InceptionV3 true/false classifier

Create True - False data.ipynb

@@ -0,0 +1,435 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 61,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import cv2\n",
+    "import numpy\n",
+    "import pickle\n",
+    "import skimage\n",
+    "from scipy.misc import imread\n",
+    "from xmljson import badgerfish as bf\n",
+    "from xml.etree.ElementTree import fromstring\n",
+    "from matplotlib import pyplot, rcParams\n",
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def negative_regions(positive):\n",
+    "    \"\"\"Estimate some negative rectangular regions, where positive is a bitmap marking diatomenes.\n",
+    "    First extract 200 to 800 (randomly) consequtive rows from positive.  From that extract all column\n",
+    "    sequences without positive marks. Yield those as a list of 2 slices.\"\"\"\n",
+    "    for _ in range(3):\n",
+    "        height = numpy.random.randint(200,800)\n",
+    "        ymin = numpy.random.randint(0, positive.shape[0]-width)\n",
+    "        ymax = ymin + height\n",
+    "        has_diatomeen = positive[ymin:ymax].sum(0) == 0\n",
+    "\n",
+    "        for cont in cv2.findContours(\n",
+    "            has_diatomeen[:,None].astype(numpy.uint8),\n",
+    "            cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE\n",
+    "        )[1]:\n",
+    "            if len(cont) != 2:\n",
+    "                continue\n",
+    "            xmin, xmax = cont[0][0][1], cont[1][0][1]\n",
+    "            if xmax - xmin > 200 and xmax - xmin < 800:\n",
+    "                region = [slice(ymin, ymax), slice(xmin, xmax)]\n",
+    "                assert positive[region].sum() == 0, \"Due to a bug, some positive regions were selected as negative.\"\n",
+    "                yield region\n",
+    "                break"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "negatives = []\n",
+    "positives = []\n",
+    "\n",
+    "for annotation in os.listdir('annotations/'):\n",
+    "    with open('annotations/' + annotation) as f:\n",
+    "        data = bf.data(fromstring(f.read()))['annotation']\n",
+    "        filename = data['filename']['$']\n",
+    "        try:\n",
+    "            image = imread('images/' + filename)\n",
+    "        except FileNotFoundError:\n",
+    "            continue\n",
+    "        positive = numpy.zeros(image.shape[:2]).astype(numpy.bool)\n",
+    "        for o in data['object'] if type(data['object'])==list else [data['object']]:\n",
+    "            region = [\n",
+    "                slice(o['bndbox']['ymin']['$'], o['bndbox']['ymax']['$']),\n",
+    "                slice(o['bndbox']['xmin']['$'], o['bndbox']['xmax']['$']),\n",
+    "            ]\n",
+    "            positive[region] = 1\n",
+    "            positives.append(image[region])\n",
+    "        for region in negative_regions(positive):\n",
+    "            negatives.append(image[region])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = negatives + positives\n",
