{"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":"import os\n\n# import efficientnet.tfkeras as efn\nimport numpy as np\nimport pandas as pd\nfrom kaggle_datasets import KaggleDatasets\nfrom sklearn.model_selection import train_test_split\nimport tensorflow as tf\nimport tensorflow.keras.applications.efficientnet as efn","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Helper functions","metadata":{}},{"cell_type":"markdown","source":"The following functions are hidden:\n```python\nauto_select_accelerator()\n\nbuild_decoder(with_labels=True, target_size=(256, 256), ext='jpg')\n\nbuild_augmenter(with_labels=True)\n\nbuild_dataset(paths, labels=None, bsize=32, cache=True,\n              decode_fn=None, augment_fn=None,\n              augment=True, repeat=True, shuffle=1024, \n              cache_dir=\"\")\n```\n\nUnhide below to see:","metadata":{}},{"cell_type":"code","source":"def auto_select_accelerator():\n    try:\n        tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\n        tf.config.experimental_connect_to_cluster(tpu)\n        tf.tpu.experimental.initialize_tpu_system(tpu)\n        strategy = tf.distribute.experimental.TPUStrategy(tpu)\n        print(\"Running on TPU:\", tpu.master())\n    except ValueError:\n        strategy = tf.distribute.get_strategy()\n    print(f\"Running on {strategy.num_replicas_in_sync} replicas\")\n    \n    return strategy\n\n\ndef build_decoder(with_labels=True, target_size=(300, 300), ext='jpg'):\n    def decode(path):\n        file_bytes = tf.io.read_file(path)\n        if ext == 'png':\n            img = tf.image.decode_png(file_bytes, channels=3)\n        elif ext in ['jpg', 'jpeg']:\n            img = tf.image.decode_jpeg(file_bytes, channels=3)\n        else:\n            raise ValueError(\"Image extension not supported\")\n\n        img = tf.cast(img, tf.float32) / 255.0\n        img = tf.image.resize(img, target_size)\n\n        return img\n    \n    def decode_with_labels(path, label):\n        return decode(path), label\n    \n    return decode_with_labels if with_labels else decode\n\n\ndef build_augmenter(with_labels=True):\n    def augment(img):\n        img = tf.image.random_flip_left_right(img)\n        img = tf.image.random_flip_up_down(img)\n        return img\n    \n    def augment_with_labels(img, label):\n        return augment(img), label\n    \n    return augment_with_labels if with_labels else augment\n\n\ndef build_dataset(paths, labels=None, bsize=32, cache=True,\n                  decode_fn=None, augment_fn=None,\n                  augment=True, repeat=True, shuffle=1024, \n                  cache_dir=\"\"):\n    if cache_dir != \"\" and cache is True:\n        os.makedirs(cache_dir, exist_ok=True)\n    \n    if decode_fn is None:\n        decode_fn = build_decoder(labels is not None)\n    \n    if augment_fn is None:\n        augment_fn = build_augmenter(labels is not None)\n    \n    AUTO = tf.data.experimental.AUTOTUNE\n    slices = paths if labels is None else (paths, labels)\n    \n    dset = tf.data.Dataset.from_tensor_slices(slices)\n    dset = dset.map(decode_fn, num_parallel_calls=AUTO)\n    dset = dset.cache(cache_dir) if cache else dset\n    dset = dset.map(augment_fn, num_parallel_calls=AUTO) if augment else dset\n    dset = dset.repeat() if repeat else dset\n    dset = dset.shuffle(shuffle) if shuffle else dset\n    dset = dset.batch(bsize).prefetch(AUTO)\n    \n    return dset","metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Variables and configurations","metadata":{}},{"cell_type":"code","source":"COMPETITION_NAME = \"ranzcr-clip-catheter-line-classification\"\nstrategy = auto_select_accelerator()\nBATCH_SIZE = strategy.num_replicas_in_sync * 16\n# GCS_DS_PATH = KaggleDatasets().get_gcs_path(COMPETITION_NAME)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Preparing dataset","metadata":{}},{"cell_type":"markdown","source":"### Loading and preprocess CSVs","metadata":{}},{"cell_type":"code","source":"load_dir = f\"/kaggle/input/{COMPETITION_NAME}/\"\ndf = pd.read_csv(load_dir + 'train.csv')\npaths = load_dir + \"train/\" + df['StudyInstanceUID'] + '.jpg'\n\nsub_df = pd.read_csv(load_dir + 'sample_submission.csv')\ntest_paths = load_dir + \"test/\" + sub_df['StudyInstanceUID'] + '.jpg'\n\n# Get the multi-labels\nlabel_cols = sub_df.columns[1:]\nlabels = df[label_cols].values","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Train test split\n(\n    train_paths, valid_paths, \n    train_labels, valid_labels\n) = train_test_split(paths, labels, test_size=0.2, random_state=42)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Build the tensorflow datasets\nIMSIZES = (224, 240, 260, 300, 380, 456, 528, 600)\n# index i corresponds to b-i\nsize = IMSIZES[2]\n\ndecoder = build_decoder(with_labels=True, target_size=(size, size))\ntest_decoder = build_decoder(with_labels=False, target_size=(size, size))\n\n# Build the tensorflow datasets\ndtrain = build_dataset(\n    train_paths, train_labels, bsize=BATCH_SIZE, \n    cache_dir='/kaggle/tf_cache', decode_fn=decoder\n)\n\ndvalid = build_dataset(\n    valid_paths, valid_labels, bsize=BATCH_SIZE, \n    repeat=False, shuffle=False, augment=False, \n    cache_dir='/kaggle/tf_cache', decode_fn=decoder\n)\n\ndtest = build_dataset(\n    test_paths, bsize=BATCH_SIZE, repeat=False, \n    shuffle=False, augment=False, cache=False, \n    decode_fn=test_decoder\n)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Modeling","metadata":{}},{"cell_type":"code","source":"model_path = '../input/tfkeras-efficientnet-weights/efficientnetb2_notop.h5'  # imagenet\nn_labels = labels.shape[1]\n\nwith strategy.scope():\n    model = tf.keras.Sequential([\n        efn.EfficientNetB2(\n            input_shape=(size, size, 3),\n            weights=model_path,\n            include_top=False,\n            drop_connect_rate=0.5),\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(n_labels, activation='sigmoid')\n    ])\n    model.compile(\n        optimizer='adam',\n        loss='binary_crossentropy',\n        metrics=[tf.keras.metrics.AUC(multi_label=True)])\n    model.summary()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# ############### Train the model ###############\nsteps_per_epoch = train_paths.shape[0] // BATCH_SIZE\ncheckpoint = tf.keras.callbacks.ModelCheckpoint(\n    'model.h5', save_best_only=True, monitor='val_auc', mode='max')\nlr_reducer = tf.keras.callbacks.ReduceLROnPlateau(\n    monitor=\"val_auc\", patience=3, min_lr=1e-6, mode='max')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history = model.fit(\n    dtrain, \n    epochs=20,\n    verbose=1,\n    callbacks=[checkpoint, lr_reducer],\n    steps_per_epoch=steps_per_epoch,\n    validation_data=dvalid)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.load_weights('model.h5')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Save history","metadata":{}},{"cell_type":"code","source":"hist_df = pd.DataFrame(history.history)\nhist_df.to_csv('history.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Submission","metadata":{}},{"cell_type":"code","source":"sub_df[label_cols] = model.predict(dtest, verbose=1)\nsub_df.to_csv('submission.csv', index=False)\n\nsub_df.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}