{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install iterative-stratification","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import tensorflow as tf\nimport tensorflow_addons as tfa\nimport numpy as np\nfrom pathlib import Path\nimport io\nimport matplotlib.pyplot as plt\nimport soundfile as sf\nimport librosa\nfrom kaggle_datasets import KaggleDatasets\nfrom tqdm import tqdm\nimport pandas as pd\n# from sklearn.model_selection import StratifiedKFold\nfrom iterstrat.ml_stratifiers import MultilabelStratifiedKFold\nimport seaborn as sns\nfrom IPython.display import Audio\nimport cv2\n\ntf.__version__","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cfg = {\n    'parse_params': {\n        'cut_time': 10,\n    },\n    'data_params': {\n        'sample_time': 6, # assert 60 % sample_time == 0\n        'spec_fmax': 24000.0,\n        'spec_fmin': 40.0,\n        'spec_mel': 224,\n        'mel_power': 2,\n        'img_shape': (224, 512)\n    },\n    'model_params': {\n        'batchsize_per_tpu': 16,\n        'iteration_per_epoch': 64,\n        'epoch': 15,\n        'arch': tf.keras.applications.ResNet50,\n        'arch_preprocess': tf.keras.applications.resnet50.preprocess_input,\n        'freeze_to': 0,  # Freeze to backbone.layers[:freeze_to]. If None, all layers in the backbone will be freezed.\n        'loss': {\n            'fn': tfa.losses.SigmoidFocalCrossEntropy,\n            'params': {},\n        },\n        'optim': {\n            'fn': tfa.optimizers.RectifiedAdam,\n            'params': {'lr': 1e-3, 'total_steps': 15*64, 'warmup_proportion': 0.3, 'min_lr': 1e-6},\n        },\n        'mixup': False\n    }\n}","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# detect and init the TPU\ntpu = tf.distribute.cluster_resolver.TPUClusterResolver()\ntf.config.experimental_connect_to_cluster(tpu)\ntf.tpu.experimental.initialize_tpu_system(tpu)\nprint(\"All devices: \", tf.config.list_logical_devices('TPU'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"strategy = tf.distribute.experimental.TPUStrategy(tpu)\nAUTOTUNE = tf.data.experimental.AUTOTUNE\nGCS_DS_PATH = KaggleDatasets().get_gcs_path()\n\nTRAIN_TFREC = GCS_DS_PATH + \"/tfrecords/train\"\nTEST_TFREC = GCS_DS_PATH + \"/tfrecords/test\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"CUT = cfg['parse_params']['cut_time']\nSR = 48000     # all wave's sample rate may be 48k\n\nTIME = cfg['data_params']['sample_time']\n\nFMAX = cfg['data_params']['spec_fmax']\nFMIN = cfg['data_params']['spec_fmin']\nN_MEL = cfg['data_params']['spec_mel']\n\nHEIGHT, WIDTH = cfg['data_params']['img_shape']\n\nCLASS_N = 24","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h2> Lets Explore the tfrecords, Create dataset </h2>"},{"metadata":{"trusted":true},"cell_type":"code","source":"raw_dataset = tf.data.TFRecordDataset([TRAIN_TFREC + '/00-148.tfrec'])\nraw_dataset","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h2> parse tfrecords </h3>"},{"metadata":{"trusted":true},"cell_type":"code","source":"feature_description = {\n    'recording_id': tf.io.FixedLenFeature([], tf.string, default_value=''),\n    'audio_wav': tf.io.FixedLenFeature([], tf.string, default_value=''),\n    'label_info': tf.io.FixedLenFeature([], tf.string, default_value=''),\n}\nparse_dtype = {\n    'audio_wav': tf.float32,\n    'recording_id': tf.string,\n    'species_id': tf.int32,\n    'songtype_id': tf.int32,\n    't_min': tf.float32,\n    'f_min': tf.float32,\n    't_max': tf.float32,\n    'f_max':tf.float32,\n    'is_tp': tf.int32\n}\n\n@tf.function\ndef _parse_function(example_proto):\n    sample = tf.io.parse_single_example(example_proto, feature_description)\n    wav, _ = tf.audio.decode_wav(sample['audio_wav'], desired_channels=1) # mono\n    label_info = tf.strings.split(sample['label_info'], sep='\"')[1]\n    labels = tf.strings.split(label_info, sep=';')\n    \n    @tf.function\n    def _cut_audio(label):\n        items = tf.strings.split(label, sep=',')\n        spid = tf.squeeze(tf.strings.to_number(items[0], tf.int32))\n        soid = tf.squeeze(tf.strings.to_number(items[1], tf.int32))\n        tmin = tf.squeeze(tf.strings.to_number(items[2]))\n        fmin = tf.squeeze(tf.strings.to_number(items[3]))\n        tmax = tf.squeeze(tf.strings.to_number(items[4]))\n        fmax = tf.squeeze(tf.strings.to_number(items[5]))\n        tp = tf.squeeze(tf.strings.to_number(items[6], tf.int32))\n\n        