+    "y = [False] * len(negatives) + [True] * len(positives)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 53,
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/herbert/.virtualenvs/medical/lib/python3.5/site-packages/matplotlib/pyplot.py:524: RuntimeWarning: More than 20 figures have been opened. Figures created through the pyplot interface (`matplotlib.pyplot.figure`) are retained until explicitly closed and may consume too much memory. (To control this warning, see the rcParam `figure.max_open_warning`).\n",
+      "  max_open_warning, RuntimeWarning)\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c6909a90>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c42fbac8>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c41531d0>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABGYAAAElCAYAAACmveSWAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAIABJREFUeJzsvU2v7DyzNnSVnfTe53n0gsTHEHF+H4gBCAkJ8YohMwYICfGfYAxT5sw45zz37o6rGNjllB07ne5Or4+9fd1a916rO3Ecx7Hr46oqEhEMDAwMDAwMDAwMDAwMDAwMDHw83Gd3YGBgYGBgYGBgYGBgYGBgYOBPxTDMDAwMDAwMDAwMDAwMDAwMDHwShmFmYGBgYGBgYGBgYGBgYGBg4JMwDDMDAwMDAwMDAwMDAwMDAwMDn4RhmBkYGBgYGBgYGBgYGBgYGBj4JAzDzMDAwMDAwMDAwMDAwMDAwMAnYRhmBgYGBgYGBgYGBgYGBgYGBj4JwzAzMDAwMDAwMDAwMDAwMDAw8EkYhpmBgYGBgYGBgYGBgYGBgYGBT8IwzAwMDAwMDAwMDAwMDAwMDAx8EqZHDv5PiOSf39SRgYGBEv/XP/3Ev/7bP+iz+/GRGGvMwMD3xf/9t7/jX/71X/6oNessjLVv4HfG/wn8vyLyn352PwYGBga+Mh4yzPwzgP/jPf0YGBio8J/9h//us7vw4fhnjDVmYOC74j//j/7jz+7Ct8U/Y6x9A78vCPh/PrsPAwMDA18dI5RpYGBgYGBgYGBgYGBgYGBg4JMwDDMDA18WIyJgYGBgYGBgYGBgYGDgd8dDoUw1/rf/8b/DDZz/dm618whfi2O99xARcChtQc45EBFCCMXnzAznHJxzYFnbIiKICEQEoL7i2vtGzC2LSNlHx7GPzCCi/FMf9yjs+bTTZwvtAwAECEjiPU3kQAI4AcLs8ljUfXQCLA4I6XITA15iW865on0ACLy10RFRPDb82n7GjCA+f+53nr2dF8zt+VLPi2Is3JLv3wny/QMTGIAQwBT/FaxzhAA4EFyIY+MAMC3Na/T6WH9X9Ks67ggCTSCiOL/NI3Mg/Ff/0/9cHEvDMIP//X/5X/N8q2HnvYjk+WzXlN6zA+Lz0/Nk9gALSASTUDHf/iLO817P0+vYdUvXLO1XsR6m69xbT+bKVh5CyNe2r8jeHK3bf3X90uvpPTEz5nm+O//r6+rzOLoG6nXtuHvvc1+898Wxvfus+2n3lrovDGk+v+V6g/c+Pz/7na6xDnFtQuA8f2hn/u0seaCl/DLvn8yQOa2vMgFwWG5pHrtyfO296fuQ55KZt2Gh/Pk0lSLBspTrZb0v/hf/zX/Zv4mBl/Bf/7f/Pj7DE+UPKzNtZIbOe2nfl9Y71lybze+63+mebOegzqU99GSG+hg7N4u+mD6/vhK2+2Wv4Uw/7D5ERGBzXAih2Bd0XOw7Z+Vdvcaja2gJ3/y0J6PyEvKaUD97hmCaJnjvMU0TLpcLnHPwbgYR4X/478faMDAwMPAoXjLMeAFunf2hq4DzquTsbS7TNIGZsSwLXHsvOR3at2maNoaij4Zu2M45LGHJEoXzq2GGd4SsM64P7Bsfbm5VRjwAz/H33pzYwxHhS48jASDAzmGHsHedHqzQ1Du/UOgqxWaZV9GIZB2/1qswzDIRtSIMxHG1xhhqvAuqzCpaQm4+/7YqCYuYOU9rm7VhodUvbdMacoDVsBFPLJdd28fFl+8bzR4sgiCMW4iGCYco1HtQNDwSIdB6X3vramuc6r4QUR47HefCCDJ53IThCJicB7EALIAIFre2URtVIBOECXAS311rJKW56IMaIazBV9vSe5gXiQZZJOOsQzbUumUdx9qYQz62IwBApfGLOBlEiQotbhICBYFzBKJ0Ie26N+NNgHgHwWNKoM4tVX69LxU45pCeC2Ex84dIMF8IAEF4LtokUGF8hBCYBRwAoil//sMtCGAsjiEuOgFmjnuMc6VRLg+cAOzP3XMGSviOQboHq+T3wNV6WJ/fQm2QzuuM6V9ttCEYo6pINProD5IDxa3vYcsoZN/ZYv00/aqN89Z4YdvRdZvScXZtqlHvEz2njV2brLxYG8n1bxGBVOfbvjAzWB1K5t7UmFUICTvynjUG673kseyIPL0p4yaAEddpP1V7As0ItwUSGA6EBcl4PWFjNB8YGBgYOIaXDDM3v4DMRkPYCtEK3bjCjLQ5hqjQu2homByw8HYDjBvUuukV1ny/ep9rT7TnNjOGrPBC9flzFDhDuhdJ+59RIPbYL6VgMtsv1t+pbfDJrI40bpNL/efkIVEPbPKgRaNVf3MONMVxlXRvELCLggmLgIXgyD6v0oCwCmFRaFLBQfvnnMMPc4rk7Xvf4OHMhm2FmWm6YFmWplA54ZIVZHYMARDSj4WOEXCDI8qKqyBkI4cVXq2QZb3XQuW4/mDJjByeXGbozEL5PqwiOpnGinkA4HJbVTYVvrijxg21ZzWWnmF4tML2PQPGMzjanuAGwLwn1qPbuM3WvUclI/33wH0cHcejYySSFknJi2XXs756hoF6dhfrenovW9e+3W7ZgGFJJUyrgTgaXM59th+taAhVv9sfe9zO86yNj4euK5L3vfRrt42znQEDJV5Zp77bs+n1lyoZrT6nxRZutVFf47PW/vqce4a0et054jAsGEJm7F6953o+WoMYM+e9+rOdmgMDAwPfGS8ZZoDnWAePoreheF4VmRMYvy/15ZlzCpYItkLH2sD667Is0Uv+wPWtV+Zo/4vnavpSevB8+3j0vXw9D+CeB+sIyrAszorrGQFB/5CVsTQ7n38P2Kd4D7yOs8IJgZKJoW2fieNhikth4GS271d9LDeFap3fjnTlOG5wOdJfO0Z7x9WGGRFkI26NzEpxUhjb7fX098w44vK+7BqmjD1gDW9Um2pw5xtm3mnUq2ENxUFWsgERiuW1ZilY2DX/KPOiNsxw8vi33sGx5r0XBdvpQbzTCPEOtOZnHZJaz0HLBNm7R12PrJHi7D37mTFWR9Se3POMkaMeI8tQl4PrQAv1nsDLahTTe7FGmoGBgYGBx/GyYeYeNf4MdA0zYgwzKA0z4U2yyDP3W5xjPi/PP0YrjhteyXa5h2cUit597nm28jF3+tICM2OapkMesHvtZk9O+nl1KgRPkdYvRgEEsNDWezRwLlyiT1M1350J0yg+r2jkNpTsp5uSspnyhJjzgl+F9drL+IjQrUqwzeFUhxh4P6fPgRAEIRiqfXUpez8+5YkiIiB5UlVsF5ZCCNexqan41pCoQr81ftnQsJqNqP86Lu9HHMX8TmoUSe3W1yViAJzuO2CadBwEi3AO6/vpZ0hgyI1RpVrB5XLJ93apXjkWBlRpSOc5AI4cPAi8BPCvG+Yij4pgSuxIsGyup7iBDWOlnBM+bNk/eXwvU2EYL/prDFDzPOfP0s0YZqcNIdpbw0vWo58IOkPISbEOinBmXs5uhoPAs+DGjEDAL0eAI1x+eYSAnF/HYpKXxYeBHdT5Ru6hXm+abe6tZQf2/HpNdKqMV/m8BDGkRtI5yioFl/m6crs7IaHajvYj57whyoySPYae/c6GFdXH1Ib7Fo7kuAmdfGi69vba0nuxfX5GxrRP2FWMm/6drcdpX2MYVd8w5HIoI4McIfAVLISL+6chDw0MDAw8iZclq2lZwzwCYlhGgGBC2xPwM20ggVNoUwjgtKE53942rFJmhY6bsNmFJOZf0c38ZhOorW1pgti8bZCevU2Llj0A5jO74VxJioS8BOSErkWSWUvTt+1P6xUXlvIIM3QeBJYYf+y8AwO43vOQyw0iMT5bIClPTwAkhvV4Fz336gm+ubX/lBSA9V5WxawQAExeC5jwH0nH8BKvpQlNnaQLN0CeEMI1CW21kSrk62i8ecw/8WPjDQNWAUewDXkS430GVoFsYnvN8vqlYYYSM0AgKVHoRNGzT/AAAzdvE1SXAvPPEJXYQDF5XvDxepemyDSEG6AtnD4jsGp+BQ11+ajRvWfY2fu+5TG9d+/fzVsOKANIDexWaSqPs/cWqicollVSn2ONTCf3vdWezjHFmc/hkXC0eyAihGRUEwIga94rqZakoWx9LA6HEiZ8l3f9CI7MtUffg3p8bPLho2zdmtmneGbsewag2kHwCj6KuVKsyymp8cDAwMDA43jZMKOUa43xz4p9Z5+qN8lXNmBXfexB4MBFgrtHULNsiM5hXBQem84x9fZZbPpV0suviMLDlv5VZetMTcjmHvooTDZ0gGKS0WhzoWygUU/2vWdki1+RRBYEAPCOL+tPRo+qbg2Fe8KnPW/Riei3z+gdb1bNYOnBKgb1WmdzDBz1ovYUka+M2jBD6BtmdCyXemHpGGZsBbS6utUZ2LYnIEcxOfsbwuaOKuN7x9k5sngAGhac1iQdxz7D83vNr++Ke/vcMMxE3AvLbIVCPcOIPHO8e/d4NETrqWu8aY5sEr0PDAwMDDyFlw0zV4/MJnACuABAgGunZV20VeE4soj3KvZsCDYcorePCAs9bg2oBWxKnsTpxX3Gbo6TtDdGrj7uVRX4qp6IwpOU7mVyPiq84bw+F6U7P2j/n8Najju4+HsAMIsRRJhBzt1NEnr1q0HGIb0vAK40hJkWVEhtlUY+IlTb9+hXWGP6a4POO4IyLH39nmEm0+BDP/eK7fdeCFdRheSO4eqrwDmXmRp8W+DJpbErj7MhWqF61dSQQwS4Kg+LSCpji/0w12cKDdXtiaQqNN4By+qVP2vtPsswo+9CDt/SULnEmvGClKZ62969aw+8B1ZZP6q49+QnG3LXCnnsXb/GvXW41baGLv/69WsT4mPbJBXCDLQa0l6FqdY91ywUW4K+rvhWt9G6TstoDgBk7rfIZyYSqy6Z0CnbR+2Lvfe6D8V9il0ALTN0fWunqdzZenNBGezxcwIRg3kb6mohKEO4Ft27JkAeyoI4MDAwMKB4WR+JCXgFIS3abk4KQQg50VghDFSe4ULh6igdVgmz8bv9NCuSN41aeHHu0r2XiatSyJGP3mUzXKrypCJiwmZLine truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74bf146780>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74bf83d2e8>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74bff936a0>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABFkAAAElCAYAAAA/RT0jAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAIABJREFUeJzsvc2OLcuS5/U384iVufc551aLqgsThK54Hx4AhFoIiSFPgJgy4AEYMGDSaiEx5jGKWY+YlZBooa4uqeuej50Z4WYM3D3CwsPjY+Va+bW3/Y7y7My1Ijw8PDz84+9m5qSqcBzHcRzHcRzHcRzHcW6D3zsDjuM4juM4juM4juM43wMusjiO4ziO4ziO4ziO49wBF1kcx3Ecx3Ecx3Ecx3HugIssjuM4juM4juM4juM4d8BFFsdxHMdxHMdxHMdxnDvgIovjOI7jOI7jOI7jOM4dcJHFcRzHcRzHcRzHcRznDrjI4jiO4ziO4ziO4ziOcwdcZHEcx3Ecx3Ecx3Ecx7kDLrI4juM4juM4juM4juPcge6ag/+OSP/yShlxnM/C/wX8o6r++b3z4TiO4ziO4ziO43wsrhJZ/gLg718nH47zaSDgH947D47jOI7jOI7jOM7Hw92FHMdxHMdxHMdxHMdx7oCLLI7jOI7jOI7jOI7jOHfgKnehmn/5P/4vgDIiPUFVoaoAgBDC4jgimn4vx9wNPboFBiAACQCBiADQ/DcQ+LJMrsofV9kdx3H5fb99fVXN1wOYGaoKIpp+elIoAcIBIMbT0xM6YXTCCMJ4GnoQEUII6Pv0u4ggxggRAYeUd0VEjCOG8Qnj+AyRlMeRIogADgLiEcQRXUfoegAQKD2CmRG4B3OHcRR04YIQApgZT8oIoPRsoyAOI0gVkPSsR3kCEYGZEWNc3Ntx1VqWY6kjpR4R9c3nMqePRZ2r4bj+nJmn85/1qXn9+XpzHf7X/9N/f3AvjuM4juM4juM4jnOjyCI0AgRgZLCZ/JJWE1aKm2nUIkbNIOnc5QTeQGPjrG2Yi/FOaH5fT9rrOfx8fiZK83tVBaQHIyYxQATMAJGCIIACzxRAILAogIgvXQcZI1QHxI7Q45cksDx04D6guwRERMQYEXWExPT4VEbIIAhPBGJCjARSoC+ZFwWU0VEHioqALDSEBxAFQBkqBKYklqgqmBkX/gpAIBohGMFBIBIhNEJVEWguw1pYOxJR9lg940a5W9GlSc+rawkUgAIndL7NdB3HcRzHcRzHcRxng5tElrPc3XrljqxFlX2R5Wx6RAQQIalQAEBQlTzB18Wx0yWyVQhlESRcQhJZLozuwuCe0FFAFIKCIEN6fDIyug4YOSI+C0QYBOB5LCkn6x3qKAk9nPIXOKysjOxPuQ8mxuxZlgSbJCJdVza38JHrkOM4juM4juM4juMA7yCyfDQLgWtFlqP8iwiYGcwMUQLRbFEholDRZM1CZMSMbKXDDBDAnFyEEAZoJ9BOICGCux6CCHQKIkGQHoCAoFAAJARGgIiCFBi5uNwIQJp+GMmIhwisa+sQ+zOOI0KgdF7je8LbPcv6uXy0euQ4juM4juM4juM4LrLcWWSpY4do9Z09vcRoWaRNAGeLlid9AksAaQDQQTVCSaBEAAQkHUCaXHhkBHESX4oRDU3uPIQpDk0xSskiy2RNY6xXZlEoAiAQK1RTPBsRgagkd6E3jJvsIovjOI7jOI7jOI7z0bktJksO6tqFy+5xTPP3EmURX0Vo2D13HevjvnTEEJEpgKuAFoIDCIvva5YWKUkMKHFNhIbk/sOULVjSveTIIOiAyTWISKE6ACyIpBAicOB8zQCNASLFnSgLIRigolBScJcsT+SSLGZEBI/GiiYJOjn/JTSJypQWVBGscCECxjM0AhrtZwTS7mr3nWuFthB0CvKbyr4+Z+2rZAMLl8C129dqB9ad83iYRcdxHMdxHMdxHMdZ8CaWLE6b5cQ+iSMgmdyJQhcm65FhSGKUDawbuF+lQaQ5wC6BsQz+GuMyAHHLimX5vewe/5rWJPYabrXiOI7jOI7jOI7jfAZcZHlH1iJLzC4/SVyQLKyU45hnqxsRwYhhW4QgQGUpsrRco/Z2+1FpCS/LoLivhYis7ttxHMdxHMdxHMdxPjIusrwzs8Chk9tO2W9oHIaFa9Vg/k4BdmdLD2aeXGuALIBIaO4YtJ+PGalEFusu9dq7/byFtYzjOI7jOI7jOI7j3JObRJauxMnQcf9AY4XQ2bgmCgh0ISRca7HAB3N9OZijE9Ei7ksdd2WQCBBDVBElrmLEcCVi2O9rgSCE0BQ80t+AKoN0Lgubk7Tzs5aItgi5rBQC0IAoT2BmqHZQ6aBK+SS7jXRFXG/XvLi3VRwUXOG+s1+1iNquS/Pfc9DeGAGibvf4EMJk/SKiYB53j09ltbz3dK7k9B528+84juM4juM4juM4NW9iybI3KX9ti4i3xt5PmuzzaWHi6mCywml7ZWWAAhQMKEOV0nfYT+89bUSO7rUIUkU4OQqAXMSRuayXYt01u0I5juM4juM4juM4zktwkeXOLCxUzOf3EFnqNJK1ShJYoAoFQ5WhUqxX9q2C6B1llqMtma1F09mys2LWtVtvl1g3HmjXcRzHcRzHcRzHeSlvLrK0d7G5bnvfj0wtstTuKNecX7MSWSRkSxbKew4nSxaA83cHblwfWGSZt27mq0SWktaRyLJVzvMW0IeXdBzHcRzHcRzHcZwFt4ksmiauETrFuEgBWZdxTfikcKCqq3OPhImx2ma4Pv+QsDy+uKdM8Tq0S1FNinGIYmHxEDVZQCAKSAQQneLE0MMIIkkWJyhuQwEqBAUB+m1xLQIv0lY8V5kVTLFxAXRc4rkQJAaocMqnRkDHY0sVWsZYOYqHsyd2zBYkJWDtuJs282X3Wl1VM4+Elvr6c0wX5OvXIsuw+Nu6Ix0FCXYcx3Ecx3Ecx3GcFh9ud6HPNrmdhITp5572IbVgtO1Sc7W41DjnjEvNWe79HD9bvXAcx3Ecx3Ecx3F+PD68yPLR3YdeVWTROthr2+VldnG5MnDuakef+wkZdgvmezzDz1YvHMdxHMdxHAcA/o5I//LemXAc5yb+zcMjvn3749Qk1EWWG7FxQN7akkV1rOKQXCeS1JYpR5Yq11jL2Bgp9+Cz1QvHcRzHcRzHAYC/APj7986E4zg38bc//3L62JtElkEiAIDQI0r6bQ6+apkDsNa7uAQO0+etmCxnWMQxqSbjoZqL19+PQzo/hJDSgCCHrAURoPkeC1P+puAoHYgUFADqCOMYEaEACVj7Vf4ABYVsgSKPGMcRw/AMkTmeTQgBITBC0MU2xn3fL/IixDmngKhkDUZRgsiQdlOZnBE9iGohY33vNmbN3rMK4WH3WiWGz1YcnzpmCnOd96P4Mcu/1wJUXfWXJ9Bh0GDHcRzHcRzHcRzHWfLuliyvvbPQtdYdqzwc7UqjWebI/6YAqgoQIR7M08vOOaqKcRxXAVeLsFAEidfmbEyWe7gAHcWTeW1LFbeEcRzHcRzHcRzHce7Nu4sstWXLawdMPZpcWwsLVV2JLCuXmkpkyR/mn2PRoliGtPM9uwK9xMLnWtbbHK/zZAWWW57VUTyZs1suv5TXTt9xHMdxHMdxWvxX//V/t/mdHfPXu7CWcbOdj9gdMvfmVWcXGMsisL2GTcfmw+b11rG0Yu2doKqI47xqvXWNrZAHrfF+HTeyVS6lDOxPa8OQupyICDHGKU+tHUtXO9nuUDwH6udoz513pW3f95mnfpSPowX2GONUZuM4LsqreC3YerqFrLxhZgIv6+ARKu33CLx8p6ZjkJ4bM0/38K//1f96eJ0t3l1ksRXkNdMvXHOdKc7KTnq1yJJetOQuRAfFO47j9CIWVxz7ItcNwGsLAWdFlnLsrSLLXlousjiO4ziO4zjfI61Ja1l83VtYta72tRgBYCV6lEm/qqLr2vMSO0G2E+PFRH1n/hRCWOWr67okkORr1/du73m6jyI+mPsgAF3XYRzH1UR9af0/z6Nq0aM+vi77VkiFkkYJJ1FDFKfy6jo29xqmvNShEWyeSj7L76Wc7LXOClgtw4Br59X18a1yq0W+8q8NIaGqKzGlhOWwbMcB3Q4HoTrX0TJ/LtcsP/Y6xO20JIqp66Zc84YzEgGmvnnuNdwkskw3UvnFMOr4GrqocPbzW11PWhWwNDgiApJu4eaiYgLVIsUyqQWORd5lfkHSB2G6lqqCxz/S4+kI1DFSiBmBIILxCECgGCEaIVEA7QDtAQTEoQeLopMBw9PvCKSQMCL2Cn0ghJEWDVb9gvVVhV29gFTuezpityyJ0rXKi14aFhuDpW7QCrayA0A42u3ZnNt60UTqDmatHm91KgCgRIAIGIQAgkIhMQKS6tyIuEpvcb6LLo7jOI7jOM4rsDX3eYnl+tEE/GieNcWlfMF8bE/QKNc+O6beu/41+bv3wr0VGeZrzN9Zr4Ry7TK3PJu+XXhuUQterz1P+YjzoK358Efl3S1ZXhsrGtiKXxTbM9gXqDb96oqQIZTEN0piBTFNQXMVClXCOABQyj9dbSQzpzulv5+/13CtOtMYt1gpwPfK1EnqstD04RwYuCitN4p6juM4juM4jnML9STcrsJfO74vligtgaaM698i7ECdp2uFmz3LjXJ/Z4SLe7owbS3CA0srlNnzYG25coR9Rlv5bVm4XHudazjjZmbr3WcRPt6SH0ZkKZPsYrIUQjLnwolGpxZX7E9EerEQAaViVZGC1qoWszeBCkGVAekAvQD6AArPq7wqK1QEEMF6C+d1viy3ige3BLatj48bxxXu3dQfiSxWYU6N01vLQI7jOI7jOI6DyX3Hzk8KIYTJdWjrc0u9+6ilnF/HIbG03IXsuTVF7BAREPNkJz9ZtasiGFeZVjrlfOvCZHcxLcdYy/pSBtbK31JEqtodqfxb7q0lTLTmVLasVvMMDQAIIgrVYEIsrHc9abl11d+3rlHEi7qcasOBqZxt/kQOhZtWzJ3JTauynCnPq5S/PbZO/xbhx95bq+5Y7wqbP2sJ1NqxuLXLine truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c64ab978>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c66424a8>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c7352e10>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c64cbe80>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c71a1780>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c4b91a90>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c6727eb8>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c6eb2320>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c6bee748>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c69d5b38>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c6df80f0>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c726a400>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c78db828>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c441ac50>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c680de48>