{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":91844,"databundleVersionId":11361821,"isSourceIdPinned":false,"sourceType":"competition"},{"sourceId":11488494,"sourceType":"datasetVersion","datasetId":7201132}],"dockerImageVersionId":31012,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import os\nimport gc\nimport warnings\nimport logging\nimport time\nimport math\nimport cv2\nfrom pathlib import Path\n\nimport numpy as np\nimport pandas as pd\nimport librosa\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nimport timm\nfrom tqdm.auto import tqdm\n\nwarnings.filterwarnings(\"ignore\")\nlogging.basicConfig(level=logging.ERROR)","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"jupyter":{"source_hidden":true},"execution":{"iopub.status.busy":"2025-04-20T11:19:44.782529Z","iopub.execute_input":"2025-04-20T11:19:44.782831Z","iopub.status.idle":"2025-04-20T11:19:57.060448Z","shell.execute_reply.started":"2025-04-20T11:19:44.782786Z","shell.execute_reply":"2025-04-20T11:19:57.059214Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#自定义类\nimport torch\nimport torch.nn as nn\n\nclass CBAM(nn.Module):\n    def __init__(self, channel, reduction=16, spatial_kernel=7):\n        super(CBAM, self).__init__()\n \n        # channel attention 压缩H,W为1\n        self.max_pool = nn.AdaptiveMaxPool2d(1)\n        self.avg_pool = nn.AdaptiveAvgPool2d(1)\n \n        # shared MLP\n        self.mlp = nn.Sequential(\n            # Conv2d比Linear方便操作\n            # nn.Linear(channel, channel // reduction, bias=False)\n            nn.Conv2d(channel, channel // reduction, 1, bias=False),\n            # inplace=True直接替换，节省内存\n            nn.ReLU(inplace=True),\n            # nn.Linear(channel // reduction, channel,bias=False)\n            nn.Conv2d(channel // reduction, channel, 1, bias=False)\n        )\n \n        # spatial attention\n        self.conv = nn.Conv2d(2, 1, kernel_size=spatial_kernel,\n                              padding=spatial_kernel // 2, bias=False)\n        self.sigmoid = nn.Sigmoid()\n \n    def forward(self, x):\n        max_out = self.mlp(self.max_pool(x))\n        avg_out = self.mlp(self.avg_pool(x))\n        channel_out = self.sigmoid(max_out + avg_out)\n        x = channel_out * x\n \n        max_out, _ = torch.max(x, dim=1, keepdim=True)\n        avg_out = torch.mean(x, dim=1, keepdim=True)\n        spatial_out = self.sigmoid(self.conv(torch.cat([max_out, avg_out], dim=1)))\n        x = spatial_out * x\n        return x\n\n\n\nclass GeM(nn.Module):\n    def __init__(self, p_init=3.0, eps=1e-6):\n        super().__init__()\n        self.p = nn.Parameter(torch.tensor(p_init, dtype=torch.float32))\n        self.eps = eps\n\n    def forward(self, x):\n        p = self.p.clamp(min=1e-6)\n        x = x.clamp(min=self.eps)\n        return x.pow(p).mean(dim=(-2, -1)).pow(1./p)","metadata":{"trusted":true,"jupyter":{"source_hidden":true},"execution":{"iopub.status.busy":"2025-04-20T11:19:57.061651Z","iopub.execute_input":"2025-04-20T11:19:57.061904Z","iopub.status.idle":"2025-04-20T11:19:57.069616Z","shell.execute_reply.started":"2025-04-20T11:19:57.061886Z","shell.execute_reply":"2025-04-20T11:19:57.068951Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class CFG:\n\n    pretrained = False\n    \n    test_soundscapes = '/kaggle/input/birdclef-2025/test_soundscapes'\n    submission_csv = '/kaggle/input/birdclef-2025/sample_submission.csv'\n    taxonomy_csv = '/kaggle/input/birdclef-2025/taxonomy.csv'\n    model_path = '/kaggle/input/birdmodelv3'  \n\n\n    # Audio parameters\n    FS = 32000  \n    WINDOW_SIZE = 5  \n    \n    # Mel spectrogram parameters\n    N_FFT = 1024\n    HOP_LENGTH = 512\n    N_MELS = 128\n    FMIN = 50\n    FMAX = 14000\n    TARGET_SHAPE = (256, 256)\n    \n    model_name = 'efficientnet_b0'\n    in_channels = 1\n    device = 'cpu' \n\n    # Inference parameters\n    batch_size = 16\n    use_tta = False  \n    tta_count = 3   \n    threshold = 0.5\n    \n    use_specific_folds = False  # If False, use all found models\n    folds = [0, 1]  # Used only if use_specific_folds is True\n    \n    debug = False\n    debug_count = 3\n\n\ncfg = CFG()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-04-20T11:19:57.070192Z","iopub.execute_input":"2025-04-20T11:19:57.070355Z","iopub.status.idle":"2025-04-20T11:19:57.101936Z","shell.execute_reply.started":"2025-04-20T11:19:57.070332Z","shell.execute_reply":"2025-04-20T11:19:57.100970Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(f\"Using device: {cfg.device}\")\nprint(f\"Loading taxonomy data...\")\ntaxonomy_df = pd.read_csv(cfg.taxonomy_csv)\nspecies_ids = taxonomy_df['primary_label'].tolist()\nnum_classes = len(species_ids)\nprint(f\"Number of classes: {num_classes}\")","metadata":{"trusted":true,"jupyter":{"source_hidden":true},"execution":{"iopub.status.busy":"2025-04-20T11:19:57.103860Z","iopub.execute_input":"2025-04-20T11:19:57.104127Z","iopub.status.idle":"2025-04-20T11:19:57.142760Z","shell.execute_reply.started":"2025-04-20T11:19:57.104105Z","shell.execute_reply":"2025-04-20T11:19:57.141843Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class BirdCLEFModel(nn.Module):\n    def __init__(self, cfg, num_classes):\n        super().__init__()\n        self.cfg = cfg\n\n        taxonomy_df = pd.read_csv(cfg.taxonomy_csv)\n        cfg.num_classes = len(taxonomy_df)\n\n        self.backbone = timm.create_model(\n            cfg.model_name,\n            pretrained=cfg.pretrained,\n            in_chans=cfg.in_channels,\n            drop_rate=0.2,\n            drop_path_rate=0.2\n        )\n\n        if 'efficientnet' in cfg.model_name:\n            backbone_out = self.backbone.classifier.in_features\n            self.backbone.classifier = nn.Identity()\n        elif 'resnet' in cfg.model_name:\n            backbone_out = self.backbone.fc.in_features\n            self.backbone.fc = nn.Identity()\n        else:\n            backbone_out = self.backbone.get_classifier().in_features\n            self.backbone.reset_classifier(0, '')\n\n        self.cbam = CBAM(backbone_out)\n        self.pool = GeM()\n        # self.pooling = nn.AdaptiveAvgPool2d(1)\n\n        self.feat_dim = backbone_out\n\n        # self.classifier = nn.Linear(backbone_out, cfg.num_classes)\n        # 分类头\n        self.classifier = nn.Sequential(\n            nn.Linear(backbone_out, 512),\n            nn.BatchNorm1d(512),\n            nn.SiLU(),\n            nn.Dropout(0.3),\n            nn.Linear(512, cfg.num_classes)\n        )\n\n    def forward(self, x, targets=None):\n\n        features = self.backbone(x)\n\n        if isinstance(features, dict):\n            features = features['features']\n\n        if len(features.shape) == 4:\n            features = self.cbam(features)\n            features = self.pool(features)\n            features = features.view(features.size(0), -1)\n\n        logits = self.classifier(features)\n\n        return logits","metadata":{"trusted":true,"jupyter":{"source_hidden":true},"execution":{"iopub.status.busy":"2025-04-20T11:19:57.143880Z","iopub.execute_input":"2025-04-20T11:19:57.144180Z","iopub.status.idle":"2025-04-20T11:19:57.151484Z","shell.execute_reply.started":"2025-04-20T11:19:57.144161Z","shell.execute_reply":"2025-04-20T11:19:57.150659Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def