadir = Path(\"../input/birdclef-2021/train_short_audio\")\n    train_csv = \"../input/birdclef-2021/train_metadata.csv\"\n    train_soundscape = \"../input/birdclef-2021/train_soundscape_labels.csv\"\n\n    ######################\n    # Dataset #\n    ######################\n    transforms = {\n        \"train\": [{\"name\": \"Normalize\"}],\n        \"valid\": [{\"name\": \"Normalize\"}],\n        \"test\": [{\"name\": \"Normalize\"}]\n    }\n    period = 20\n    n_mels = 128\n    fmin = 20\n    fmax = 16000\n    n_fft = 2048\n    hop_length = 512\n    sample_rate = 32000\n    melspectrogram_parameters = {\n        \"n_mels\": 224,\n        \"fmin\": 20,\n        \"fmax\": 16000\n    }\n\n    target_columns = [\n        'acafly', 'acowoo', 'aldfly', 'ameavo', 'amecro',\n        'amegfi', 'amekes', 'amepip', 'amered', 'amerob',\n        'amewig', 'amtspa', 'andsol1', 'annhum', 'astfly',\n        'azaspi1', 'babwar', 'baleag', 'balori', 'banana',\n        'banswa', 'banwre1', 'barant1', 'barswa', 'batpig1',\n        'bawswa1', 'bawwar', 'baywre1', 'bbwduc', 'bcnher',\n        'belkin1', 'belvir', 'bewwre', 'bkbmag1', 'bkbplo',\n        'bkbwar', 'bkcchi', 'bkhgro', 'bkmtou1', 'bknsti', 'blbgra1',\n        'blbthr1', 'blcjay1', 'blctan1', 'blhpar1', 'blkpho',\n        'blsspa1', 'blugrb1', 'blujay', 'bncfly', 'bnhcow', 'bobfly1',\n        'bongul', 'botgra', 'brbmot1', 'brbsol1', 'brcvir1', 'brebla',\n        'brncre', 'brnjay', 'brnthr', 'brratt1', 'brwhaw', 'brwpar1',\n        'btbwar', 'btnwar', 'btywar', 'bucmot2', 'buggna', 'bugtan',\n        'buhvir', 'bulori', 'burwar1', 'bushti', 'butsal1', 'buwtea',\n        'cacgoo1', 'cacwre', 'calqua', 'caltow', 'cangoo', 'canwar',\n        'carchi', 'carwre', 'casfin', 'caskin', 'caster1', 'casvir',\n        'categr', 'ccbfin', 'cedwax', 'chbant1', 'chbchi', 'chbwre1',\n        'chcant2', 'chispa', 'chswar', 'cinfly2', 'clanut', 'clcrob',\n        'cliswa', 'cobtan1', 'cocwoo1', 'cogdov', 'colcha1', 'coltro1',\n        'comgol', 'comgra', 'comloo', 'commer', 'compau', 'compot1',\n        'comrav', 'comyel', 'coohaw', 'cotfly1', 'cowscj1', 'cregua1',\n        'creoro1', 'crfpar', 'cubthr', 'daejun', 'dowwoo', 'ducfly', 'dusfly',\n        'easblu', 'easkin', 'easmea', 'easpho', 'eastow', 'eawpew', 'eletro',\n        'eucdov', 'eursta', 'fepowl', 'fiespa', 'flrtan1', 'foxspa', 'gadwal',\n        'gamqua', 'gartro1', 'gbbgul', 'gbwwre1', 'gcrwar', 'gilwoo',\n        'gnttow', 'gnwtea', 'gocfly1', 'gockin', 'gocspa', 'goftyr1',\n        'gohque1', 'goowoo1', 'grasal1', 'grbani', 'grbher3', 'grcfly',\n        'greegr', 'grekis', 'grepew', 'grethr1', 'gretin1', 'greyel',\n        'grhcha1', 'grhowl', 'grnher', 'grnjay', 'grtgra', 'grycat',\n        'gryhaw2', 'gwfgoo', 'haiwoo', 'heptan', 'hergul', 'herthr',\n        'herwar', 'higmot1', 'hofwoo1', 'houfin', 'houspa', 'houwre',\n        'hutvir', 'incdov', 'indbun', 'kebtou1', 'killde', 'labwoo', 'larspa',\n        'laufal1', 'laugul', 'lazbun', 'leafly', 'leasan', 'lesgol', 'lesgre1',\n        'lesvio1', 'linspa', 'linwoo1', 'littin1', 'lobdow', 'lobgna5', 'logshr',\n        'lotduc', 'lotman1', 'lucwar', 'macwar', 'magwar', 'mallar3', 'marwre',\n        'mastro1', 'meapar', 'melbla1', 'monoro1', 'mouchi', 'moudov', 'mouela1',\n        'mouqua', 'mouwar', 'mutswa', 'naswar', 'norcar', 'norfli', 'normoc', 'norpar',\n        'norsho', 'norwat', 'nrwswa', 'nutwoo', 'oaktit', 'obnthr1', 'ocbfly1',\n        'oliwoo1', 'olsfly', 'orbeup1', 'orbspa1', 'orcpar', 'orcwar', 'orfpar',\n        'osprey', 'ovenbi1', 'pabspi1', 'paltan1', 'palwar', 'pasfly', 'pavpig2',\n        'phivir', 'pibgre', 'pilwoo', 'pinsis', 'pirfly1', 'plawre1', 'plaxen1',\n        'plsvir', 'plupig2', 'prowar', 'purfin', 'purgal2', 'putfru1', 'pygnut',\n        'rawwre1', 