{"cells":[{"metadata":{},"cell_type":"markdown","source":"## Credits\n\n\nThis notebook is a extension of :\n* https://www.kaggle.com/kneroma/resnest50-fast-too-much-birds-could-hurt\n\n","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"### Trainig Notebook for efficient Net \n* https://www.kaggle.com/rsinda/training-efficientnet-model","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"### NOTE: You need to train a efficient-net model before using this.","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"### import libraries","execution_count":null},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import os\nimport sys\nsys.path = [\n    '../input/efficientnet-pytorch/EfficientNet-PyTorch/EfficientNet-PyTorch-master',\n] + sys.path\nimport gc\nimport time\nimport math\nimport shutil\nimport random\nimport warnings\nimport typing as tp\nfrom pathlib import Path\nfrom contextlib import contextmanager\n\nimport yaml\nfrom joblib import delayed, Parallel\n\nimport cv2\nimport librosa\nimport audioread\nimport soundfile as sf\n\nimport numpy as np\nimport pandas as pd\n\nfrom fastprogress import progress_bar\nfrom sklearn.metrics import f1_score\nfrom sklearn.model_selection import StratifiedKFold\n\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nfrom torch.nn import Conv2d, Module, Linear, BatchNorm2d, ReLU\nfrom torch.nn.modules.utils import _pair\nimport torch.utils.data as data\n\npd.options.display.max_rows = 500\npd.options.display.max_columns = 500","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","collapsed":true,"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":false},"cell_type":"markdown","source":"### define utilities","execution_count":null},{"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\n@contextmanager\ndef timer(name: str) -> None:\n    \"\"\"Timer Util\"\"\"\n    t0 = time.time()\n    print(\"[{}] start\".format(name))\n    yield\n    print(\"[{}] done in {:.0f} s\".format(name, time.time() - t0))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nset_seed(1213)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### read data","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"ROOT = Path.cwd().parent\nINPUT_ROOT = ROOT / \"input\"\nRAW_DATA = INPUT_ROOT / \"birdsong-recognition\"\nTRAIN_AUDIO_DIR = RAW_DATA / \"train_audio\"\nTEST_AUDIO_DIR = RAW_DATA / \"test_audio\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv(RAW_DATA / \"train.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"if not TEST_AUDIO_DIR.exists():\n    TEST_AUDIO_DIR = INPUT_ROOT / \"birdcall-check\" / \"test_audio\"\n    test = pd.read_csv(INPUT_ROOT / \"birdcall-check\" / \"test.csv\")\nelse:\n    test = pd.read_csv(RAW_DATA / \"test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = pd.read_csv(\"../input/birdsong-recognition/sample_submission.csv\")\nsub.to_csv(\"submission.csv\", index=False)  # this will be overwritten if everything goes well","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### set parameters","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"TARGET_SR = 32000\nmodel_config = {\n    \"base_model_name\": \"RESNET\",\n    \"pretrained\": False,\n    \"num_classes\": 264,\n    \"trained_weights\": \"../input/training-birdsong-baseline-resnest50-fast/best_model.pth\"\n}\n\nmelspectrogram_parameters = {\n    \"n_mels\": 128,\n    \"fmin\": 20,\n    \"fmax\": 16000\n}","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Definition","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"### Dataset\n\nFor `site_3`, I decided to use the same procedure as I did for `site_1` and `site_2`, which is, crop 5 seconds out of the clip and provide prediction on that short clip.\nThe only difference is that I crop 5 seconds short clip from start to the end of the `site_3` clip and aggeregate predictions for each short clip after I did prediction for all those short clips.","execution_count":null},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"BIRD_CODE = {\n    'aldfly': 0, 'ameavo': 1, 'amebit': 2, 'amecro': 3, 'amegfi': 4,\n    'amekes': 5, 'amepip': 6, 'amered': 7, 'amerob': 8, 'amewig': 9,\n    'amewoo': 10, 'amtspa': 11, 'annhum': 12, 'astfly': 13, 'baisan': 14,\n    'baleag': 15, 'balori': 16, 'banswa': 17, 'barswa': 18, 'bawwar': 19,\n    'belkin1': 20, 'belspa2': 21, 'bewwre': 22, 'bkbcuc': 23, 'bkbmag1': 24,\n    'bkbwar': 25, 'bkcchi': 26, 'bkchum': 27, 'bkhgro': 28, 'bkpwar': 29,\n    'bktspa': 30, 