audio2melspec(audio_data, cfg):\n    \"\"\"Convert audio data to mel spectrogram\"\"\"\n    if np.isnan(audio_data).any():\n        mean_signal = np.nanmean(audio_data)\n        audio_data = np.nan_to_num(audio_data, nan=mean_signal)\n\n    mel_spec = librosa.feature.melspectrogram(\n        y=audio_data,\n        sr=cfg.FS,\n        n_fft=cfg.N_FFT,\n        hop_length=cfg.HOP_LENGTH,\n        n_mels=cfg.N_MELS,\n        fmin=cfg.FMIN,\n        fmax=cfg.FMAX,\n        power=2.0\n    )\n\n    mel_spec_db = librosa.power_to_db(mel_spec, ref=np.max)\n    mel_spec_norm = (mel_spec_db - mel_spec_db.min()) / (mel_spec_db.max() - mel_spec_db.min() + 1e-8)\n    \n    return mel_spec_norm\n\ndef process_audio_segment(audio_data, cfg):\n    \"\"\"Process audio segment to get mel spectrogram\"\"\"\n    if len(audio_data) < cfg.FS * cfg.WINDOW_SIZE:\n        audio_data = np.pad(audio_data, \n                          (0, cfg.FS * cfg.WINDOW_SIZE - len(audio_data)), \n                          mode='constant')\n    \n    mel_spec = audio2melspec(audio_data, cfg)\n    \n    # Resize if needed\n    if mel_spec.shape != cfg.TARGET_SHAPE:\n        mel_spec = cv2.resize(mel_spec, cfg.TARGET_SHAPE, interpolation=cv2.INTER_LINEAR)\n        \n    return mel_spec.astype(np.float32)","metadata":{"trusted":true,"jupyter":{"source_hidden":true},"execution":{"iopub.status.busy":"2025-04-20T11:19:57.152644Z","iopub.execute_input":"2025-04-20T11:19:57.153193Z","iopub.status.idle":"2025-04-20T11:19:57.177526Z","shell.execute_reply.started":"2025-04-20T11:19:57.153168Z","shell.execute_reply":"2025-04-20T11:19:57.176755Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def find_model_files(cfg):\n    \"\"\"\n    Find all .pth model files in the specified model directory\n    \"\"\"\n    model_files = []\n    \n    model_dir = Path(cfg.model_path)\n    \n    for path in model_dir.glob('**/*.pth'):\n        model_files.append(str(path))\n    \n    return model_files\n\ndef load_models(cfg, num_classes):\n    \"\"\"\n    Load all found model files and prepare them for ensemble\n    \"\"\"\n    models = []\n    \n    model_files = find_model_files(cfg)\n    \n    if not model_files:\n        print(f\"Warning: No model files found under {cfg.model_path}!\")\n        return models\n    \n    print(f\"Found a total of {len(model_files)} model files.\")\n    \n    if cfg.use_specific_folds:\n        filtered_files = []\n        for fold in cfg.folds:\n            fold_files = [f for f in model_files if f\"fold{fold}\" in f]\n            filtered_files.extend(fold_files)\n        model_files = filtered_files\n        print(f\"Using {len(model_files)} model files for the specified folds ({cfg.folds}).\")\n    \n    for model_path in model_files:\n        try:\n            print(f\"Loading model: {model_path}\")\n            checkpoint = torch.load(model_path, map_location=torch.device(cfg.device))\n            \n            model = BirdCLEFModel(cfg, num_classes)\n            model.load_state_dict(checkpoint['model_state_dict'])\n            model = model.to(cfg.device)\n            model.eval()\n            \n            models.append(model)\n        except Exception as e:\n            print(f\"Error loading model {model_path}: {e}\")\n    \n    return models\n\ndef predict_on_spectrogram(audio_path, models, cfg, species_ids):\n    \"\"\"Process a single audio file and predict species presence for each 5-second segment\"\"\"\n    predictions = []\n    row_ids = []\n    soundscape_id = Path(audio_path).stem\n    \n    try:\n        print(f\"Processing {soundscape_id}\")\n        audio_data, _ = librosa.load(audio_path, sr=cfg.FS)\n        \n        total_segments = int(len(audio_data) / (cfg.FS * cfg.WINDOW_SIZE))\n        \n        for segment_idx in range(total_segments):\n            start_sample = segment_idx * cfg.FS * cfg.WINDOW_SIZE\n            end_sample = start_sample + cfg.FS * cfg.WINDOW_SIZE\n            segment_audio = audio_data[start_sample:end_sample]\n            \n            end_time_sec = (segment_idx + 1) * cfg.WINDOW_SIZE\n            row_id = f\"{soundscape_id}_{end_time_sec}\"\n            row_ids.append(row_id)\n\n            if cfg.use_tta:\n                all_preds = []\n                \n                for tta_idx in range(cfg.tta_count):\n                    mel_spec = process_audio_segment(segment_audio, cfg)\n                    mel_spec = apply_tta(mel_spec, tta_idx)\n\n                    mel_spec = torch.tensor(mel_spec, dtype=torch.float32).unsqueeze(0).unsqueeze(0)\n                    mel_spec = mel_spec.to(cfg.device)\n\n                    if len(models) == 1:\n                        with torch.no_grad():\n                            outputs = models[0](mel_spec)\n                            probs = torch.sigmoid(outputs).cpu().numpy().squeeze()\n                            all_preds.append(probs)\n                    else:\n                        segment_preds = []\n                        for model in models:\n                            with torch.no_grad():\n                                outputs = model(mel_spec)\n                                probs = torch.sigmoid(outputs).cpu().numpy().squeeze()\n                                segment_preds.append(probs)\n                        \n                        avg_preds = np.mean(segment_preds, axis=0)\n                        all_preds.append(avg_preds)\n\n                final_preds = np.mean(all_preds, axis=0)\n            else:\n                mel_spec = process_audio_segment(segment_audio, cfg)\n                \n                mel_spec = torch.tensor(mel_spec, dtype=torch.float32).unsqueeze(0).unsqueeze(0)\n                mel_spec = mel_spec.to(cfg.device)\n                \n                if len(models) == 1:\n                    with torch.no_grad():\n                        outputs = models[0](mel_spec)\n                        final_preds = torch.sigmoid(outputs).cpu().numpy().squeeze()\n                else:\n                    segment_preds = []\n                    for model in models:\n                        with torch.no_grad():\n                            outputs = model(mel_spec)\n                            probs = torch.sigmoid(outputs).cpu().numpy().squeeze()\n                            segment_preds.append(probs)\n\n                    final_preds = np.mean(segment_preds, axis=0)\n                    \n            predictions.append(final_preds)\n            \n    except Exception as e:\n        print(f\"Error processing {audio_path}: {e}\")\n    \n    return row_ids, predictions","metadata":{"trusted":true,"jupyter":{"source_hidden":true},"execution":{"iopub.status.busy":"2025-04-20T11:19:57.178449Z","iopub.execute_input":"2025-04-20T11:19:57.178754Z","iopub.status.idle":"2025-04-20T11:19:57.198585Z","shell.execute_reply.started":"2025-04-20T11:19:57.178731Z","shell.execute_reply":"2025-04-20T11:19:57.197523Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def apply_tta(spec, tta_idx):\n    \"\"\"Apply test-time augmentation\"\"\"\n    if tta_idx == 0:\n        # Original spectrogram\n        return spec\n    elif tta_idx == 1:\n        # Time shift (horizontal flip)\n        return np.flip(spec, axis=1)\n    elif tta_idx == 2:\n        # Frequency shift (vertical flip)\n        return np.flip(spec, axis=0)\n    