{"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":"markdown","source":"Thanks to https://www.kaggle.com/xhlulu/ranzcr-efficientnet-tpu-training","metadata":{}},{"cell_type":"code","source":"!pip install efficientnet -q","metadata":{"execution":{"iopub.status.busy":"2022-09-22T16:03:30.221366Z","iopub.execute_input":"2022-09-22T16:03:30.222097Z","iopub.status.idle":"2022-09-22T16:03:41.288281Z","shell.execute_reply.started":"2022-09-22T16:03:30.221936Z","shell.execute_reply":"2022-09-22T16:03:41.287210Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\n\nimport 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\nfrom sklearn.model_selection import GroupKFold","metadata":{"execution":{"iopub.status.busy":"2022-09-22T16:03:41.290898Z","iopub.execute_input":"2022-09-22T16:03:41.291355Z","iopub.status.idle":"2022-09-22T16:03:49.751670Z","shell.execute_reply.started":"2022-09-22T16:03:41.291300Z","shell.execute_reply":"2022-09-22T16:03:49.750427Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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=(256, 256), ext='jpg'):\n    def decode(path):\n        file_bytes = tf.io.read_file(path)\n\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        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=128, 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":{"execution":{"iopub.status.busy":"2022-09-22T16:03:52.556654Z","iopub.execute_input":"2022-09-22T16:03:52.557116Z","iopub.status.idle":"2022-09-22T16:03:52.579159Z","shell.execute_reply.started":"2022-09-22T16:03:52.557074Z","shell.execute_reply":"2022-09-22T16:03:52.577899Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"COMPETITION_NAME = \"siimcovid19-512-img-png-600-study-png\"\nstrategy = auto_select_accelerator()\nBATCH_SIZE = strategy.num_replicas_in_sync * 16\nGCS_DS_PATH = KaggleDatasets().get_gcs_path(COMPETITION_NAME)","metadata":{"execution":{"iopub.status.busy":"2022-09-22T16:03:57.268064Z","iopub.execute_input":"2022-09-22T16:03:57.268388Z","iopub.status.idle":"2022-09-22T16:04:03.548173Z","shell.execute_reply.started":"2022-09-22T16:03:57.268358Z","shell.execute_reply":"2022-09-22T16:04:03.547264Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"load_dir = f\"/kaggle/input/{COMPETITION_NAME}/\"\ndf = pd.read_csv('../input/siim-covid19-detection/train_study_level.csv')\nlabel_cols = df.columns[1:5]\n","metadata":{"execution":{"iopub.status.busy":"2022-09-22T16:04:03.550094Z","iopub.execute_input":"2022-09-22T16:04:03.550963Z","iopub.status.idle":"2022-09-22T16:04:03.579097Z","shell.execute_reply.started":"2022-09-22T16:04:03.550905Z","shell.execute_reply":"2022-09-22T16:04:03.578061Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#x_train, y_train= df.iloc[:, 0].values, df.iloc[:, 1:].values","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#print(x_train)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#for i in range(5):\n    \n    #df2 = df['id']\n    #print(df2)\n    \n    \n#valid_paths = GCS_DS_PATH + '/study/' + df[df['fold'] == i]['id'] + '.png' #\"/train/\"\ntrain_paths = GCS_DS_PATH + '/study/' + df['id'] + '.png' #\"/train/\" \n#valid_labels = df[df['fold'] == i][label_cols].values\ntrain_labels = df[label_cols].values\n\nIMSIZE = (224, 240, 260, 300, 380, 456, 528, 600)\nIMS = 7\n\ndecoder = build_decoder(with_labels=True, target_size=(IMSIZE[IMS], IMSIZE[IMS]), ext='png')\n#test_decoder = build_decoder(with_labels=False, target_size=(IMSIZE[IMS], IMSIZE[IMS]),ext='png')\n\ntrain_dataset = build_dataset(\n    train_paths, train_labels, bsize=BATCH_SIZE, decode_fn=decoder\n)\n'''\nvalid_dataset = build_dataset(\n    valid_paths, valid_labels, bsize=BATCH_SIZE, decode_fn=decoder,\n    repeat=False, shuffle=False, augment=False\n)\n'''\n\ntry:\n    n_labels = train_labels.shape[1]\nexcept:\n    n_labels = 1\n\nwith strategy.scope():\n    model = tf.keras.Sequential([\n        efn.EfficientNetB7(\n            input_shape=(IMSIZE[IMS], IMSIZE[IMS], 3),\n            weights='imagenet',\n            include_top=False),\n        tf.keras.layers.GlobalAveragePooling2D(),\n        tf.keras.layers.Dense(n_labels, activation='softmax')\n    ])\n\n    metrics =['accuracy',tf.keras.metrics.AUC(name='auc', multi_label=True)]\n    model.compile(\n        optimizer=tf.keras.optimizers.Adam(),\n        loss='categorical_crossentropy',\n        metrics=metrics)\n        #metrics=[tf.keras.metrics.AUC(multi_label=True)])\n\n\n    model.summary()\n\n\nsteps_per_epoch = train_paths.shape[0] // BATCH_SIZE\ncheckpoint = tf.keras.callbacks.ModelCheckpoint(\n    f'model.h5', save_best_only=True, monitor='val_accuracy', mode='min')\nlr_reducer = tf.keras.callbacks.ReduceLROnPlateau(\n    monitor=\"val_accuracy\", patience=3, min_lr=1e-6, mode='min')\n\nhistory = model.fit(\n    train_dataset, \n    epochs=20,\n    verbose=1,\n    callbacks=[checkpoint, lr_reducer],\n    steps_per_epoch=steps_per_epoch)\n    #validation_data=valid_dataset\n\nhist_df = pd.DataFrame(history.history)\nhist_df.to_csv(f'history.csv')\n    ","metadata":{"execution":{"iopub.status.busy":"2022-09-22T16:04:10.241493Z","iopub.execute_input":"2022-09-22T16:04:10.241884Z","iopub.status.idle":"2022-09-22T16:33:36.903246Z","shell.execute_reply.started":"2022-09-22T16:04:10.241844Z","shell.execute_reply":"2022-09-22T16:33:36.902079Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.save('model.h5', overwrite=True,include_optimizer=True,save_format='h5')","metadata":{"execution":{"iopub.status.busy":"2022-09-22T16:47:12.296658Z","iopub.execute_input":"2022-09-22T16:47:12.297063Z","iopub.status.idle":"2022-09-22T16:47:24.664072Z","shell.execute_reply.started":"2022-09-22T16:47:12.297024Z","shell.execute_reply":"2022-09-22T16:47:24.663009Z"},"trusted":true},"execution_count":null,"outputs":[]}]}