'rcatan1', 'rebnut', 'rebsap', 'rebwoo', 'redcro', 'reevir1',\n        'rehbar1', 'relpar', 'reshaw', 'rethaw', 'rewbla', 'ribgul', 'rinkin1',\n        'roahaw', 'robgro', 'rocpig', 'rotbec', 'royter1', 'rthhum', 'rtlhum',\n        'ruboro1', 'rubpep1', 'rubrob', 'rubwre1', 'ruckin', 'rucspa1', 'rucwar',\n        'rucwar1', 'rudpig', 'rudtur', 'rufhum', 'rugdov', 'rumfly1', 'runwre1',\n        'rutjac1', 'saffin', 'sancra', 'sander', 'savspa', 'saypho', 'scamac1',\n        'scatan', 'scbwre1', 'scptyr1', 'scrtan1', 'semplo', 'shicow', 'sibtan2',\n        'sinwre1', 'sltred', 'smbani', 'snogoo', 'sobtyr1', 'socfly1', 'solsan',\n        'sonspa', 'soulap1', 'sposan', 'spotow', 'spvear1', 'squcuc1', 'stbori',\n        'stejay', 'sthant1', 'sthwoo1', 'strcuc1', 'strfly1', 'strsal1', 'stvhum2',\n        'subfly', 'sumtan', 'swaspa', 'swathr', 'tenwar', 'thbeup1', 'thbkin',\n        'thswar1', 'towsol', 'treswa', 'trogna1', 'trokin', 'tromoc', 'tropar',\n        'tropew1', 'tuftit', 'tunswa', 'veery', 'verdin', 'vigswa', 'warvir',\n        'wbwwre1', 'webwoo1', 'wegspa1', 'wesant1', 'wesblu', 'weskin', 'wesmea',\n        'westan', 'wewpew', 'whbman1', 'whbnut', 'whcpar', 'whcsee1', 'whcspa',\n        'whevir', 'whfpar1', 'whimbr', 'whiwre1', 'whtdov', 'whtspa', 'whwbec1',\n        'whwdov', 'wilfly', 'willet1', 'wilsni1', 'wiltur', 'wlswar', 'wooduc',\n        'woothr', 'wrenti', 'y00475', 'yebcha', 'yebela1', 'yebfly', 'yebori1',\n        'yebsap', 'yebsee1', 'yefgra1', 'yegvir', 'yehbla', 'yehcar1', 'yelgro',\n        'yelwar', 'yeofly1', 'yerwar', 'yeteup1', 'yetvir']\n\n    ######################\n    # Loaders #\n    ######################\n    loader_params = {\n        \"train\": {\n            \"batch_size\": 64,\n            \"num_workers\": 20,\n            \"shuffle\": True\n        },\n        \"valid\": {\n            \"batch_size\": 64,\n            \"num_workers\": 20,\n            \"shuffle\": False\n        },\n        \"test\": {\n            \"batch_size\": 64,\n            \"num_workers\": 20,\n            \"shuffle\": False\n        }\n    }\n\n    ######################\n    # Split #\n    ######################\n    split = \"StratifiedKFold\"\n    split_params = {\n        \"n_splits\": 5,\n        \"shuffle\": True,\n        \"random_state\": 1213\n    }\n\n    ######################\n    # Model #\n    ######################\n    base_model_name = \"tf_efficientnet_b0_ns\"\n    pooling = \"max\"\n    pretrained = True\n    num_classes = 397\n    in_channels = 1\n\n    ######################\n    # Criterion #\n    ######################\n    loss_name = \"BCEFocal2WayLoss\"\n    loss_params: dict = {}\n\n    ######################\n    # Optimizer #\n    ######################\n    optimizer_name = \"Adam\"\n    base_optimizer = \"Adam\"\n    optimizer_params = {\n        \"lr\": 0.001\n    }\n    # For SAM optimizer\n    base_optimizer = \"Adam\"\n\n    ######################\n    # Scheduler #\n    ######################\n    scheduler_name = \"CosineAnnealingLR\"\n    scheduler_params = {\n        \"T_max\": 10\n    }","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Data Loading"},{"metadata":{"trusted":true},"cell_type":"code","source":"TARGET_SR = 32000\nTEST = (len(list(Path(\"../input/birdclef-2021/test_soundscapes/\").glob(\"*.ogg\"))) != 0)\nif TEST:\n    DATADIR = Path(\"../input/birdclef-2021/test_soundscapes/\")\nelse:\n    DATADIR = Path(\"../input/birdclef-2021/train_soundscapes/\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"all_audios = list(DATADIR.glob(\"*.ogg\"))\nall_audio_ids = [\"_\".join(audio_id.name.split(\"_\")[:2]) for audio_id in all_audios]\nsubmission_df = pd.DataFrame({\n    \"row_id\": all_audio_ids\n})\nsubmission_df","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Define Model"},{"metadata":{"trusted":true},"cell_type":"code","source":"def init_layer(layer):\n    nn.init.xavier_uniform_(layer.weight)\n\n    if hasattr(layer, \"bias\"):\n        if layer.bias is not None:\n            layer.bias.data.fill_(0.)