{"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 in \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 \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"from __future__ import absolute_import, division, print_function\n \nimport tensorflow as tf\nprint(tf.VERSION)\n  \ntf.enable_eager_execution()\n \nAUTOTUNE = tf.data.experimental.AUTOTUNE\n \nimport IPython.display as display\nimport matplotlib.pyplot as plt","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.read_csv('../input/train.csv')\n \nf = df['file_name']\nid = df['category_id']\n \nall_image_paths = ['../input/train_images/' + fname for fname in f]\nall_image_labels = [i for i in id]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"all_image_paths[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!ls ../input/train_images/5998cfa4-23d2-11e8-a6a3-ec086b02610b.jpg -al","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"all_image_paths[0:1]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n\ndef my_fn(img):\n  a = tf.io.read_file(img)\n  b = tf.image.decode_jpeg(a)\n  c = tf.image.resize_images(b, (192,192))\n  d = tf.dtypes.cast(c, tf.uint8)\n  e = tf.image.encode_jpeg(d)\n  return e\n    \nds = tf.data.Dataset.from_tensor_slices(all_image_paths)\n\nds2 = ds.map(my_fn)\n\ndds = ds2.map(tf.io.serialize_tensor)\n\ntfrec = tf.data.experimental.TFRecordWriter('images.tfrec')\ntfrec.write(dds)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!ls -al","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ds = tf.data.TFRecordDataset('images.tfrec')\n\ndef parse(x):\n  result = tf.io.parse_tensor(x, out_type=tf.string)\n#  result = tf.reshape(result, [28, 28, 3])\n  return result\n\nds = ds.map(parse, num_parallel_calls=AUTOTUNE)\nds","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\n\nfor i in ds.take(10):\n  display.display(display.Image(i.numpy()))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}