{"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":"!pip install ../input/bird-panns/torchlibrosa-master/torchlibrosa-master/","metadata":{"papermill":{"duration":30.198673,"end_time":"2020-08-23T10:39:00.920294","exception":false,"start_time":"2020-08-23T10:38:30.721621","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-05-28T05:03:32.583185Z","iopub.execute_input":"2021-05-28T05:03:32.583538Z","iopub.status.idle":"2021-05-28T05:04:00.544199Z","shell.execute_reply.started":"2021-05-28T05:03:32.583507Z","shell.execute_reply":"2021-05-28T05:04:00.543249Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install ../input/timm-pytorch-image-models/pytorch-image-models-master/","metadata":{"execution":{"iopub.status.busy":"2021-05-28T05:09:36.806812Z","iopub.execute_input":"2021-05-28T05:09:36.807148Z","iopub.status.idle":"2021-05-28T05:10:06.82393Z","shell.execute_reply.started":"2021-05-28T05:09:36.807117Z","shell.execute_reply":"2021-05-28T05:10:06.822941Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\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\nfrom glob import glob\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\nfrom torchlibrosa.stft import Spectrogram, LogmelFilterBank\nfrom torchlibrosa.augmentation import SpecAugmentation\n#from efficientnet_pytorch import EfficientNet\n\n\npd.options.display.max_rows = 500\npd.options.display.max_columns = 500","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","papermill":{"duration":4.134883,"end_time":"2020-08-23T10:39:05.066077","exception":false,"start_time":"2020-08-23T10:39:00.931194","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-05-28T05:04:31.67266Z","iopub.execute_input":"2021-05-28T05:04:31.673005Z","iopub.status.idle":"2021-05-28T05:04:34.825139Z","shell.execute_reply.started":"2021-05-28T05:04:31.672967Z","shell.execute_reply":"2021-05-28T05:04:34.824317Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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))","metadata":{"papermill":{"duration":0.020585,"end_time":"2020-08-23T10:39:05.094949","exception":false,"start_time":"2020-08-23T10:39:05.074364","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-05-28T05:04:34.82636Z","iopub.execute_input":"2021-05-28T05:04:34.826683Z","iopub.status.idle":"2021-05-28T05:04:34.833593Z","shell.execute_reply.started":"2021-05-28T05:04:34.826648Z","shell.execute_reply":"2021-05-28T05:04:34.832828Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# logger = get_logger(\"main.log\")\nset_seed(42)","metadata":{"papermill":{"duration":0.017206,"end_time":"2020-08-23T10:39:05.120237","exception":false,"start_time":"2020-08-23T10:39:05.103031","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-05-28T05:04:38.649509Z","iopub.execute_input":"2021-05-28T05:04:38.649856Z","iopub.status.idle":"2021-05-28T05:04:38.656802Z","shell.execute_reply.started":"2021-05-28T05:04:38.649825Z","shell.execute_reply":"2021-05-28T05:04:38.655955Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"SR = 32000\nROOT = Path.cwd().parent\nINPUT_ROOT = ROOT / \"input\"\nRAW_DATA = INPUT_ROOT / \"birdsong-recognition\"\nTRAIN_AUDIO_DIR = RAW_DATA / \"train_audio\"\n# TRAIN_RESAMPLED_AUDIO_DIRS = [\n#   INPUT_ROOT / \"birdsong-resampled-train-audio-{:0>2}\".format(i)  for i in range(5)\n# ]\nTEST_AUDIO_DIR = RAW_DATA / \"test_audio\"","metadata":{"papermill":{"duration":0.016764,"end_time":"2020-08-23T10:39:05.144779","exception":false,"start_time":"2020-08-23T10:39:05.128015","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-05-28T05:04:39.379142Z","iopub.execute_input":"2021-05-28T05:04:39.379466Z","iopub.status.idle":"2021-05-28T05:04:39.384227Z","shell.execute_reply.started":"2021-05-28T05:04:39.379433Z","shell.execute_reply":"2021-05-28T05:04:39.383302Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = pd.read_csv(RAW_DATA / \"train.csv\")","metadata":{"papermill":{"duration":0.287998,"end_time":"2020-08-23T10:39:05.440418","exception":false,"start_time":"2020-08-23T10:39:05.15242","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-05-28T05:04:41.869517Z","iopub.execute_input":"2021-05-28T05:04:41.869868Z","iopub.status.idle":"2021-05-28T05:04:42.208051Z","shell.execute_reply.started":"2021-05-28T05:04:41.869831Z","shell.execute_reply":"2021-05-28T05:04:42.207266Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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\")","metadata":{"papermill":{"duration":0.023162,"end_time":"2020-08-23T10:39:05.471655","exception":false,"start_time":"2020-08-23T10:39:05.448493","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-05-28T05:04:42.209511Z","iopub.execute_input":"2021-05-28T05:04:42.209853Z","iopub.status.idle":"2021-05-28T05:04:42.224563Z","shell.execute_reply.started":"2021-05-28T05:04:42.209815Z","shell.execute_reply":"2021-05-28T05:04:42.223842Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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","metadata":{"papermill":{"duration":0.188261,"end_time":"2020-08-23T10:39:05.668603","exception":false,"start_time":"2020-08-23T10:39:05.480342","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-05-28T05:04:44.925493Z","iopub.execute_input":"2021-05-28T05:04:44.925861Z","iopub.status.idle":"2021-05-28T05:04:45.277035Z","shell.execute_reply.started":"2021-05-28T05:04:44.925825Z","shell.execute_reply":"2021-05-28T05:04:45.276238Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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()}","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.052079,"end_time":"2020-08-23T10:39:05.72851","exception":false,"start_time":"2020-08-23T10:39:05.676431","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-05-28T05:04:45.278671Z","iopub.execute_input":"2021-05-28T05:04:45.279011Z","iopub.status.idle":"2021-05-28T05:04:45.312962Z","shell.execute_reply.started":"2021-05-28T05:04:45.278984Z","shell.execute_reply":"2021-05-28T05:04:45.311844Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class