jeanpat/LoadingPairsDataset.ipynb

## 129 changes: 129 additions & 0 deletions LoadingPairsDataset.ipynb
@@ -0,0 +1,129 @@

    {
{

     "cells": [
 "cells": [

      {
  {

       "cell_type": "code",
   "cell_type": "code",

       "execution_count": 13,
   "execution_count": 13,

       "metadata": {
   "metadata": {

        "collapsed": true
    "collapsed": true

       },
   },

       "outputs": [],
   "outputs": [],

       "source": [
   "source": [

        "import h5py\n",
    "import h5py\n",

        "import numpy as np\n",
    "import numpy as np\n",

        "import skimage as sk\n",
    "import skimage as sk\n",

        "#print sk.__version__\n",
    "#print sk.__version__\n",

        "from skimage import io\n",
    "from skimage import io\n",

        "from matplotlib import pyplot as plt"
    "from matplotlib import pyplot as plt"

       ]
   ]

      },
  },

      {
  {

       "cell_type": "code",
   "cell_type": "code",

       "execution_count": 2,
   "execution_count": 2,

       "metadata": {
   "metadata": {

        "collapsed": false
    "collapsed": false

       },
   },

       "outputs": [],
   "outputs": [],

       "source": [
   "source": [

        "h5f = h5py.File('overlapping_pairs.h5','r')\n",
    "h5f = h5py.File('overlapping_pairs.h5','r')\n",

        "pairs = h5f['dataset_1'][:]\n",
    "pairs = h5f['dataset_1'][:]\n",

        "h5f.close()"
    "h5f.close()"

       ]
   ]

      },
  },

      {
  {

       "cell_type": "code",
   "cell_type": "code",

       "execution_count": 3,
   "execution_count": 3,

       "metadata": {
   "metadata": {

        "collapsed": false
    "collapsed": false

       },
   },

       "outputs": [
   "outputs": [

        {
    {

         "data": {
     "data": {

          "text/plain": [
      "text/plain": [

           "(2853, 190, 189, 2)"
       "(2853, 190, 189, 2)"

          ]
      ]

         },
     },

         "execution_count": 3,
     "execution_count": 3,

         "metadata": {},
     "metadata": {},

         "output_type": "execute_result"
     "output_type": "execute_result"

        }
    }

       ],
   ],

       "source": [
   "source": [

        "pairs.shape"
    "pairs.shape"

       ]
   ]

      },
  },

      {
  {

       "cell_type": "code",
   "cell_type": "code",

       "execution_count": 17,
   "execution_count": 17,

       "metadata": {
   "metadata": {

        "collapsed": true
    "collapsed": true

       },
   },

       "outputs": [],
   "outputs": [],

       "source": [
   "source": [

        "subset = pairs[0:100,:,:,1]"
    "subset = pairs[0:100,:,:,1]"

       ]
   ]

      },
  },

      {
  {

       "cell_type": "code",
   "cell_type": "code",

       "execution_count": 18,
   "execution_count": 18,

       "metadata": {
   "metadata": {

        "collapsed": false
    "collapsed": false

       },
   },

       "outputs": [
   "outputs": [

        {
    {

         "data": {
     "data": {

          "text/plain": [
      "text/plain": [

           "<matplotlib.image.AxesImage at 0x7fd3ff787d50>"
       "<matplotlib.image.AxesImage at 0x7fd3ff787d50>"

          ]
      ]

         },
     },

         "execution_count": 18,
     "execution_count": 18,

         "metadata": {},
     "metadata": {},

         "output_type": "execute_result"
     "output_type": "execute_result"

        },
    },

        {
    {

         "data": {
     "data": {

          "image/png": "iVBORw0KGgoAAAANSUhEUgAAAQMAAAEACAYAAAC3RRNlAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nM9QgAAAAAElFTkSuQmCC\n",
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAQMAAAEACAYAAAC3RRNlAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nM9QgAAAAAElFTkSuQmCC\n",

          "text/plain": [
      "text/plain": [

           "<matplotlib.figure.Figure at 0x7fd418b73dd0>"
       "<matplotlib.figure.Figure at 0x7fd418b73dd0>"

          ]
      ]

         },
     },

         "metadata": {},
     "metadata": {},

         "output_type": "display_data"
     "output_type": "display_data"

        }
    }

       ],
   ],

       "source": [
   "source": [

        "%matplotlib inline\n",
    "%matplotlib inline\n",

        "plt.imshow(subset[80,:,:])"
    "plt.imshow(subset[80,:,:])"

       ]
   ]

      },
  },

      {
  {

       "cell_type": "code",
   "cell_type": "code",

       "execution_count": null,
   "execution_count": null,

       "metadata": {
   "metadata": {

        "collapsed": true
    "collapsed": true

       },
   },

       "outputs": [],
   "outputs": [],

       "source": []
   "source": []

      }
  }

     ],
 ],

     "metadata": {
 "metadata": {

      "kernelspec": {
  "kernelspec": {

       "display_name": "Python 2",
   "display_name": "Python 2",

       "language": "python2",
   "language": "python2",

       "name": "python2"
   "name": "python2"

      },
  },

      "language_info": {
  "language_info": {

       "codemirror_mode": {
   "codemirror_mode": {

        "name": "ipython",
    "name": "ipython",

        "version": 2
    "version": 2

       },
   },

       "file_extension": ".py",
   "file_extension": ".py",

       "mimetype": "text/x-python",
   "mimetype": "text/x-python",

       "name": "python",
   "name": "python",

       "nbconvert_exporter": "python",
   "nbconvert_exporter": "python",

       "pygments_lexer": "ipython2",
   "pygments_lexer": "ipython2",

       "version": "2.7.11"
   "version": "2.7.11"

      }
  }

     },
 },

     "nbformat": 4,
 "nbformat": 4,

     "nbformat_minor": 0
 "nbformat_minor": 0

    }
}