\n\n\ndef init_bn(bn):\n    bn.bias.data.fill_(0.)\n    bn.weight.data.fill_(1.0)\n\n\ndef init_weights(model):\n    classname = model.__class__.__name__\n    if classname.find(\"Conv2d\") != -1:\n        nn.init.xavier_uniform_(model.weight, gain=np.sqrt(2))\n        model.bias.data.fill_(0)\n    elif classname.find(\"BatchNorm\") != -1:\n        model.weight.data.normal_(1.0, 0.02)\n        model.bias.data.fill_(0)\n    elif classname.find(\"GRU\") != -1:\n        for weight in model.parameters():\n            if len(weight.size()) > 1:\n                nn.init.orghogonal_(weight.data)\n    elif classname.find(\"Linear\") != -1:\n        model.weight.data.normal_(0, 0.01)\n        model.bias.data.zero_()\n\n\ndef do_mixup(x: torch.Tensor, mixup_lambda: torch.Tensor):\n    \"\"\"Mixup x of even indexes (0, 2, 4, ...) with x of odd indexes\n    (1, 3, 5, ...).\n    Args:\n      x: (batch_size * 2, ...)\n      mixup_lambda: (batch_size * 2,)\n    Returns:\n      out: (batch_size, ...)\n    \"\"\"\n    out = (x[0::2].transpose(0, -1) * mixup_lambda[0::2] +\n           x[1::2].transpose(0, -1) * mixup_lambda[1::2]).transpose(0, -1)\n    return out\n\n\nclass Mixup(object):\n    def __init__(self, mixup_alpha, random_seed=1234):\n        \"\"\"Mixup coefficient generator.\n        \"\"\"\n        self.mixup_alpha = mixup_alpha\n        self.random_state = np.random.RandomState(random_seed)\n\n    def get_lambda(self, batch_size):\n        \"\"\"Get mixup random coefficients.\n        Args:\n          batch_size: int\n        Returns:\n          mixup_lambdas: (batch_size,)\n        \"\"\"\n        mixup_lambdas = []\n        for n in range(0, batch_size, 2):\n            lam = self.random_state.beta(\n                self.mixup_alpha, self.mixup_alpha, 1)[0]\n            mixup_lambdas.append(lam)\n            mixup_lambdas.append(1. - lam)\n\n        return torch.from_numpy(np.array(mixup_lambdas, dtype=np.float32))\n\n\ndef interpolate(x: torch.Tensor, ratio: int):\n    \"\"\"Interpolate data in time domain. This is used to compensate the\n    resolution reduction in downsampling of a CNN.\n    Args:\n      x: (batch_size, time_steps, classes_num)\n      ratio: int, ratio to interpolate\n    Returns:\n      upsampled: (batch_size, time_steps * ratio, classes_num)\n    \"\"\"\n    (batch_size, time_steps, classes_num) = x.shape\n    upsampled = x[:, :, None, :].repeat(1, 1, ratio, 1)\n    upsampled = upsampled.reshape(batch_size, time_steps * ratio, classes_num)\n    return upsampled\n\n\ndef pad_framewise_output(framewise_output: torch.Tensor, frames_num: int):\n    \"\"\"Pad framewise_output to the same length as input frames. The pad value\n    is the same as the value of the last frame.\n    Args:\n      framewise_output: (batch_size, frames_num, classes_num)\n      frames_num: int, number of frames to pad\n    Outputs:\n      output: (batch_size, frames_num, classes_num)\n    \"\"\"\n    output = F.interpolate(\n        framewise_output.unsqueeze(1),\n        size=(frames_num, framewise_output.size(2)),\n        align_corners=True,\n        mode=\"bilinear\").squeeze(1)\n\n    return output\n\n\ndef gem(x: torch.Tensor, p=3, eps=1e-6):\n    return F.avg_pool2d(x.clamp(min=eps).pow(p), (x.size(-2), x.size(-1))).pow(1. / p)\n\n\nclass GeM(nn.Module):\n    def __init__(self, p=3, eps=1e-6):\n        super().__init__()\n        self.p = nn.Parameter(torch.ones(1) * p)\n        self.eps = eps\n\n    def forward(self, x):\n        return gem(x, p=self.p, eps=self.eps)\n\n    def __repr__(self):\n        return self.