Quick example of padded_batch for medium post

padded_batch_example.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow as tf"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Preparing the dataset\n",
    "We'll get into this later"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "def gen_func():\n",
    "    for i in range(100):\n",
    "        yield (list(range(i)),)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset = tf.data.Dataset.from_generator(gen_func,(tf.float32,),)\n",
    "value = dataset.make_one_shot_iterator().get_next()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "sess = tf.InteractiveSession()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "When we pull"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([], dtype=float32),)"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sess.run(value)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([0.], dtype=float32),)"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sess.run(value)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([0., 1.], dtype=float32),)"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sess.run(value)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Batched"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset = tf.data.Dataset.from_generator(gen_func,(tf.float32,),)\n",
    "batched_ds = dataset.padded_batch(5,padded_shapes=(tf.TensorShape([None]),))\n",
    "batched_value = batched_ds.make_one_shot_iterator().get_next()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([[0., 0., 0., 0.],\n",
       "        [0., 0., 0., 0.],\n",
       "        [0., 1., 0., 0.],\n",
       "        [0., 1., 2., 0.],\n",
       "        [0., 1., 2., 3.]], dtype=float32),)"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sess.run(batched_value)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array([[0., 1., 2., 3., 4., 0., 0., 0., 0.],\n",
       "        [0., 1., 2., 3., 4., 5., 0., 0., 0.],\n",
       "        [0., 1., 2., 3., 4., 5., 6., 0., 0.],\n",
       "        [0., 1., 2., 3., 4., 5., 6., 7., 0.],\n",
       "        [0., 1., 2., 3., 4., 5., 6., 7., 8.]], dtype=float32),)"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sess.run(batched_value)"
   ]
  }
 ],
 "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}