{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"import os\n\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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nIMAGE_SIZE = 512","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def auto_select_accelerator():\n    \"\"\"\n    Reference: \n        * https://www.kaggle.com/mgornergoogle/getting-started-with-100-flowers-on-tpu\n        * https://www.kaggle.com/xhlulu/ranzcr-efficientnet-tpu-training\n    \"\"\"\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    return strategy\n\n\n\ndef build_decoder(with_labels=True, target_size=(IMAGE_SIZE, IMAGE_SIZE), 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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"COMPETITION_NAME = \"ranzcr-clip-catheter-line-classification\"\nstrategy = auto_select_accelerator()\nBATCH_SIZE = strategy.num_replicas_in_sync * 16\nGCS_DS_PATH = KaggleDatasets().get_gcs_path(COMPETITION_NAME)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"load_dir = f\"/kaggle/input/{COMPETITION_NAME}/\"\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:]\n\ntest_decoder = build_decoder(with_labels=False, target_size=(IMAGE_SIZE, IMAGE_SIZE))\ndtest = build_dataset(\n    test_paths, bsize=BATCH_SIZE, repeat=False, \n    shuffle=False, augment=False, cache=False,\n    decode_fn=test_decoder\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nwith strategy.scope():\n    model = tf.keras.models.load_model(\"../input/inception-fold-0/model_fold_0.h5\")\n    \nsub_df[label_cols] = model.predict(dtest, verbose=1) \n    \n    \nsub_df.to_csv('submission.csv', index=False)\n\nsub_df.head()","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}