__class__.__name__ + f\"(p={self.p.data.tolist()[0]:.4f}, eps={self.eps})\"\n\n\nclass AttBlockV2(nn.Module):\n    def __init__(self,\n                 in_features: int,\n                 out_features: int,\n                 activation=\"linear\"):\n        super().__init__()\n\n        self.activation = activation\n        self.att = nn.Conv1d(\n            in_channels=in_features,\n            out_channels=out_features,\n            kernel_size=1,\n            stride=1,\n            padding=0,\n            bias=True)\n        self.cla = nn.Conv1d(\n            in_channels=in_features,\n            out_channels=out_features,\n            kernel_size=1,\n            stride=1,\n            padding=0,\n            bias=True)\n\n        self.init_weights()\n\n    def init_weights(self):\n        init_layer(self.att)\n        init_layer(self.cla)\n\n    def forward(self, x):\n        # x: (n_samples, n_in, n_time)\n        norm_att = torch.softmax(torch.tanh(self.att(x)), dim=-1)\n        cla = self.nonlinear_transform(self.cla(x))\n        x = torch.sum(norm_att * cla, dim=2)\n        return x, norm_att, cla\n\n    def nonlinear_transform(self, x):\n        if self.activation == 'linear':\n            return x\n        elif self.activation == 'sigmoid':\n            return torch.sigmoid(x)\n\n\nclass TimmSED(nn.Module):\n    def __init__(self, base_model_name: str, pretrained=False, num_classes=24, in_channels=1):\n        super().__init__()\n        # Spectrogram extractor\n        self.spectrogram_extractor = Spectrogram(n_fft=CFG.n_fft, hop_length=CFG.hop_length,\n                                                 win_length=CFG.n_fft, window=\"hann\", center=True, pad_mode=\"reflect\",\n                                                 freeze_parameters=True)\n\n        # Logmel feature extractor\n        self.logmel_extractor = LogmelFilterBank(sr=CFG.sample_rate, n_fft=CFG.n_fft,\n                                                 n_mels=CFG.n_mels, fmin=CFG.fmin, fmax=CFG.fmax, ref=1.0, amin=1e-10, top_db=None,\n                                                 freeze_parameters=True)\n\n        # Spec augmenter\n        self.spec_augmenter = SpecAugmentation(time_drop_width=64, time_stripes_num=2,\n                                               freq_drop_width=8, freq_stripes_num=2)\n\n        self.bn0 = nn.BatchNorm2d(CFG.n_mels)\n\n        base_model = timm.create_model(\n            base_model_name, pretrained=pretrained, in_chans=in_channels)\n        layers = list(base_model.children())[:-2]\n        self.encoder = nn.Sequential(*layers)\n\n        if hasattr(base_model, \"fc\"):\n            in_features = base_model.fc.in_features\n        else:\n            in_features = base_model.classifier.in_features\n        self.fc1 = nn.Linear(in_features, in_features, bias=True)\n        self.att_block = AttBlockV2(\n            in_features, num_classes, activation=\"sigmoid\")\n\n        self.init_weight()\n\n    def init_weight(self):\n        init_layer(self.fc1)\n        init_bn(self.bn0)\n\n    def forward(self, input):\n        # (batch_size, 1, time_steps, freq_bins)\n        x = self.spectrogram_extractor(input)\n        x = self.logmel_extractor(x)    # (batch_size, 1, time_steps, mel_bins)\n\n        frames_num = x.shape[2]\n\n        x = x.transpose(1, 3)\n        x = self.bn0(x)\n        x = x.transpose(1, 3)\n\n        if self.training:\n            x = self.spec_augmenter(x)\n\n        x = x.transpose(2, 3)\n        # (batch_size, channels, freq, frames)\n        x = self.encoder(x)\n\n        # (batch_size, channels, frames)\n        x = torch.mean(x, dim=2)\n\n        # channel smoothing\n        x1 = F.max_pool1d(x, kernel_size=3, stride=1, padding=1)\n        x2 = F.avg_pool1d(x, kernel_size=3, stride=1, padding=1)\n        x = x1 + x2\n\n        x = F.dropout(x, p=0.5, training=self.training)\n        x = x.transpose(1, 2)\n        x = F.relu_(self.fc1(x))\n        x = x.transpose(1, 2)\n        x = F.dropout(x, p=0.5, training=self.training)\n        (clipwise_output, norm_att, segmentwise_output) = self.att_block(x)\n        logit = torch.sum(norm_att * self.att_block.cla(x), dim=2)\n        segmentwise_logit = self.att_block.cla(x).transpose(1, 2)\n        segmentwise_output = segmentwise_output.transpose(1, 2)\n\n        interpolate_ratio = frames_num // segmentwise_output.size(1)\n\n        # Get framewise output\n        framewise_output = interpolate(segmentwise_output,\n                                       interpolate_ratio)\n        framewise_output = pad_framewise_output(framewise_output, frames_num)\n\n        framewise_logit = interpolate(segmentwise_logit, interpolate_ratio)\n        framewise_logit = pad_framewise_output(framewise_logit, frames_num)\n\n        output_dict = {\n            \"framewise_output\": framewise_output,\n            \"segmentwise_output\": segmentwise_output,\n            \"logit\": logit,\n            \"framewise_logit\": framewise_logit,\n            \"clipwise_output\": clipwise_output\n        }\n\n        return output_dict","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Dataset"},{"metadata":{"trusted":true},"cell_type":"code","source":"class TestDataset(torchdata.Dataset):\n    def __init__(self, df: pd.DataFrame, clip: np.ndarray,\n                 waveform_transforms=None):\n        self.df = df\n        self.clip = clip\n        self.waveform_transforms=waveform_transforms\n        \n    def __len__(self):\n        return len(self.df)\n    \n    def __getitem__(self, idx: int):\n        SR = 32000\n        sample = self.df.loc[idx, :]\n        row_id = sample.row_id\n\n        end_seconds = int(sample.seconds)\n        start_seconds = int(end_seconds - 5)\n\n        start_index = SR * start_seconds\n        end_index = SR * end_seconds\n\n        y = self.clip[start_index:end_index].astype(np.float32)\n\n        y = np.nan_to_num(y)\n\n        if self.waveform_transforms:\n            y = self.waveform_transforms(y)\n\n        y = np.nan_to_num(y)\n\n        return y, row_id","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_transforms(phase: str):\n    transforms = CFG.transforms\n    if transforms is None:\n        return None\n    else:\n        if transforms[phase] is None:\n            return None\n        trns_list = []\n        for trns_conf in transforms[phase]:\n            trns_name = trns_conf[\"name\"]\n            trns_params = {} if trns_conf.get(\"params\") is None else \\\n                trns_conf[\"params\"]\n            if globals().get(trns_name) is not None:\n                trns_cls = globals()[trns_name]\n                trns_list.append(trns_cls(**trns_params))\n\n        if len(trns_list) > 0:\n            return Compose(trns_list)\n        else:\n            return None\n\n\ndef get_waveform_transforms(config: dict, phase: str):\n    return get_transforms(config, phase)\n\n\ndef get_spectrogram_transforms(config: dict, phase: str):\n    transforms = config.get('spectrogram_transforms')\n    if transforms is None:\n        return None\n    else:\n        if transforms[phase] is None:\n            return None\n        trns_list = []\n        for trns_conf in transforms[phase]:\n            trns_name = trns_conf[\"name\"]\n            trns_params = {} if trns_conf.get(\"params\") is None else \\\n                trns_conf[\"params\"]\n            if hasattr(A, trns_name):\n                trns_cls = A.