mem-profile-cenir.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import dipy.core.gradients as dpg\n",
    "import dipy.data as dpd\n",
    "import dipy.reconst.dti as dti\n",
    "import nibabel as nib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "%load_ext memory_profiler"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Dataset is already in place. If you want to fetch it again please first remove the folder /Users/arokem/.dipy/cenir_multib \n"
     ]
    }
   ],
   "source": [
    "img, gtab = dpd.read_cenir_multib()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "data = img.get_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(104, 104, 72, 652)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "peak memory: 5784.47 MiB, increment: 2755.86 MiB\n",
      "peak memory: 5405.55 MiB, increment: 4303.24 MiB\n",
      "peak memory: 6594.60 MiB, increment: 6446.70 MiB\n",
      "peak memory: 6220.90 MiB, increment: 4129.81 MiB\n",
      "peak memory: 6123.64 MiB, increment: 5464.41 MiB\n"
     ]
    }
   ],
   "source": [
    "for step in [1, 10, 100, 1000, 10000]:\n",
    "    tenmodel = dti.TensorModel(gtab, step=step)\n",
    "    %memit tenfit = tenmodel.fit(data)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}

It happens in tenfit.predict actually, the fit does not seem to be problematic