TestDataset(data.Dataset):\n    def __init__(self, df: pd.DataFrame, clip: np.ndarray):\n        \n        self.df = df\n        self.clip = clip\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            y_all = []\n            while len_y > start:\n                y_batch = y[start:end].astype(np.float32)\n                if len(y_batch) != (SR * 5):\n                    y_pad = np.zeros(5 * SR, dtype=np.float32)\n                    y_pad[:len(y_batch)] = y_batch\n                    y_all.append(y_pad)\n                    break\n                start = end\n                end = end + SR * 5\n                y_all.append(y_batch)\n            y_all = np.asarray(y_all)\n            return y_all, 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        return y, row_id, site","metadata":{"papermill":{"duration":0.025539,"end_time":"2020-08-23T10:39:05.76198","exception":false,"start_time":"2020-08-23T10:39:05.736441","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-05-28T05:04:46.779407Z","iopub.execute_input":"2021-05-28T05:04:46.780451Z","iopub.status.idle":"2021-05-28T05:04:46.793446Z","shell.execute_reply.started":"2021-05-28T05:04:46.780231Z","shell.execute_reply":"2021-05-28T05:04:46.792616Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from torchlibrosa.stft import LogmelFilterBank, Spectrogram\nfrom torchlibrosa.augmentation import SpecAugmentation\n\nclass BirdCLEFNet(nn.Module):\n    def __init__(self, model_name,params):\n        super(BirdCLEFNet, self).__init__()\n        self.model_name = model_name\n        self.n_label = 264\n        self.params=params\n        self.spectrogram_extractor = Spectrogram(n_fft=2048, hop_length=512,\n                                                 win_length=None, window=\"hann\", center=True, pad_mode=\"reflect\",\n                                                 freeze_parameters=True)\n\n        # Logmel feature extractor\n        self.logmel_extractor = LogmelFilterBank(sr=params.sr, n_fft=2048,\n                                                 n_mels=params.n_mels, fmin=params.fmin, fmax=params.fmax, ref=1.0, amin=1e-10, top_db=80.0,\n                                                 freeze_parameters=True)\n        \n        self.spec_augmenter = SpecAugmentation(time_drop_width=8,time_stripes_num=2,\n                                               freq_drop_width=4,freq_stripes_num=2)\n        \n        self.base_model = timm.create_model(model_name, pretrained=False,num_classes=self.n_label,in_chans=3)\n\n\n    def forward(self, x):  # input x: (batch, channel, Hz, time)\n        x = self.spectrogram_extractor(x)\n        x = self.logmel_extractor(x)\n        x=(x-x.mean())/x.std()\n        x=torch.squeeze(x,dim=1)\n        x = torch.stack([x,x,x],dim=1)\n        x=self.base_model(x)\n        return x","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"papermill":{"duration":0.09151,"end_time":"2020-08-23T10:39:05.860939","exception":false,"start_time":"2020-08-23T10:39:05.769429","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-05-28T05:05:02.996769Z","iopub.execute_input":"2021-05-28T05:05:02.997092Z","iopub.status.idle":"2021-05-28T05:05:03.01148Z","shell.execute_reply.started":"2021-05-28T05:05:02.997063Z","shell.execute_reply":"2021-05-28T05:05:03.010651Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Prediction loop","metadata":{"papermill":{"duration":0.007217,"end_time":"2020-08-23T10:39:05.971337","exception":false,"start_time":"2020-08-23T10:39:05.96412","status":"completed"},"tags":[]}},{"cell_type":"code","source":"def prediction_for_clip(test_df, \n                        clip, \n                        model, \n                        threshold=0.5):\n\n    dataset = TestDataset(df=test_df, clip=clip)\n    loader = data.DataLoader(dataset, batch_size=1, shuffle=False)\n    device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n    \n    \n    prediction_dict = {}\n    for image, row_id, site in progress_bar(loader):\n        site = site[0]\n        row_id = row_id[0]\n        image = image.to(device).float()\n        if site in {\"site_1\", \"site_2\"}:\n            image = image.to(device).float()\n\n            with torch.no_grad():\n                proba = 0.0\n                model.eval()\n                prediction = model(image)\n                prediction = prediction.sigmoid()\n                proba += prediction.detach().cpu().numpy().reshape(-1)\n                #print(proba.shape)\n\n            events = proba >= threshold\n            labels = np.argwhere(events).reshape(-1).