'blkpho': 31, 'blugrb1': 32, 'blujay': 33, 'bnhcow': 34,\n    'boboli': 35, 'bongul': 36, 'brdowl': 37, 'brebla': 38, 'brespa': 39,\n    'brncre': 40, 'brnthr': 41, 'brthum': 42, 'brwhaw': 43, 'btbwar': 44,\n    'btnwar': 45, 'btywar': 46, 'buffle': 47, 'buggna': 48, 'buhvir': 49,\n    'bulori': 50, 'bushti': 51, 'buwtea': 52, 'buwwar': 53, 'cacwre': 54,\n    'calgul': 55, 'calqua': 56, 'camwar': 57, 'cangoo': 58, 'canwar': 59,\n    'canwre': 60, 'carwre': 61, 'casfin': 62, 'caster1': 63, 'casvir': 64,\n    'cedwax': 65, 'chispa': 66, 'chiswi': 67, 'chswar': 68, 'chukar': 69,\n    'clanut': 70, 'cliswa': 71, 'comgol': 72, 'comgra': 73, 'comloo': 74,\n    'commer': 75, 'comnig': 76, 'comrav': 77, 'comred': 78, 'comter': 79,\n    'comyel': 80, 'coohaw': 81, 'coshum': 82, 'cowscj1': 83, 'daejun': 84,\n    'doccor': 85, 'dowwoo': 86, 'dusfly': 87, 'eargre': 88, 'easblu': 89,\n    'easkin': 90, 'easmea': 91, 'easpho': 92, 'eastow': 93, 'eawpew': 94,\n    'eucdov': 95, 'eursta': 96, 'evegro': 97, 'fiespa': 98, 'fiscro': 99,\n    'foxspa': 100, 'gadwal': 101, 'gcrfin': 102, 'gnttow': 103, 'gnwtea': 104,\n    'gockin': 105, 'gocspa': 106, 'goleag': 107, 'grbher3': 108, 'grcfly': 109,\n    'greegr': 110, 'greroa': 111, 'greyel': 112, 'grhowl': 113, 'grnher': 114,\n    'grtgra': 115, 'grycat': 116, 'gryfly': 117, 'haiwoo': 118, 'hamfly': 119,\n    'hergul': 120, 'herthr': 121, 'hoomer': 122, 'hoowar': 123, 'horgre': 124,\n    'horlar': 125, 'houfin': 126, 'houspa': 127, 'houwre': 128, 'indbun': 129,\n    'juntit1': 130, 'killde': 131, 'labwoo': 132, 'larspa': 133, 'lazbun': 134,\n    'leabit': 135, 'leafly': 136, 'leasan': 137, 'lecthr': 138, 'lesgol': 139,\n    'lesnig': 140, 'lesyel': 141, 'lewwoo': 142, 'linspa': 143, 'lobcur': 144,\n    'lobdow': 145, 'logshr': 146, 'lotduc': 147, 'louwat': 148, 'macwar': 149,\n    'magwar': 150, 'mallar3': 151, 'marwre': 152, 'merlin': 153, 'moublu': 154,\n    'mouchi': 155, 'moudov': 156, 'norcar': 157, 'norfli': 158, 'norhar2': 159,\n    'normoc': 160, 'norpar': 161, 'norpin': 162, 'norsho': 163, 'norwat': 164,\n    'nrwswa': 165, 'nutwoo': 166, 'olsfly': 167, 'orcwar': 168, 'osprey': 169,\n    'ovenbi1': 170, 'palwar': 171, 'pasfly': 172, 'pecsan': 173, 'perfal': 174,\n    'phaino': 175, 'pibgre': 176, 'pilwoo': 177, 'pingro': 178, 'pinjay': 179,\n    'pinsis': 180, 'pinwar': 181, 'plsvir': 182, 'prawar': 183, 'purfin': 184,\n    'pygnut': 185, 'rebmer': 186, 'rebnut': 187, 'rebsap': 188, 'rebwoo': 189,\n    'redcro': 190, 'redhea': 191, 'reevir1': 192, 'renpha': 193, 'reshaw': 194,\n    'rethaw': 195, 'rewbla': 196, 'ribgul': 197, 'rinduc': 198, 'robgro': 199,\n    'rocpig': 200, 'rocwre': 201, 'rthhum': 202, 'ruckin': 203, 'rudduc': 204,\n    'rufgro': 205, 'rufhum': 206, 'rusbla': 207, 'sagspa1': 208, 'sagthr': 209,\n    'savspa': 210, 'saypho': 211, 'scatan': 212, 'scoori': 213, 'semplo': 214,\n    'semsan': 215, 'sheowl': 216, 'shshaw': 217, 'snobun': 218, 'snogoo': 219,\n    'solsan': 220, 'sonspa': 221, 'sora': 222, 'sposan': 223, 'spotow': 224,\n    'stejay': 225, 'swahaw': 226, 'swaspa': 227, 'swathr': 228, 'treswa': 229,\n    'truswa': 230, 'tuftit': 231, 'tunswa': 232, 'veery': 233, 'vesspa': 234,\n    'vigswa': 235, 'warvir': 236, 'wesblu': 237, 'wesgre': 238, 'weskin': 239,\n    'wesmea': 240, 'wessan': 241, 'westan': 242, 'wewpew': 243, 'whbnut': 244,\n    'whcspa': 245, 'whfibi': 246, 'whtspa': 247, 'whtswi': 248, 'wilfly': 249,\n    'wilsni1': 250, 'wiltur': 251, 'winwre3': 252, 'wlswar': 253, 'wooduc': 254,\n    'wooscj2': 255, 'woothr': 256, 'y00475': 257, 'yebfly': 258, 'yebsap': 259,\n    'yehbla': 260, 'yelwar': 261, 'yerwar': 262, 'yetvir': 263\n}\n\nINV_BIRD_CODE = {v: k for k, v in BIRD_CODE.items()}","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"def mono_to_color(X: np.ndarray,\n                  mean=None,\n                  std=None,\n                  norm_max=None,\n                  norm_min=None,\n                  eps=1e-6):\n    \"\"\"\n    Code from https://www.kaggle.com/daisukelab/creating-fat2019-preprocessed-data\n    \"\"\"\n    # Stack X as [X,X,X]\n    X = np.stack([X, X, X], axis=-1)\n\n    # Standardize\n    mean = mean or X.mean()\n    X = X - mean\n    std = std or X.std()\n    Xstd = X / (std + eps)\n    _min, _max = Xstd.min(), Xstd.max()\n    norm_max = norm_max or _max\n    norm_min = norm_min or _min\n    if (_max - _min) > eps:\n        # Normalize to [0, 255]\n        V = Xstd\n        