Load Semantic3D data

load_sem3d_data.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Most code is adapted from https://github.com/yangyanli/PointCNN/blob/master/data_conversions/prepare_scannet_cls_data.py"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "# the point cloud filename from semantic3D\n",
    "filename_pts = \"./data/train/bildstein_station3_xyz_intensity_rgb.txt\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "# get each point one per line into a list if the line has 7 components: xyzirgb\n",
    "xyzrgb = [pnt.strip().split(' ') for pnt in open(filename_pts, 'r') if len(pnt.strip().split(' ')) == 7]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "# get the x, y, z and r, g, b components as floats of each point \n",
    "xyzrgbs = np.array([[float(value) for value in pnt] for pnt in xyzrgb])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "# better to do all operations per line instead of looping through it twice\n",
    "xyzrgbs = [[float(value) for value in pnt.strip().split(' ')] for pnt \n",
    "           in open(filename_pts, 'r') if len(pnt.strip().split(' ')) == 7]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(23995481, 7)"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.shape(xyzrgbs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "# load everything into a pandas dataframe for easier handling\n",
    "df = pd.DataFrame(xyzrgbs, columns=['x', 'y', 'z', 'i', 'r', 'g', 'b'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "      <th>z</th>\n",
       "      <th>i</th>\n",
       "      <th>r</th>\n",
       "      <th>g</th>\n",
       "      <th>b</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-0.003</td>\n",
       "      <td>-31.752</td>\n",
       "      <td>-2.618</td>\n",
       "      <td>-134.0</td>\n",
       "      <td>130.0</td>\n",
       "      <td>146.0</td>\n",
       "      <td>162.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-0.001</td>\n",
       "      <td>-31.756</td>\n",
       "      <td>-2.807</td>\n",
       "      <td>-89.0</td>\n",
       "      <td>142.0</td>\n",
       "      <td>157.0</td>\n",
       "      <td>178.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.002</td>\n",
       "      <td>-31.759</td>\n",
       "      <td>-2.899</td>\n",
       "      <td>-281.0</td>\n",
       "      <td>144.0</td>\n",
       "      <td>157.0</td>\n",
       "      <td>176.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-0.002</td>\n",
       "      <td>-31.759</td>\n",
       "      <td>-2.902</td>\n",
       "      <td>-162.0</td>\n",
       "      <td>143.0</td>\n",
       "      <td>156.0</td>\n",
       "      <td>175.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-0.003</td>\n",
       "      <td>-31.759</td>\n",
       "      <td>-2.902</td>\n",
       "      <td>-113.0</td>\n",
       "      <td>143.0</td>\n",
       "      <td>156.0</td>\n",
       "      <td>175.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       x       y      z      i      r      g      b\n",
       "0 -0.003 -31.752 -2.618 -134.0  130.0  146.0  162.0\n",
       "1 -0.001 -31.756 -2.807  -89.0  142.0  157.0  178.0\n",
       "2 -0.002 -31.759 -2.899 -281.0  144.0  157.0  176.0\n",
       "3 -0.002 -31.759 -2.902 -162.0  143.0  156.0  175.0\n",
       "4 -0.003 -31.759 -2.902 -113.0  143.0  156.0  175.0"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}