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            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                    proba = 0.0\n                    model.eval()\n                    prediction = model(image)\n                    prediction = prediction.sigmoid()\n                    proba += prediction.detach().cpu().numpy()\n                #print(proba.shape)\n                    \n                events = proba >= threshold\n                #print(len(events))\n                for i in range(len(events)):\n                    event = events[i, :]\n                    labels = np.argwhere(event).reshape(-1).tolist()\n                    for label in labels:\n                        all_events.add(label)\n                        \n            labels = list(all_events)\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)\n            prediction_dict[row_id] = label_string\n    return prediction_dict","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.032111,"end_time":"2020-08-23T10:39:06.011105","exception":false,"start_time":"2020-08-23T10:39:05.978994","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-05-28T05:11:39.335297Z","iopub.execute_input":"2021-05-28T05:11:39.335716Z","iopub.status.idle":"2021-05-28T05:11:39.354175Z","shell.execute_reply.started":"2021-05-28T05:11:39.335683Z","shell.execute_reply":"2021-05-28T05:11:39.353309Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import timm\nclass AudioParams:\n    sr = 32000\n    stride = 5\n    true_kernel_size = 5\n\n    img_size = None\n    \n    # Melspectrogram\n    n_mels = 128\n    fmin = 20\n    fmax = 16000","metadata":{"execution":{"iopub.status.busy":"2021-05-28T05:10:06.82754Z","iopub.execute_input":"2021-05-28T05:10:06.827996Z","iopub.status.idle":"2021-05-28T05:10:06.859761Z","shell.execute_reply.started":"2021-05-28T05:10:06.827951Z","shell.execute_reply":"2021-05-28T05:10:06.85889Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def prediction(test_df,\n               test_audio,\n               weight_path,\n               target_sr,\n               threshold=0.5):\n    \n    model = BirdCLEFNet('resnext50_32x4d',AudioParams)\n    model.to('cuda')\n    model.load_state_dict(torch.load('../input/cornell-data-downloading-version1/birdclefnet_f0_best_model_resnext50_32x4dtry7_cornell(30).pth'))\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                                                  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","metadata":{"papermill":{"duration":0.02217,"end_time":"2020-08-23T10:39:06.040989","exception":false,"start_time":"2020-08-23T10:39:06.018819","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-05-28T05:10:49.36419Z","iopub.execute_input":"2021-05-28T05:10:49.364579Z","iopub.status.idle":"2021-05-28T05:10:49.375536Z","shell.execute_reply.started":"2021-05-28T05:10:49.364544Z","shell.execute_reply":"2021-05-28T05:10:49.374665Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Prediction","metadata":{"papermill":{"duration":0.007197,"end_time":"2020-08-23T10:39:06.055913","exception":false,"start_time":"2020-08-23T10:39:06.048716","status":"completed"},"tags":[]}},{"cell_type":"code","source":"submission = prediction(test_df=test,\n                           test_audio=TEST_AUDIO_DIR,\n                           weight_path=None,\n                           target_sr=32000,\n                           threshold=0.5)\nsubmission.to_csv(\"submission.csv\", index=False)","metadata":{"_kg_hide-output":true,"papermill":{"duration":24.652942,"end_time":"2020-08-23T10:39:30.716743","exception":false,"start_time":"2020-08-23T10:39:06.063801","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-05-28T05:11:42.70306Z","iopub.execute_input":"2021-05-28T05:11:42.703605Z","iopub.status.idle":"2021-05-28T05:11:59.449711Z","shell.execute_reply.started":"2021-05-28T05:11:42.703561Z","shell.execute_reply":"2021-05-28T05:11:59.448761Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission","metadata":{"papermill":{"duration":0.0427,"end_time":"2020-08-23T10:39:30.771919","exception":false,"start_time":"2020-08-23T10:39:30.729219","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-05-28T05:12:02.89304Z","iopub.execute_input":"2021-05-28T05:12:02.893389Z","iopub.status.idle":"2021-05-28T05:12:02.917539Z","shell.execute_reply.started":"2021-05-28T05:12:02.893356Z","shell.execute_reply":"2021-05-28T05:12:02.91691Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission['birds'].value_counts()","metadata":{"papermill":{"duration":0.02511,"end_time":"2020-08-23T10:39:30.810179","exception":false,"start_time":"2020-08-23T10:39:30.785069","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2021-05-28T05:12:08.127474Z","iopub.execute_input":"2021-05-28T05:12:08.127806Z","iopub.status.idle":"2021-05-28T05:12:08.137635Z","shell.execute_reply.started":"2021-05-28T05:12:08.127774Z","shell.execute_reply":"2021-05-28T05:12:08.136648Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## EOF","metadata":{"papermill":{"duration":0.013182,"end_time":"2020-08-23T10:39:30.836469","exception":false,"start_time":"2020-08-23T10:39:30.823287","status":"completed"},"tags":[]}}]}