V[V < norm_min] = norm_min\n        V[V > norm_max] = norm_max\n        V = 255 * (V - norm_min) / (norm_max - norm_min)\n        V = V.astype(np.uint8)\n    else:\n        # Just zero\n        V = np.zeros_like(Xstd, dtype=np.uint8)\n    return V\n\n\nclass TestDataset(data.Dataset):\n    def __init__(self, df: pd.DataFrame, clip: np.ndarray,\n                 img_size=224, melspectrogram_parameters={}):\n        self.df = df\n        self.clip = clip\n        self.img_size = img_size\n        self.melspectrogram_parameters = melspectrogram_parameters\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        site = sample.site\n        row_id = sample.row_id\n        \n        if site == \"site_3\":\n            y = self.clip.astype(np.float32)\n            len_y = len(y)\n            start = 0\n            end = SR * 5\n            images = []\n            while len_y > start:\n                y_batch = y[start:end].astype(np.float32)\n                if len(y_batch) != (SR * 5):\n                    break\n                start = end\n                end = end + SR * 5\n                \n                melspec = librosa.feature.melspectrogram(y_batch,\n                                                         sr=SR,\n                                                         **self.melspectrogram_parameters)\n                melspec = librosa.power_to_db(melspec).astype(np.float32)\n                image = mono_to_color(melspec)\n                height, width, _ = image.shape\n                image = cv2.resize(image, (int(width * self.img_size / height), self.img_size))\n                image = np.moveaxis(image, 2, 0)\n                image = (image / 255.0).astype(np.float32)\n                images.append(image)\n            images = np.asarray(images)\n            return images, row_id, site\n        else:\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            melspec = librosa.feature.melspectrogram(y, sr=SR, **self.melspectrogram_parameters)\n            melspec = librosa.power_to_db(melspec).astype(np.float32)\n\n            image = mono_to_color(melspec)\n            height, width, _ = image.shape\n            image = cv2.resize(image, (int(width * self.img_size / height), self.img_size))\n            image = np.moveaxis(image, 2, 0)\n            image = (image / 255.0).astype(np.float32)\n\n            return image, row_id, site","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### model\n\n* I forked this code from authors' original implementation. [GitHub](https://github.com/zhanghang1989/ResNeSt)","execution_count":null},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"class SplAtConv2d(Module):\n    \"\"\"Split-Attention Conv2d\n    \"\"\"\n    def __init__(self, in_channels, channels, kernel_size, stride=(1, 1), padding=(0, 0),\n                 dilation=(1, 1), groups=1, bias=True,\n                 radix=2, reduction_factor=4,\n                 rectify=False, rectify_avg=False, norm_layer=None,\n                 dropblock_prob=0.0, **kwargs):\n        super(SplAtConv2d, self).__init__()\n        padding = _pair(padding)\n        self.rectify = rectify and (padding[0] > 0 or padding[1] > 0)\n        self.rectify_avg = rectify_avg\n        inter_channels = max(in_channels*radix//reduction_factor, 32)\n        self.radix = radix\n        self.cardinality = groups\n        self.channels = channels\n        self.dropblock_prob = dropblock_prob\n        if self.rectify:\n            from rfconv import RFConv2d\n            self.conv = RFConv2d(in_channels, channels*radix, kernel_size, stride, padding, dilation,\n                                 groups=groups*radix, bias=bias, average_mode=rectify_avg, **kwargs)\n        else:\n            self.conv = Conv2d(in_channels, channels*radix, kernel_size, stride, padding, dilation,\n                               groups=groups*radix, bias=bias, **kwargs)\n        self.use_bn = norm_layer is not None\n        if self.use_bn:\n            self.bn0 = norm_layer(channels*radix)\n        self.relu = ReLU(inplace=True)\n        self.fc1 = Conv2d(channels, inter_channels, 1, groups=self.cardinality)\n        if self.use_bn:\n            self.bn1 = norm_layer(inter_channels)\n        self.fc2 = Conv2d(inter_channels, channels*radix, 1, groups=self.cardinality)\n        if dropblock_prob > 0.0:\n            self.dropblock = DropBlock2D(dropblock_prob, 3)\n        self.rsoftmax = rSoftMax(radix, groups)\n\n    def forward(self, x):\n        x = self.conv(x)\n        if self.use_bn:\n            x = self.bn0(x)\n        if self.dropblock_prob > 0.0:\n            x = self.dropblock(x)\n        x = self.relu(x)\n\n        batch, rchannel = x.shape[:2]\n        if self.radix > 1:\n            if torch.