else:\n        return spec\n\ndef run_inference(cfg, models, species_ids):\n    \"\"\"Run inference on all test soundscapes\"\"\"\n    test_files = list(Path(cfg.test_soundscapes).glob('*.ogg'))\n    \n    if cfg.debug:\n        print(f\"Debug mode enabled, using only {cfg.debug_count} files\")\n        test_files = test_files[:cfg.debug_count]\n    \n    print(f\"Found {len(test_files)} test soundscapes\")\n\n    all_row_ids = []\n    all_predictions = []\n\n    for audio_path in tqdm(test_files):\n        row_ids, predictions = predict_on_spectrogram(str(audio_path), models, cfg, species_ids)\n        all_row_ids.extend(row_ids)\n        all_predictions.extend(predictions)\n    \n    return all_row_ids, all_predictions\n\ndef create_submission(row_ids, predictions, species_ids, cfg):\n    \"\"\"Create submission dataframe\"\"\"\n    print(\"Creating submission dataframe...\")\n\n    submission_dict = {'row_id': row_ids}\n    \n    for i, species in enumerate(species_ids):\n        submission_dict[species] = [pred[i] for pred in predictions]\n\n    submission_df = pd.DataFrame(submission_dict)\n\n    submission_df.set_index('row_id', inplace=True)\n\n    sample_sub = pd.read_csv(cfg.submission_csv, index_col='row_id')\n\n    missing_cols = set(sample_sub.columns) - set(submission_df.columns)\n    if missing_cols:\n        print(f\"Warning: Missing {len(missing_cols)} species columns in submission\")\n        for col in missing_cols:\n            submission_df[col] = 0.0\n\n    submission_df = submission_df[sample_sub.columns]\n\n    submission_df = submission_df.reset_index()\n    \n    return submission_df\n","metadata":{"trusted":true,"jupyter":{"source_hidden":true},"execution":{"iopub.status.busy":"2025-04-20T11:19:57.199523Z","iopub.execute_input":"2025-04-20T11:19:57.199798Z","iopub.status.idle":"2025-04-20T11:19:57.223406Z","shell.execute_reply.started":"2025-04-20T11:19:57.199775Z","shell.execute_reply":"2025-04-20T11:19:57.222439Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def main():\n    start_time = time.time()\n    print(\"Starting BirdCLEF-2025 inference...\")\n    print(f\"TTA enabled: {cfg.use_tta} (variations: {cfg.tta_count if cfg.use_tta else 0})\")\n\n    models = load_models(cfg, num_classes)\n    \n    if not models:\n        print(\"No models found! Please check model paths.\")\n        return\n    \n    print(f\"Model usage: {'Single model' if len(models) == 1 else f'Ensemble of {len(models)} models'}\")\n\n    row_ids, predictions = run_inference(cfg, models, species_ids)\n\n    submission_df = create_submission(row_ids, predictions, species_ids, cfg)\n\n    submission_path = 'submission.csv'\n    submission_df.to_csv(submission_path, index=False)\n    print(f\"Submission saved to {submission_path}\")\n    \n    end_time = time.time()\n    print(f\"Inference completed in {(end_time - start_time)/60:.2f} minutes\")","metadata":{"trusted":true,"jupyter":{"source_hidden":true},"execution":{"iopub.status.busy":"2025-04-20T11:19:57.224410Z","iopub.execute_input":"2025-04-20T11:19:57.224691Z","iopub.status.idle":"2025-04-20T11:19:57.244987Z","shell.execute_reply.started":"2025-04-20T11:19:57.224669Z","shell.execute_reply":"2025-04-20T11:19:57.244328Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"if __name__ == \"__main__\":\n    main()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-04-18T13:32:06.847737Z","iopub.execute_input":"2025-04-18T13:32:06.848115Z","iopub.status.idle":"2025-04-18T13:32:07.142584Z","shell.execute_reply.started":"2025-04-18T13:32:06.848091Z","shell.execute_reply":"2025-04-18T13:32:07.141660Z"}},"outputs":[],"execution_count":null}]}