Train and test split on DFC2018

Notebooks/DFC2018 Ground truth split train and validation.ipynb

@@ -0,0 +1,196 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd\n",
+    "\n",
+    "# Triskele\n",
+    "import sys\n",
+    "from pathlib import Path\n",
+    "triskele_path = Path('../triskele/python/')\n",
+    "sys.path.append(str(triskele_path.resolve()))\n",
+    "import triskele"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fs = np.array([16,3]) * 2  # Figure Size"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Load ground truth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gt = triskele.read('../Data/ground_truth/2018_IEEE_GRSS_DFC_GT_TR.tif')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.figure(figsize=fs)\n",
+    "plt.imshow(gt)\n",
+    "plt.colorbar()\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "count = np.unique(gt, return_counts=True)\n",
+    "lbl = pd.read_csv('../Data/ground_truth/labels.csv', header=None, names=['Label'], index_col=0)\n",
+    "lbl['Count'] = count[1]\n",
+    "lbl"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.bar(*count, log=True)\n",
+    "plt.xticks(lbl.index.values,lbl['Label'], rotation=90)\n",
+    "plt.show()\n",
+    "\n",
+    "plt.bar(count[0][1:], count[1][1:])\n",
+    "plt.xticks(lbl.index.values[1:], lbl['Label'][1:], rotation=90)\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Split data\n",
+    "\n",
+    "Create a filter raster `split` with values:\n",
+    "\n",
+    "- `0` No Data\n",
+    "- `1` Train\n",
+    "- `2` Test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_part = .7\n",
+    "\n",
+    "split = np.zeros_like(gt)\n",
+    "\n",
+    "for lbl, lblc in zip(count[0][1:], count[1][1:]):\n",
+    "    treshold = int(lblc * train_part)\n",
+    "    #print('lbl:{}, count:{}, train:{}'.format(lbl, lblc, treshold))\n",
+    "    f = np.nonzero(gt == lbl)\n",
+    "    split[f[0][:treshold], f[1][:treshold]] = 1\n",
+    "    split[f[0][treshold:], f[1][treshold:]] = 2\n",
+    "    \n",
+    "plt.figure(figsize=fs)\n",
+    "plt.imshow(split)\n",
+    "#plt.imshow(split * (gt==1))\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Metaclasses "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "metaclasses_A = {'Grass': [1, 2, 3],\n",
+    "                 'Trees': [4, 5],\n",
+    "                 'Hard Ground': [6, 17],\n",
+    "                 'Water': [7],\n",
+    "                 'Buildings': [8, 9],\n",
+    "                 'Roads': [10, 11, 12, 13, 14, 16],\n",
+    "                 'Railways': [15],\n",
+    "                 'Cars': [18],\n",
+    "                 'Trains': [19],\n",
+    "                 'Stadium': [20]}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.figure(figsize=fs)\n",
+    "plt.imshow(np.isin(gt, metaclasses_A['Roads']))\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.figure(figsize=fs)\n",
+    "plt.imshow(gt * np.isin(gt, [10, 11]))#metaclasses_A['Roads']))\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "~~on~~"
+   ]
+  }
+ ],
+ "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"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}