__version__ < '1.5':\n                splited = torch.split(x, int(rchannel//self.radix), dim=1)\n            else:\n                splited = torch.split(x, rchannel//self.radix, dim=1)\n            gap = sum(splited) \n        else:\n            gap = x\n        gap = F.adaptive_avg_pool2d(gap, 1)\n        gap = self.fc1(gap)\n\n        if self.use_bn:\n            gap = self.bn1(gap)\n        gap = self.relu(gap)\n\n        atten = self.fc2(gap)\n        atten = self.rsoftmax(atten).view(batch, -1, 1, 1)\n\n        if self.radix > 1:\n            if torch.__version__ < '1.5':\n                attens = torch.split(atten, int(rchannel//self.radix), dim=1)\n            else:\n                attens = torch.split(atten, rchannel//self.radix, dim=1)\n            out = sum([att*split for (att, split) in zip(attens, splited)])\n        else:\n            out = atten * x\n        return out.contiguous()\n\nclass rSoftMax(nn.Module):\n    def __init__(self, radix, cardinality):\n        super().__init__()\n        self.radix = radix\n        self.cardinality = cardinality\n\n    def forward(self, x):\n        batch = x.size(0)\n        if self.radix > 1:\n            x = x.view(batch, self.cardinality, self.radix, -1).transpose(1, 2)\n            x = F.softmax(x, dim=1)\n            x = x.reshape(batch, -1)\n        else:\n            x = torch.sigmoid(x)\n        return x","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"class DropBlock2D(object):\n    def __init__(self, *args, **kwargs):\n        raise NotImplementedError\n\nclass GlobalAvgPool2d(nn.Module):\n    def __init__(self):\n        \"\"\"Global average pooling over the input's spatial dimensions\"\"\"\n        super(GlobalAvgPool2d, self).__init__()\n\n    def forward(self, inputs):\n        return nn.functional.adaptive_avg_pool2d(inputs, 1).view(inputs.size(0), -1)\n\nclass Bottleneck(nn.Module):\n    \"\"\"ResNet Bottleneck\n    \"\"\"\n    # pylint: disable=unused-argument\n    expansion = 4\n    def __init__(self, inplanes, planes, stride=1, downsample=None,\n                 radix=1, cardinality=1, bottleneck_width=64,\n                 avd=False, avd_first=False, dilation=1, is_first=False,\n                 rectified_conv=False, rectify_avg=False,\n                 norm_layer=None, dropblock_prob=0.0, last_gamma=False):\n        super(Bottleneck, self).__init__()\n        group_width = int(planes * (bottleneck_width / 64.)) * cardinality\n        self.conv1 = nn.Conv2d(inplanes, group_width, kernel_size=1, bias=False)\n        self.bn1 = norm_layer(group_width)\n        self.dropblock_prob = dropblock_prob\n        self.radix = radix\n        self.avd = avd and (stride > 1 or is_first)\n        self.avd_first = avd_first\n\n        if self.avd:\n            self.avd_layer = nn.AvgPool2d(3, stride, padding=1)\n            stride = 1\n\n        if dropblock_prob > 0.0:\n            self.dropblock1 = DropBlock2D(dropblock_prob, 3)\n            if radix == 1:\n                self.dropblock2 = DropBlock2D(dropblock_prob, 3)\n            self.dropblock3 = DropBlock2D(dropblock_prob, 3)\n\n        if radix >= 1:\n            self.conv2 = SplAtConv2d(\n                group_width, group_width, kernel_size=3,\n                stride=stride, padding=dilation,\n                dilation=dilation, groups=cardinality, bias=False,\n                radix=radix, rectify=rectified_conv,\n                rectify_avg=rectify_avg,\n                norm_layer=norm_layer,\n                dropblock_prob=dropblock_prob)\n        elif rectified_conv:\n            from rfconv import RFConv2d\n            self.conv2 = RFConv2d(\n                group_width, group_width, kernel_size=3, stride=stride,\n                padding=dilation, dilation=dilation,\n                groups=cardinality, bias=False,\n                average_mode=rectify_avg)\n            self.bn2 = norm_layer(group_width)\n        else:\n            self.conv2 = nn.Conv2d(\n                group_width, group_width, kernel_size=3, stride=stride,\n                padding=dilation, dilation=dilation,\n                groups=cardinality, bias=False)\n            self.bn2 = norm_layer(group_width)\n\n        self.conv3 = nn.Conv2d(\n            group_width, planes * 4, kernel_size=1, bias=False)\n        self.bn3 = norm_layer(planes*4)\n\n        if last_gamma:\n            from torch.nn.init import zeros_\n            zeros_(self.bn3.weight)\n        self.relu = nn.ReLU(inplace=True)\n        self.downsample = downsample\n        self.dilation = dilation\n        self.stride = stride\n\n    def forward(self, x):\n        residual = x\n\n        out = self.conv1(x)\n        out = self.bn1(out)\n        if self.dropblock_prob > 0.0:\n            out = self.dropblock1(out)\n        out = self.relu(out)\n\n        if self.avd and self.avd_first:\n            out = self.avd_layer(out)\n\n        out = self.conv2(out)\n        if self.radix == 0:\n            out = self.bn2(out)\n            if self.dropblock_prob > 0.0:\n                out = self.dropblock2(out)\n            out = self.relu(out)\n\n        if self.avd and not self.avd_first:\n            out = self.avd_layer(out)\n\n        out = self.conv3(out)\n        out = self.bn3(out)\n        if self.dropblock_prob > 0.0:\n            out = self.dropblock3(out)\n\n        if self.downsample is not None:\n            residual = self.downsample(x)\n\n        out += residual\n        out = self.relu(out)\n\n        return out\n\nclass ResNet(nn.Module):\n    \"\"\"ResNet Variants\n    Parameters\n    ----------\n    block : Block\n        Class for the residual block. Options are BasicBlockV1, BottleneckV1.\n    layers : list of int\n        Numbers of layers in each block\n    classes : int, default 1000\n        Number of classification classes.\n    dilated : bool, default False\n        Applying dilation strategy to pretrained ResNet yielding a stride-8 model,\n        typically used in Semantic Segmentation.\n    norm_layer : object\n        Normalization layer used in backbone network (default: :class:`mxnet.gluon.nn.BatchNorm`;\n        for Synchronized Cross-GPU BachNormalization).\n    Reference:\n        - He, Kaiming, et al. \"Deep residual learning for image recognition.\" Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.\n        - Yu, Fisher, and Vladlen Koltun. \"Multi-scale context aggregation by dilated convolutions.\"\n    \"\"\"\n    # pylint: disable=unused-variable\n    def __init__(self, block, layers, radix=1, groups=1, bottleneck_width=64,\n                 num_classes=1000, dilated=False, dilation=1,\n                 deep_stem=False, stem_width=64, avg_down=False,\n                 rectified_conv=False, rectify_avg=False,\n                 avd=False, avd_first=False,\n                 final_drop=0.0, dropblock_prob=0,\n                 last_gamma=False, norm_layer=nn.BatchNorm2d):\n        self.cardinality = groups\n        self.bottleneck_width = bottleneck_width\n        # ResNet-D params\n        self.inplanes = stem_width*2 if deep_stem else 64\n        self.avg_down = avg_down\n        self.last_gamma = last_gamma\n        # ResNeSt params\n        self.radix = radix\n        self.avd = avd\n        self.avd_first = avd_first\n\n        super(ResNet, self).__init__()\n        self.rectified_conv = rectified_conv\n        self.rectify_avg = rectify_avg\n        if rectified_conv:\n            from rfconv import RFConv2d\n            conv_layer = RFConv2d\n        else:\n            conv_layer = nn.Conv2d\n        conv_kwargs = {'average_mode': rectify_avg} if rectified_conv else {}\n        if deep_stem:\n            self.conv1 = nn.Sequential(\n                conv_layer(3, stem_width, kernel_size=3, stride=2, padding=1, bias=False, **conv_kwargs),\n                norm_layer(stem_width),\n                nn.ReLU(inplace=True),\n                conv_layer(stem_width, stem_width, kernel_size=3, stride=1, padding=1, bias=False, **conv_kwargs),\n                norm_layer(stem_width),\n                nn.ReLU(inplace=True),\n                conv_layer(stem_width, stem_width*2, kernel_size=3, stride=1, padding=1, bias=False, **conv_kwargs),\n            )\n        else:\n            self.conv1 = conv_layer(3, 64, kernel_size=7, stride=2, padding=3,\n                                   bias=False, **conv_kwargs)\n        self.bn1 = norm_layer(self.inplanes)\n        self.relu = nn.ReLU(inplace=True)\n        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)\n        self.layer1 = self._make_layer(block, 64, layers[0], norm_layer=norm_layer, is_first=False)\n        self.layer2 = self._make_layer(block, 128, layers[1], stride=2, norm_layer=norm_layer)\n        if dilated or dilation == 4:\n            self.layer3 = self._make_layer(block, 256, layers[2], stride=1,\n                                           dilation=2, norm_layer=norm_layer,\n                                           dropblock_prob=dropblock_prob)\n            self.layer4 = self._make_layer(block, 512, layers[3], stride=1,\n                                           dilation=4, norm_layer=norm_layer,\n                                           dropblock_prob=dropblock_prob)\n        elif dilation==2:\n            self.layer3 = self._make_layer(block, 256, layers[2], stride=2,\n                                           dilation=1, norm_layer=norm_layer,\n                                           dropblock_prob=dropblock_prob)\n            self.layer4 = self._make_layer(block, 512, layers[3], stride=1,\n                                           dilation=2, norm_layer=norm_layer,\n                                           dropblock_prob=dropblock_prob)\n        else:\n            self.layer3 = self._make_layer(block, 256, layers[2], stride=2,\n                                           norm_layer=norm_layer,\n                                           dropblock_prob=dropblock_prob)\n            self.layer4 = self._make_layer(block, 512, layers[3], stride=2,\n                                           norm_layer=norm_layer,\n                                           dropblock_prob=dropblock_prob)\n        self.avgpool = GlobalAvgPool2d()\n        self.drop = nn.Dropout(final_drop) if final_drop > 0.0 else None\n        self.fc = nn.Linear(512 * block.expansion, num_classes)\n\n        for m in self.modules():\n            if isinstance(m, nn.Conv2d):\n                n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels\n                m.weight.data.normal_(0, math.sqrt(2. / n))\n            elif isinstance(m, norm_layer):\n                m.weight.data.fill_(1)\n                m.bias.data.zero_()\n\n    def _make_layer(self, block, planes, blocks, stride=1, dilation=1, norm_layer=None,\n                    dropblock_prob=0.0, is_first=True):\n        downsample = None\n        if stride != 1 or self.inplanes != planes * block.expansion:\n            down_layers = []\n            if self.avg_down:\n                if dilation == 1:\n                    down_layers.append(nn.AvgPool2d(kernel_size=stride, stride=stride,\n                                                    ceil_mode=True, count_include_pad=False))\n                else:\n                    down_layers.append(nn.AvgPool2d(kernel_size=1, stride=1,\n                                                    ceil_mode=True, count_include_pad=False))\n                down_layers.append(nn.Conv2d(self.inplanes, planes * block.expansion,\n                                             kernel_size=1, stride=1, bias=False))\n            else:\n                down_layers.append(nn.Conv2d(self.inplanes, planes * block.expansion,\n                                             kernel_size=1, stride=stride, bias=False))\n            down_layers.append(norm_layer(planes * block.expansion))\n            downsample = nn.Sequential(*down_layers)\n\n        layers = []\n        if dilation == 1 or dilation == 2:\n            layers.append(block(self.inplanes, planes, stride, downsample=downsample,\n                                radix=self.radix, cardinality=self.cardinality,\n                                bottleneck_width=self.bottleneck_width,\n                                avd=self.avd, avd_first=self.avd_first,\n                                dilation=1, is_first=is_first, rectified_conv=self.rectified_conv,\n                                rectify_avg=self.rectify_avg,\n                                norm_layer=norm_layer, dropblock_prob=dropblock_prob,\n                                last_gamma=self.last_gamma))\n        elif dilation == 4:\n            layers.append(block(self.inplanes, planes, stride, downsample=downsample,\n                                radix=self.radix, cardinality=self.cardinality,\n                                bottleneck_width=self.bottleneck_width,\n                                avd=self.avd, avd_first=self.avd_first,\n                                dilation=2, is_first=is_first, rectified_conv=self.rectified_conv,\n                                rectify_avg=self.rectify_avg,\n                                