Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- {
- "cells": [
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {},
- "outputs": [
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "Using TensorFlow backend.\n"
- ]
- }
- ],
- "source": [
- "import pandas as pd\n",
- "import numpy as np\n",
- "import tensorflow as tf\n",
- "import os,sys\n",
- "\n",
- "from keras.datasets import mnist"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 3,
- "metadata": {},
- "outputs": [],
- "source": [
- "(x_train,y_train),(x_test,y_test) = mnist.load_data()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 4,
- "metadata": {},
- "outputs": [],
- "source": [
- "x_train = x_train.astype(np.int64)\n",
- "x_test = x_test.astype(np.int64)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "metadata": {},
- "outputs": [],
- "source": [
- "train_path = os.path.abspath('./mnist_train.tfrecords')\n",
- "test_path = os.path.abspath('./mnist_test.tfrecords')"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "`Numpy int format ---> Numpy string format ---> TF Example ---> Serialized Example ---> TFRecords Format`"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 7,
- "metadata": {},
- "outputs": [],
- "source": [
- "def _int64_feature(value):\n",
- " return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))\n",
- "\n",
- "def _bytes_feature(value):\n",
- " return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 10,
- "metadata": {},
- "outputs": [],
- "source": [
- "def convert_to_records(x,y,path):\n",
- " print('writing to {}'.format(path))\n",
- " with tf.python_io.TFRecordWriter(path) as writer:\n",
- " for i in range(x.shape[0]):\n",
- " example = tf.train.Example(features = tf.train.Features(\n",
- " feature = \n",
- " {\n",
- " 'image_raw':_bytes_feature(x[i].tostring()),\n",
- " 'label':_int64_feature(int(y[i]))\n",
- " }\n",
- " )\n",
- " )\n",
- " writer.write(example.SerializeToString())\n",
- " if i%5000==0:\n",
- " print('writing {}th image'.format(i))\n",
- " "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": 11,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "writing to /home/lilhope/Downloads/fastai/mnist_train.tfrecords\n",
- "writing 0 iteration\n",
- "writing 5000 iteration\n",
- "writing 10000 iteration\n",
- "writing 15000 iteration\n",
- "writing 20000 iteration\n",
- "writing 25000 iteration\n",
- "writing 30000 iteration\n",
- "writing 35000 iteration\n",
- "writing 40000 iteration\n",
- "writing 45000 iteration\n",
- "writing 50000 iteration\n",
- "writing 55000 iteration\n"
- ]
- },
- {
- "data": {
- "text/plain": [
- "0"
- ]
- },
- "execution_count": 11,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "convert_to_records(x_train,y_train,train_path)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 10,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "writing to /home/lilhope/Downloads/fastai/mnist_test.tfrecords\n",
- "writing 0 iteration\n",
- "writing 5000 iteration\n"
- ]
- },
- {
- "data": {
- "text/plain": [
- "0"
- ]
- },
- "execution_count": 10,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "convert_to_records(x_test,y_test,test_path)"
- ]
- }
- ],
- "metadata": {
- "kernelspec": {
- "display_name": "Python 3",
- "language": "python",
- "name": "python3"
- },
- "language_info": {
- "codemirror_mode": {
- "name": "ipython",
- "version": 3
- },
- "file_extension": ".py",
- "mimetype": "text/x-python",
- "name": "python",
- "nbconvert_exporter": "python",
- "pygments_lexer": "ipython3",
- "version": "3.6.5"
- }
- },
- "nbformat": 4,
- "nbformat_minor": 2
- }
Add Comment
Please, Sign In to add comment