tmax_s = tmax * tf.cast(SR, tf.float32)\n        tmin_s = tmin * tf.cast(SR, tf.float32)\n        cut_s = tf.cast(CUT * SR, tf.float32)\n        all_s = tf.cast(60 * SR, tf.float32)\n        tsize_s = tmax_s - tmin_s\n        cut_min = tf.cast(\n            tf.maximum(0.0, \n                tf.minimum(tmin_s - (cut_s - tsize_s) / 2,\n                           tf.minimum(tmax_s + (cut_s - tsize_s) / 2, all_s) - cut_s)\n            ), tf.int32\n        )\n        cut_max = cut_min + CUT * SR\n        \n        _sample = {\n            'audio_wav': tf.reshape(wav[cut_min:cut_max], [CUT*SR]),\n            'recording_id': sample['recording_id'],\n            'species_id': spid,\n            'songtype_id': soid,\n            't_min': tmin - tf.cast(cut_min, tf.float32)/tf.cast(SR, tf.float32),\n            'f_min': fmin,\n            't_max': tmax - tf.cast(cut_min, tf.float32)/tf.cast(SR, tf.float32),\n            'f_max': fmax,\n            'is_tp': tp\n        }\n        return _sample\n    \n    samples = tf.map_fn(_cut_audio, labels, dtype=parse_dtype)\n    return samples\n\nparsed_dataset = raw_dataset.map(_parse_function).unbatch()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"@tf.function\ndef _cut_wav(x):\n    # random cut in training\n    cut_min = tf.random.uniform([], maxval=tf.minimum((CUT-TIME) * SR, tf.cast(x['t_max'] * SR, tf.int32)), dtype=tf.int32)\n    cut_max = cut_min + TIME * SR\n    cutwave = tf.reshape(x['audio_wav'][cut_min:cut_max], [TIME*SR])\n    y = {}\n    y.update(x)\n    y['audio_wav'] = cutwave\n    y['t_min'] = tf.maximum(0.0, x['t_min'] - tf.cast(cut_min, tf.float32) / SR)\n    y['t_max'] = tf.maximum(0.0, x['t_max'] - tf.cast(cut_min, tf.float32) / SR)\n    return y\n\n@tf.function\ndef _cut_wav_val(x):\n    # center crop in validation\n    cut_min = tf.minimum((CUT-TIME)*SR // 2, tf.cast((x['t_min'] + x['t_max']) / 2 * SR, tf.int32))\n    cut_max = cut_min + TIME * SR\n    cutwave = tf.reshape(x['audio_wav'][cut_min:cut_max], [TIME*SR])\n    \n    y = {}\n    y.update(x)\n    y['audio_wav'] = cutwave\n    y['t_min'] = tf.maximum(0.0, x['t_min'] - tf.cast(cut_min, tf.float32) / SR)\n    y['t_max'] = tf.maximum(0.0, x['t_max'] - tf.cast(cut_min, tf.float32) / SR)\n    return y\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"@tf.function\ndef _filtTP(x):\n    return x['is_tp'] == 1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def show_wav(sample, ax):\n    print(sample)\n    wav = sample[\"audio_wav\"].numpy()\n    rate = SR\n    ax.plot(np.arange(len(wav)) / rate, wav)\n    #print(type(np.arange(len(wav)) / rate), type(wav))\n    #print((np.arange(len(wav)) / rate).shape, wav.shape)\n    ax.set_title(\n        sample[\"recording_id\"].numpy().decode()\n        + (\"/%d\" % sample[\"species_id\"])\n        + (\"TP\" if sample[\"is_tp\"] else \"FP\"))\n\n    return Audio((wav * 2**15).astype(np.int16), rate=rate)\n\nfig, ax = plt.subplots(figsize=(20, 3))\nshow_wav(next(iter(parsed_dataset)), ax)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"<h2> create mel-spectrogram </h2>"},{"metadata":{"trusted":true},"cell_type":"code","source":"@tf.function\ndef _wav_to_spec(x):\n    mel_power = cfg['data_params']['mel_power']\n    \n    stfts = tf.signal.stft(x[\"audio_wav\"], frame_length=2048, frame_step=512, fft_length=2048)\n    spectrograms = tf.abs(stfts) ** mel_power\n    \n    # warp the linear scale spectrograms into the mel-scale\n    num_spectrogram_bins = stfts.shape[-1]\n    lower_edge_hertz, upper_edge_hertz, num_mel_bins = FMIN, FMAX, N_MEL\n    \n    linear_to_mel_weight_matrix = tf.signal.linear_to_mel_weight_matrix(\n        num_mel_bins, num_spectrogram_bins, SR, lower_edge_hertz,\n        upper_edge_hertz)\n    \n    mel_spectrograms = tf.tensordot(\n        spectrograms, linear_to_mel_weight_matrix, 1)\n    mel_spectrograms.set_shape(spectrograms.shape[:-1].concatenate(\n        linear_to_mel_weight_matrix.shape[-1:]))\n    \n    # Compute a stabilized log to get log-magnitude mel-scale spectrograms.\n    log_mel_spectrograms = tf.math.log(mel_spectrograms + 1e-6)\n    \n    y = {\n        'audio_spec': tf.transpose(log_mel_spectrograms), # (num_mel_bins, frames)\n    }\n    y.update(x)\n    return y\n\nspec_dataset = parsed_dataset.filter(_filtTP).map(_cut_wav).map(_wav_to_spec)","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}