__getattribute__(trns_name)\n                trns_list.append(trns_cls(**trns_params))\n            else:\n                trns_cls = globals().get(trns_name)\n                if trns_cls is not None:\n                    trns_list.append(trns_cls(**trns_params))\n\n        if len(trns_list) > 0:\n            return A.Compose(trns_list, p=1.0)\n        else:\n            return None\n\n\nclass Normalize:\n    def __call__(self, y: np.ndarray):\n        max_vol = np.abs(y).max()\n        y_vol = y * 1 / max_vol\n        return np.asfortranarray(y_vol)\n\n\nclass NewNormalize:\n    def __call__(self, y: np.ndarray):\n        y_mm = y - y.mean()\n        return y_mm / y_mm.abs().max()\n\n\nclass Compose:\n    def __init__(self, transforms: list):\n        self.transforms = transforms\n\n    def __call__(self, y: np.ndarray):\n        for trns in self.transforms:\n            y = trns(y)\n        return y\n\n\nclass AudioTransform:\n    def __init__(self, always_apply=False, p=0.5):\n        self.always_apply = always_apply\n        self.p = p\n\n    def __call__(self, y: np.ndarray):\n        if self.always_apply:\n            return self.apply(y)\n        else:\n            if np.random.rand() < self.p:\n                return self.apply(y)\n            else:\n                return y\n\n    def apply(self, y: np.ndarray):\n        raise NotImplementedError\n\n\nclass NoiseInjection(AudioTransform):\n    def __init__(self, always_apply=False, p=0.5, max_noise_level=0.5, sr=32000):\n        super().__init__(always_apply, p)\n\n        self.noise_level = (0.0, max_noise_level)\n        self.sr = sr\n\n    def apply(self, y: np.ndarray, **params):\n        noise_level = np.random.uniform(*self.noise_level)\n        noise = np.random.randn(len(y))\n        augmented = (y + noise * noise_level).astype(y.dtype)\n        return augmented\n\n\nclass GaussianNoise(AudioTransform):\n    def __init__(self, always_apply=False, p=0.5, min_snr=5, max_snr=20, sr=32000):\n        super().__init__(always_apply, p)\n\n        self.min_snr = min_snr\n        self.max_snr = max_snr\n        self.sr = sr\n\n    def apply(self, y: np.ndarray, **params):\n        snr = np.random.uniform(self.min_snr, self.max_snr)\n        a_signal = np.sqrt(y ** 2).max()\n        a_noise = a_signal / (10 ** (snr / 20))\n\n        white_noise = np.random.randn(len(y))\n        a_white = np.sqrt(white_noise ** 2).max()\n        augmented = (y + white_noise * 1 / a_white * a_noise).astype(y.dtype)\n        return augmented\n\n\nclass PinkNoise(AudioTransform):\n    def __init__(self, always_apply=False, p=0.5, min_snr=5, max_snr=20, sr=32000):\n        super().__init__(always_apply, p)\n\n        self.min_snr = min_snr\n        self.max_snr = max_snr\n        self.sr = sr\n\n    def apply(self, y: np.ndarray, **params):\n        snr = np.random.uniform(self.min_snr, self.max_snr)\n        a_signal = np.sqrt(y ** 2).max()\n        a_noise = a_signal / (10 ** (snr / 20))\n\n        pink_noise = cn.powerlaw_psd_gaussian(1, len(y))\n        a_pink = np.sqrt(pink_noise ** 2).max()\n        augmented = (y + pink_noise * 1 / a_pink * a_noise).astype(y.dtype)\n        return augmented\n\n\nclass PitchShift(AudioTransform):\n    def __init__(self, always_apply=False, p=0.5, max_range=5, sr=32000):\n        super().__init__(always_apply, p)\n        self.max_range = max_range\n        self.sr = sr\n\n    def apply(self, y: np.ndarray, **params):\n        n_steps = np.random.randint(-self.max_range, self.max_range)\n        augmented = librosa.effects.pitch_shift(y, self.sr, n_steps)\n        return augmented\n\n\nclass TimeStretch(AudioTransform):\n    def __init__(self, always_apply=False, p=0.5, max_rate=1, sr=32000):\n        super().