norm_layer=norm_layer, dropblock_prob=dropblock_prob,\n                                last_gamma=self.last_gamma))\n        else:\n            raise RuntimeError(\"=> unknown dilation size: {}\".format(dilation))\n\n        self.inplanes = planes * block.expansion\n        for i in range(1, blocks):\n            layers.append(block(self.inplanes, planes,\n                                radix=self.radix, cardinality=self.cardinality,\n                                bottleneck_width=self.bottleneck_width,\n                                avd=self.avd, avd_first=self.avd_first,\n                                dilation=dilation, rectified_conv=self.rectified_conv,\n                                rectify_avg=self.rectify_avg,\n                                norm_layer=norm_layer, dropblock_prob=dropblock_prob,\n                                last_gamma=self.last_gamma))\n\n        return nn.Sequential(*layers)\n\n    def forward(self, x):\n        x = self.conv1(x)\n        x = self.bn1(x)\n        x = self.relu(x)\n        x = self.maxpool(x)\n\n        x = self.layer1(x)\n        x = self.layer2(x)\n        x = self.layer3(x)\n        x = self.layer4(x)\n\n        x = self.avgpool(x)\n        #x = x.view(x.size(0), -1)\n        x = torch.flatten(x, 1)\n        if self.drop:\n            x = self.drop(x)\n        x = self.fc(x)\n\n        return x","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## efficientnet","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"from efficientnet_pytorch import model as enet\npretrained_model = {\n    'efficientnet-b2': '../input/efficientnet-pytorch/efficientnet-b2-27687264.pth'\n}\n\nenet_type = 'efficientnet-b4'\n\ndevice = torch.device('cuda')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class enetv2(nn.Module):\n    def __init__(self, backbone):\n        super(enetv2, self).__init__()\n        self.enet = enet.EfficientNet.from_name(backbone)\n        self.myfc = nn.Sequential(\n        nn.Linear(self.enet._fc.in_features,1024), nn.ReLU(), nn.Dropout(p=0.2),\n        nn.Linear(1024, 264))\n        \n        self.enet._fc = nn.Identity()\n\n    def extract(self, x):\n        return self.enet(x)\n\n    def forward(self, x):\n        x = self.extract(x)\n#         print(x.shape)\n        x = self.myfc(x)\n        return x","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_model_enet():\n    model =enetv2(enet_type)\n    model.load_state_dict(torch.load(\"../input/bird-enet-model/fold3.pth\"))\n    model = model.to(device)\n    model.eval()\n    \n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_model(args: tp.Dict):\n    # # get resnest50_fast_1s1x64d\n    model = ResNet(\n        Bottleneck, [3, 4, 6, 3],\n        radix=1, groups=1, bottleneck_width=64,\n        deep_stem=True, stem_width=32, avg_down=True,\n        avd=True, avd_first=True)\n    \n    del model.fc\n    # # use the same head as the baseline notebook.\n    model.fc = nn.Sequential(\n        nn.Linear(2048, 1024), nn.ReLU(), nn.Dropout(p=0.2),\n        nn.Linear(1024, 1024), nn.ReLU(), nn.Dropout(p=0.2),\n        nn.Linear(1024, args[\"num_classes\"]))\n    \n    device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n    model = model.to(device)\n#     state_dict = torch.load(args[\"trained_weights\"], map_location=device)\n#     model.load_state_dict(state_dict)\n    \n    model.eval()\n    \n    return model","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Prediction loop","execution_count":null},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"def prediction_for_clip(test_df: pd.DataFrame, \n                        clip: np.ndarray, \n                        model:ResNet,\n                        model_enet : enetv2,\n                        mel_params: dict, \n                        threshold=0.5,\n                        maxpreds=3, # New param --> @kkiller\n                       ):\n    \n\n    dataset = TestDataset(df=test_df, \n                          clip=clip,\n                          img_size=224,\n                          melspectrogram_parameters=mel_params)\n    loader = data.DataLoader(dataset, batch_size=1, shuffle=False)\n    device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n    \n    model.eval()\n    model_enet.eval()\n    prediction_dict = {}\n    for image, row_id, site in progress_bar(loader):\n        site = site[0]\n        row_id = row_id[0]\n        if site in {\"site_1\", \"site_2\"}:\n            image = image.to(device)\n\n            with torch.no_grad():\n                prediction_1 = F.sigmoid(model(image))\n                prediction_2 = F.sigmoid(model_enet(image))\n                \n                proba = (prediction_1.detach().cpu().numpy().reshape(-1) +   prediction_2.detach().cpu().numpy().reshape(-1) )/2 #prediction.detach().cpu().numpy().reshape(-1)\n\n            events = proba >= threshold\n            labels = np.argsort(-proba)[:events.sum()].tolist()\n\n        else:\n            # to avoid prediction on large batch\n            image = image.squeeze(0)\n            batch_size = 16\n            whole_size = image.size(0)\n            if whole_size % batch_size == 0:\n                n_iter = whole_size // batch_size\n            else:\n                n_iter = whole_size // batch_size + 1\n                \n            all_events = set()\n            probas = []\n            for batch_i in range(n_iter):\n                batch = image[batch_i * batch_size:(batch_i + 1) * batch_size]\n                if batch.ndim == 3:\n                    batch = batch.unsqueeze(0)\n\n                batch = batch.to(device)\n                with torch.no_grad():\n                    prediction_1 = F.sigmoid(model(batch))\n                    prediction_2 = F.sigmoid(model_enet(batch))\n                    proba = (prediction_1.detach().cpu().numpy() +   prediction_2.detach().cpu().numpy() )/2 #prediction.detach().cpu().numpy()\n\n                    probas.append(proba)\n                \n            probas = np.vstack(probas)\n            probas = probas.max(0)\n            events = (probas>=threshold)\n            labels = np.argsort(-probas)[:events.sum()].tolist()\n        \n        if len(labels) == 0:\n            prediction_dict[row_id] = \"nocall\"\n        else:\n            labels_str_list = list(map(lambda x: INV_BIRD_CODE[x], labels))\n            label_string = \" \".join(labels_str_list[:maxpreds])\n            prediction_dict[row_id] = label_string\n    return prediction_dict","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":true},"cell_type":"code","source":"def prediction(test_df: pd.DataFrame,\n               test_audio: Path,\n               model_config: dict,\n               mel_params: dict,\n               target_sr: int,\n               threshold=0.5,\n               maxpreds = 3, # New param --> @kkiller\n              ):\n    model = get_model(model_config)\n    model_enet = get_model_enet()\n    unique_audio_id = test_df.audio_id.unique()\n\n    warnings.filterwarnings(\"ignore\")\n    prediction_dfs = []\n    for audio_id in unique_audio_id:\n        with timer(f\"Loading {audio_id}\"):\n            clip, _ = librosa.load(test_audio / (audio_id + \".mp3\"),\n                                   sr=target_sr,\n                                   mono=True,\n                                   res_type=\"kaiser_fast\")\n        \n        test_df_for_audio_id = test_df.query(\n            f\"audio_id == '{audio_id}'\").reset_index(drop=True)\n        with timer(f\"Prediction on {audio_id}\"):\n            prediction_dict = prediction_for_clip(test_df_for_audio_id,\n                                                  clip=clip,\n                                                  model=model,\n                                                  model_enet = model_enet,\n                                                  mel_params=mel_params,\n                                                  threshold=threshold,\n                                                  maxpreds = maxpreds, # New param --> @kkiller\n                                                 )\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","execution_count":null},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"submission = prediction(test_df=test,\n                        test_audio=TEST_AUDIO_DIR,\n                        model_config=model_config,\n                        mel_params=melspectrogram_parameters,\n                        target_sr=TARGET_SR,\n                        threshold=0.56,\n                        maxpreds=2, # New param --> @kkiller\n                       )\nsubmission.to_csv(\"submission.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"submission\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"markdown","source":"## EOF","execution_count":null}],"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}