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c6f6a6a0>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c6da4a90>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c6a148d0>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c4506208>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c6ac1630>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c662ba58>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABDwAAAElCAYAAAAIi/IXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAIABJREFUeJzs3VeTpFl+3/fvOefxz5M+y7ef7jE9dhfYXawEIgAIIYcgQTGC17rU29CtLhWUREbQCAQpQIAIkjDrAOxiF2tmd8yON909bavLu/SPPefooroLs6IYICYQgebE+URUVEXWUx2Z+Zyb/PXfCGstjuM4juM4juM4juM4nyfyb/sJOI7jOI7jOI7jOI7j/E1zgYfjOI7jOI7jOI7jOJ87LvBwHMdxHMdxHMdxHOdzxwUejuM4juM4juM4juN87rjAw3Ecx3Ecx3Ecx3Gczx0XeDiO4ziO4ziO4ziO87njAg/HcRzHcRzHcRzHcT53XODhOI7jOI7jOI7jOM7njgs8HMdxHMdxHMdxHMf53HGBh+M4juM4juM4juM4nzve3/YTcBzHcRzHcRzHcZzHRCIs3b/tZ+E80XY4tNYu/VWXucDDcRzHcRzHcRzHeXJ0gf/pb/tJOE+0/5n7/ymXuZYWx3Ecx3Ecx3Ecx3E+d1zg4TiO4ziO4ziO4zjO545raXEcx3Ecx3Ecx3GeWP988L/S6/UIw5DR4TH5dMz97Xts7x6yPxpjjKGVDYiCHu0wJV1b5fLyKuc21hiuruDFIZUZ08q6xFGL4miPoO3RGfSY7Rzw/q1Deus+X/1yyu/8s5tsHhyw9kyPfL/kaHuHwyplOFxmMhtTHU+oMFx75QWuPvUsvheQIFnkE2bzEYeHB8zG+7z/zmuMRmOytE2Y1OSLhjC6wvMvvcyVi212Hjzk4OiY0eiYk5Mj8qmgllNEEJOmGd3OMoP+Ml4nJY0Dnn26hSd2+eb//Sa1F9NdfYqnnrpCWU3J5wHCUwzCFC/16IQNgZzSb43502++jqVLvLREv92iOClQHoShIjANtSe40FvCCwpqEdOIOS999RztMOff/4u32R0X2LRFGpVsHhkWi4KqHlPM5uR5TlUvMMYghEDJkKqqAAhFjO/7RFFEkLSIoog4jkmDmDRNCcOQJEnwfZ84jvE8jyT0CKRF+pKmaQBoaiirGb/67j/4TGfHBR6O4ziO4ziO4zjOE6uqappGEwQgRYQUBUEQIKVECAH29LtUDdZv0U97LK2dZ2NjhfZaRss3PLytufhclzQQfPuNTcaV5hd+7SrC5Mz2H3Bnc8Lu9pDDiURR8sFr90hbA0a5oKymlGWLThbSpCuknT5PX32eV156iqWegAruvfMR98sei2BC4/ksdfuMjw7JqxIbCuI4ZjY7YHe0x5XrPdqDFkcnx0gpCYKIMlng6ZAw8PED8DxJ0jKE4oDxnYa7fsrf/3vn+PDaBg/v1RzuHdNOu8RxTJAlhJFgpd2mLA7Y39pGWMOV/27IU9cvsLsZoGqJbwJ07IGpkMYglI9vG0zQUMYNnthi+2bBh7fvc/7cGjMVYT2oCk2+8KGqoamR2sNTMUkikIXEWktVVUjVoJRAN5JaGMAgrcYzBmPM6b2kwjMh0sYs6pJICWgqUinRWiM9D20NBouUkjD2OTlYfOaz4wIPx3Ecx3Ecx3Ec54kltMHWDbZuCCNoSkkgJbEvCYSkVB4qknRWz9Hpv8DKus+Xfu3n6c9H7EzmxCuC8miHjz5WLPkVB0cjkm7A63/xLqnMKOsKg2DvzgyDYpororBNGsWotTWUTBgutejEKUU5Y9BfYmMdQj1DyhYqarj2/BDrzSj0KvP5FL/dxvd9irrGr7t4HUEzndCcFNSVoNvt08rGlGXNbD4i9KAyGl8aqBoIJZcuteka+Pat+0zeP+bf6ZSod4lWXhPrBdZ4CJsQK4VQAi/KWVnKufmTPSo/5wc/SOknl1kaNtR1jZI+qWyodQZRTWgXTGYLjo5riASr52KM35AfVuyR0+utIH1LMZ2TT2csqpqAiDAI8P2SqvLxvYiyLNENeLbAAlhoTIk0Bm1A6AppFLpc4NkMI2u0WOD5yVkQAqBR5MYjkBXWWoQQrK6eIwxT/tNGlP6HXODhOI7jOI7jOI7jPLG01lRVRZqm+L5/1gYRRRGe51GedlEQxzHF5n2SzjJ3fvwqr5eKZ7pw88inoEd99zYnYRtrNSeHNdKPMF1F2l+ntCX9OKGRAf7RCe1eQpIkGDshiXq0Oh7dTPLwrs/x+CbXuxbPO+EPf3+H4WCNFy6s0c7WaHenRMcJnWyD4XCL+zsH5HlOHHukacrh4SEn+Yz20pAkSfDGHkEQnAYSSlHXNZPxFo0/pN1v+Or1K7z+1i637k8ZzTa5/NQyadbBV0sIVRCnDaGeMr63x43C8Pf/7lXWnmnz0U3N3nZBstYmihqCIMBaS2cYMp/XzPSYB80JX/pyl49fv81i1OJwL2Mw7HPh3Hk8z8P3fYIYplagLBBFSGUII4/JvGA+nxN7Y6ZTy+7imLyqkDJAa40WGiklxhiqqkIphed5Z/dSKYWn9em1n3pMSokW+uzeB51lFsfzz3x2XODhOI7jOI7jOI7jPLEaDA2GyjR4SqGUIvYz0jggDQMKrSnnhsn+Pl4T8vFuSONBXYbcrzpkLQhTiTArhElMlHY5mo0Jo4jlpT62yhk2Af0BRMqweTtipgxfeEVy8/2Y99++Q3c15Vd++TI/uf8BD27NebDzDi9dXePB5gkf3JwxXnicX7bkowVGxoSRR9ZbJznYY9EUVFVCqxWzP93mcHvEpdUNsiwjDMOzcEFrTZ7nBNkSKVt85xsV5TQh6W2wlo+oPB+jfTzPQ4aGOE5Ju5aknnLv5h4nu5LfX8Qsd9a5dLGP76XghQRSok2J8gQyhmEf9t4/JqgFN+/kmKBL2IRkYUgqBF73tPLC9z0M4PdaLEJFV3l02ylrq0MePPiAGx+PGB2XLIqGUgUYU9GYEnwPZRXGGLTWNDRUVYXv++A1CBTS1MhCI4VFCk2U+mezQITv4SmJFDHltOTkYfGZz44LPBzHcRzHcRzHcZwnlmhK6rqhbiyhklilkF6ICkIaoTG6ZFFVHOwL0niIOt7npi65cP4pfA+S/gpxZGgKjex0WFKCbF/h9yJeeDHlk59W3Hr3JllvjW6o2PzpB2zqgqa8zPZmTn5yyNb9ezx8OGYxmdJQsvXRGJqU1bUVltNz9LtLFIsaaSEUDXMV0B0skcQhi9mCsgjIMosXlGxv7nJ4cYNer8XBYYTvxQhp8W3BgpDBpZdZig748J1dyupjBoNlsuEqKg7JIkW3FbMoak7u3qBaivjC311m92GPnRsP+eSTBfbqOu2gTdbJCNWCXhQymU84PDwk38z50q9dJkkV+zsFxx9Zuv2UbuyTxi2QitD38XxA1KR+i+hiwNpgmfs373JwtGCyn3M4yZmUOQdlQa1rlDQ0KLSugRrwgUfVOarEaomsDVoUZ5UcQVDSaEEkPeq6xvO80xYX24BSdIY9zj0zZHl5CDc+29lxgYfjOI7jOI7jOI7zxKpKg580NLoEAoQQRF5GGmYEEjxpMQi09Ekjgd8e0B1c4OLVy2wsdWgPIwZDjzs/uoPqT7l8uc/XfnKf+R2D3zzNBx98QlOUvPW9W3hxm02zIJ81/MUP79ANYkYjTVlK/JMxQZJQE7DUjlg/t8L1Zy9z7fIVui1FlY/ZfvsYK1ss9JSmjukM1xlPbtLkNY0WxJ2Qo90dTo5G9C6t0el0ODg+Qs3nLKzCk4bDj9/iEGiahmleIyZTNjbaRGFE2orIluBSq+QbHxywN/X5xh8P6K5d51LZprYJni7wbIOUAWFS47canl4r2bm7zUnp8d1vPGR17RxZfAwxCASBn2HrEllnZMOSrJ1Q2F303gM284zk3Av4keWT3TfYnFhE7aPx8AOJsRKdi7O5G0opPGsw2sPUllrUYD1qr0ZKeVbtUZYlvu9TVRWh9M4qQuocIt9HlXPykyPi7uAznx0XeDiO4ziO4ziO4zhPtMezHqy1BEFAaauzeR5K1SghCYKAYGPI8vrzXFgKuHD9AlldMtp9SBxvUBawe3uLel5SVRrrN7z5xnvUFUynC/JmQWJPZ23Mi0N6UUKQBQzbA4IgYNgKsdKntpI48ji/1qIdNQhZgVREmcf5l/rU7xxyXK0wH90lTVOCICCvNEVRkPUijvfHHB9NufIo8AiC4Oy1ABh9upI1yzJi0dAOBInUUOccPtwjVBEvfXWJT15d4Z1bhzx8cEBRCdKgjYxj8CFtd/DFjKOtA/aiin/465e48sKEwzem1JWkzCEIAowxp6tjQ0sW+9Tzirq03Nvf45f+3ivs/vQ93vnBNq+/eYduFpEXAbY0VHWJ1p+atREEIJqzzTnKWrASY+xZkKG1xjza2KK1xvf5y8qOwJzNMVGP7nee5zzYvMWqbT7zuXGBh+M4juM4juM4jvPEEkLQNKdzIGprCKQi8AyRH5HGKeNJTVNX2CaH3HB0712SvEfqHbO3XXLlqQ6HW4eMK0GgCx42h/jtCNE0iNAjN5ZkuIQnPaqmRhvDlacvE4SC2WiO1+4Th4a1gcKagNu3dpktDFdeiLk4rPnD3/u/mLLMamvIM+fbRMMBg6nmMMxIWx2STkpxmLOY1yStCF8u2Nm6x+LZDZJWSidrUS5yqqpCa02kDVYFBEFMmGakKy1+4b9Y4t47H/KTG8c8eFAyLa6TLK1yru5QWIkpKqowJJI1SoHqSJ6/mvP//Is7FEXEP9mvuXjuHOtrC5rG4CkfJVPquibPS4btGJUoepcMD9+7y3Hh87u/9SrDLCHMenTrHGskngrI5IKpEQhbIcMWUoQoWaHx8WSDMCXaFFhqrAWtBUKUaDtHax9rT0MQW5dIL4JKsfA1WhiED9ZaWNSU2hKVhvvTDz/z2XGBh+M4juM4juM4jvPECqTCGottNEIbROAhkhBbq9OqiNBDaE1dVpzsbBOGY0y1ILMNeeGxvRmQJALZXie0Hp6GoN0Line truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f74c4b3f898>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "rcParams['figure.figsize'] = (20,5)\n",
+    "axes = (axis for _ in range(10000) for axis in pyplot.subplots(1,4)[1])\n",
+    "\n",
+    "for image, class_ in zip(X, y):\n",
+    "    if numpy.random.rand() < 0.05:\n",
+    "        axis = next(axes)\n",
+    "        axis.imshow(image)\n",
+    "        axis.set_xticks([])\n",
+    "        axis.set_yticks([])\n",
+    "        h, w, _ = image.shape\n",
+    "        axis.plot([w, 0, 0, w, w], [0, 0, h, h, 0], 'g' if class_ else 'r', linewidth=8)\n",