__init__(always_apply, p)\n        self.max_rate = max_rate\n        self.sr = sr\n\n    def apply(self, y: np.ndarray, **params):\n        rate = np.random.uniform(0, self.max_rate)\n        augmented = librosa.effects.time_stretch(y, rate)\n        return augmented\n\n\ndef _db2float(db: float, amplitude=True):\n    if amplitude:\n        return 10**(db / 20)\n    else:\n        return 10 ** (db / 10)\n\n\ndef volume_down(y: np.ndarray, db: float):\n    \"\"\"\n    Low level API for decreasing the volume\n    Parameters\n    ----------\n    y: numpy.ndarray\n        stereo / monaural input audio\n    db: float\n        how much decibel to decrease\n    Returns\n    -------\n    applied: numpy.ndarray\n        audio with decreased volume\n    \"\"\"\n    applied = y * _db2float(-db)\n    return applied\n\n\ndef volume_up(y: np.ndarray, db: float):\n    \"\"\"\n    Low level API for increasing the volume\n    Parameters\n    ----------\n    y: numpy.ndarray\n        stereo / monaural input audio\n    db: float\n        how much decibel to increase\n    Returns\n    -------\n    applied: numpy.ndarray\n        audio with increased volume\n    \"\"\"\n    applied = y * _db2float(db)\n    return applied\n\n\nclass RandomVolume(AudioTransform):\n    def __init__(self, always_apply=False, p=0.5, limit=10):\n        super().__init__(always_apply, p)\n        self.limit = limit\n\n    def apply(self, y: np.ndarray, **params):\n        db = np.random.uniform(-self.limit, self.limit)\n        if db >= 0:\n            return volume_up(y, db)\n        else:\n            return volume_down(y, db)\n\n\nclass OneOf:\n    def __init__(self, transforms: list):\n        self.transforms = transforms\n\n    def __call__(self, y: np.ndarray):\n        n_trns = len(self.transforms)\n        trns_idx = np.random.choice(n_trns)\n        trns = self.transforms[trns_idx]\n        y = trns(y)\n        return y\n\n\nclass CosineVolume(AudioTransform):\n    def __init__(self, always_apply=False, p=0.5, limit=10):\n        super().__init__(always_apply, p)\n        self.limit = limit\n\n    def apply(self, y: np.ndarray, **params):\n        db = np.random.uniform(-self.limit, self.limit)\n        cosine = np.cos(np.arange(len(y)) / len(y) * np.pi * 2)\n        dbs = _db2float(cosine * db)\n        return y * dbs\n\n\ndef drop_stripes(image: np.ndarray, dim: int, drop_width: int, stripes_num: int):\n    total_width = image.shape[dim]\n    lowest_value = image.min()\n    for _ in range(stripes_num):\n        distance = np.random.randint(low=0, high=drop_width, size=(1,))[0]\n        begin = np.random.randint(\n            low=0, high=total_width - distance, size=(1,))[0]\n\n        if dim == 0:\n            image[begin:begin + distance] = lowest_value\n        elif dim == 1:\n            image[:, begin + distance] = lowest_value\n        elif dim == 2:\n            image[:, :, begin + distance] = lowest_value\n    return image\n\n\nclass TimeFreqMasking(ImageOnlyTransform):\n    def __init__(self,\n                 time_drop_width: int,\n                 time_stripes_num: int,\n                 freq_drop_width: int,\n                 freq_stripes_num: int,\n                 always_apply=False,\n                 p=0.5):\n        super().__init__(always_apply, p)\n        self.time_drop_width = time_drop_width\n        self.time_stripes_num = time_stripes_num\n        self.freq_drop_width = freq_drop_width\n        self.freq_stripes_num = freq_stripes_num\n\n    def apply(self, img, **params):\n        img_ = img.copy()\n        if img.ndim == 2:\n            img_ = drop_stripes(\n                img_, dim=0, drop_width=self.freq_drop_width, stripes_num=self.freq_stripes_num)\n            img_ = drop_stripes(\n                img_, dim=1, drop_width=self.time_drop_width, stripes_num=self.time_stripes_num)\n        return img_","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Get model"},{"metadata":{"trusted":true},"cell_type":"code","source":"def prepare_model_for_inference(model, path: Path):\n    if not torch.cuda.is_available():\n        ckpt = torch.load(path, map_location=\"cpu\")\n    else:\n        ckpt = torch.load(path)\n    model.load_state_dict(ckpt[\"model_state_dict\"])\n    model.eval()\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def prediction_for_clip(test_df: pd.DataFrame, \n                        clip: np.ndarray, \n                        model, \n                        threshold=0.5):\n\n    dataset = TestDataset(df=test_df, \n                          clip=clip,\n                          waveform_transforms=get_transforms(phase=\"test\"))\n    loader = torchdata.DataLoader(dataset, batch_size=1, shuffle=False)\n    device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n    \n    model.eval()\n    prediction_dict = {}\n    for image, row_id in tqdm(loader):\n        row_id = row_id[0]\n        image = image.to(device)\n\n        with torch.no_grad():\n            prediction = model(image)\n            proba = prediction[\"clipwise_output\"].detach().cpu().numpy().reshape(-1)\n\n        events = proba >= threshold\n        labels = np.argwhere(events).reshape(-1).tolist()\n\n        if len(labels) == 0:\n            prediction_dict[row_id] = \"nocall\"\n        else:\n            labels_str_list = list(map(lambda x: CFG.target_columns[x], labels))\n            label_string = \" \".join(labels_str_list)\n            prediction_dict[row_id] = label_string\n    return prediction_dict","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def prediction(test_audios,\n               weights_path: Path,\n               threshold=0.5):\n    device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n    model = TimmSED(base_model_name=CFG.base_model_name,\n                    pretrained=False,\n                    num_classes=CFG.num_classes,\n                    in_channels=CFG.in_channels)\n    model = prepare_model_for_inference(model, weights_path).to(device)\n\n    warnings.filterwarnings(\"ignore\")\n    prediction_dfs = []\n    for audio_path in test_audios:\n        with timer(f\"Loading {str(audio_path)}\", logger):\n            clip, _ = sf.read(audio_path)\n\n        seconds = []\n        row_ids = []\n        for second in range(5, 605, 5):\n            row_id = \"_\".join(audio_path.name.split(\"_\")[:2]) + f\"_{second}\"\n            seconds.append(second)\n            row_ids.append(row_id)\n            \n        test_df = pd.DataFrame({\n            \"row_id\": row_ids,\n            \"seconds\": seconds\n        })\n        with timer(f\"Prediction on {audio_path}\", logger):\n            prediction_dict = prediction_for_clip(test_df,\n                                                  clip=clip,\n                                                  model=model,\n                                                  threshold=threshold)\n        row_id = list(prediction_dict.keys())\n        birds = list(prediction_dict.values())\n        prediction_df = pd.DataFrame({\n            \"row_id\": row_id,\n            \"birds\": birds\n        })\n        prediction_dfs.append(prediction_df)\n    \n    prediction_df = pd.concat(prediction_dfs, axis=0, sort=False).reset_index(drop=True)\n    return prediction_df","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Prediction"},{"metadata":{"trusted":true},"cell_type":"code","source":"weights_path = Path(\"../input/birdclef2021-effnetb0-starter-weight/best.pth\")\nsubmission = prediction(test_audios=all_audios,\n                        weights_path=weights_path,\n                        threshold=0.5)\nsubmission.to_csv(\"submission.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pd.read_csv(\"submission.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}