{"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\n# You can write up to 5GB 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\n\nimport tensorflow as tf\nimport cv2\nimport openslide\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom kaggle_datasets import KaggleDatasets\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"try:\n    tpu = tf.distribute.cluster_resolver.TPUClusterResolver()\n    print('Running on TPU ', tpu.master())\nexcept ValueError:\n    tpu = None\n\nif tpu:\n    tf.config.experimental_connect_to_cluster(tpu)\n    tf.tpu.experimental.initialize_tpu_system(tpu)\n    strategy = tf.distribute.experimental.TPUStrategy(tpu)\nelse:\n    # Default distribution strategy in Tensorflow. Works on CPU and single GPU.\n    strategy = tf.distribute.get_strategy()\n\nprint(\"REPLICAS: \", strategy.num_replicas_in_sync)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"AUTO = tf.data.experimental.AUTOTUNE\nBATCH_SIZE = 32*strategy.num_replicas_in_sync\nEPOCHS = 20\nIMAGE_SIZE = (224, 224)\nIMAGE_SHAPE = (224,224,3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def decode_image(filename, label=None, image_size=IMAGE_SIZE):\n    bits = tf.io.read_file(filename)\n    image = tf.image.decode_jpeg(bits, channels=3)\n    image = tf.cast(image, tf.float32) / 255.0\n    image = tf.image.resize(image, image_size)\n    if label is None:\n        return image\n    else:\n        return image, label","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"class PreparedData():\n    def __init__(self):\n        # Data access\n        GCS_PATH = KaggleDatasets().get_gcs_path('panda-resized-train-data-512x512')\n        train_df = pd.read_csv('/kaggle/input/prostate-cancer-grade-assessment/train.csv')\n        train_dir=GCS_PATH+'/train_images/train_images/'\n\n        train,valid = train_test_split(train_df, test_size=0.2, random_state=1)\n        \n        train_paths = train[\"image_id\"].apply(lambda x: train_dir + x + '.png').values\n        valid_paths = valid[\"image_id\"].apply(lambda x: train_dir + x + '.png').values\n        \n        self.train_labels = pd.get_dummies(train['isup_grade']).astype('int32').values\n        self.valid_labels = pd.get_dummies(valid['isup_grade']).astype('int32').values\n\n\n        self.train_dataset = (\n            tf.data.Dataset\n            .from_tensor_slices((train_paths, self.train_labels))\n            .map(decode_image, num_parallel_calls=AUTO)\n            .repeat()\n            .cache()\n            .shuffle(512)\n            .batch(BATCH_SIZE)\n            .prefetch(AUTO)\n        )\n        self.valid_dataset = (\n            tf.data.Dataset\n            .from_tensor_slices((valid_paths, self.valid_labels))\n            .map(decode_image, num_parallel_calls=AUTO)\n            .batch(BATCH_SIZE)\n            .cache()\n            .prefetch(AUTO)\n        )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pd_obj = PreparedData()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data = pd_obj.train_dataset\nvalid_data = pd_obj.valid_dataset\ntrain_labels = pd_obj.train_labels\nvalid_labels = pd_obj.valid_labels","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class DefineModels():\n    def get_tl_model(self):\n        tl_model = tf.keras.applications.vgg16.VGG16(weights='/kaggle/input/keras-pretrained-models/vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5', \n                                                include_top=False, input_shape=IMAGE_SHAPE)\n        model = tf.keras.models.Sequential()\n        model.add(tl_model)\n        model.add(tf.keras.layers.Flatten())\n        model.add(tf.keras.layers.Dropout(0.01))\n        model.add(tf.keras.layers.Dense(6, activation='softmax'))\n        return model\n        \n    def run(self,model,epochs):\n        model.compile(loss='categorical_crossentropy',optimizer=tf.keras.optimizers.Adam(lr=1e-3),metrics=['accuracy'])\n        #history = model.fit(train_data,epochs=epochs,validation_data=valid_data)\n        #history = model.fit(train_data,epochs=epochs,validation_data=valid_data,verbose=1)\n        callbacks = None#[lr_callback, Checkpoint]\n        history = model.fit(\n            train_data, \n            validation_data = valid_data, \n            steps_per_epoch=train_labels.shape[0] // BATCH_SIZE,            \n            validation_steps=valid_labels.shape[0] // BATCH_SIZE,            \n            callbacks=callbacks,\n            epochs=epochs,\n            verbose=1\n)\n        return history\n        ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model_obj = DefineModels()\nmodel = model_obj.get_tl_model()\nhistory = model_obj.run(model,10)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df = pd.read_csv('../input/prostate-cancer-grade-assessment/test.csv')\ntest_dir = \"../input/prostate-cancer-grade-assessment/test_images/\"\ndef processed_image(image_path): \n    biopsy = openslide.OpenSlide(image_path)\n    img = np.array(biopsy.get_thumbnail(size=IMAGE_SIZE))\n    img = np.resize(img,IMAGE_SHAPE) / 255\n    return img\ndata = list()\nfor i in range(test_df.shape[0]):\n    data.append(self.processed_image(test_dir + test_df['image_id'].iloc[i]+'.tiff'))\ntest_df=pd.DataFrame(data)\ntest_df.columns=['image']\ntest_dataset = (\n            tf.data.Dataset\n            .from_tensor_slices(test_df)\n            .batch(BATCH_SIZE)\n        )\ny_pred = np.argmax(model.predict(test_dataset))\ntest_df['isup_grade'] = y_pred\ntest_df = test_df[[\"image_id\",\"isup_grade\"]]\ntest_df.to_csv('submission.csv',index=False)\n\n","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}