+    "        axis.set_xlim(0, w)\n",
+    "        axis.set_ylim(0, h)\n",
+    "#         axis.set_ylabel('negative' if not class_ else 'positive')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 62,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('true_false_data.p3', 'wb') as file:\n",
+    "    pickle.dump((X,y), file)"
+   ]
+  }
+ ],
+ "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
+}

List tensorflow devices.ipynb

@@ -0,0 +1,70 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "os.environ['LD_LIBRARY_PATH'] = '/usr/local/cuda-9.1/targets/x86_64-linux/lib/'\n",
+    "from tensorflow.python.client import device_lib"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[name: \"/device:CPU:0\"\n",
+       " device_type: \"CPU\"\n",
+       " memory_limit: 268435456\n",
+       " locality {\n",
+       " }\n",
+       " incarnation: 8024912505704686755, name: \"/device:GPU:0\"\n",
+       " device_type: \"GPU\"\n",
+       " memory_limit: 227540992\n",
+       " locality {\n",
+       "   bus_id: 1\n",
+       "   links {\n",
+       "   }\n",
+       " }\n",
+       " incarnation: 17421789173799713590\n",
+       " physical_device_desc: \"device: 0, name: GeForce GTX 960M, pci bus id: 0000:01:00.0, compute capability: 5.0\"]"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "device_lib.list_local_devices()"
+   ]
+  }
+ ],
+ "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
+}

Load Image test.ipynb

@@ -0,0 +1,69 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from keras.applications.vgg19 import VGG19\n",
+    "from keras.preprocessing import image\n",
+    "from keras.applications.inception_v3 import preprocess_input\n",
+    "from keras.models import Model\n",
+    "import numpy as np\n",
+    "\n",
+    "# base_model = VGG19(weights='imagenet')\n",
+    "# model = Model(inputs=base_model.input, outputs=base_model.get_layer('block4_pool').output)\n",
+    "\n",
+    "img_path = 'images/Achanthidium delmontii-!-Achnanthidium delmontii.JPG'\n",
+    "img = image.load_img(img_path, target_size=(224, 224))\n",
+    "x = image.img_to_array(img)\n",
+    "x = np.expand_dims(x, axis=0)\n",
+    "x = preprocess_input(x)\n",
+    "\n",
+    "# block4_pool_features = model.predict(x)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(-1.0, 1.0)"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "x.min(), x.max()"
+   ]
+  }
+ ],
+ "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
+}

Pretrained Inception True - False Classification.ipynb

@@ -0,0 +1,523 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pickle\n",
+    "import numpy\n",
+    "from keras.models import Model\n",
+    "from keras import backend as K\n",
+    "from keras.preprocessing import image\n",
+    "from keras.layers import Dense, GlobalAveragePooling2D\n",
+    "from keras.applications.inception_v3 import InceptionV3, preprocess_input\n",
+    "\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "from sklearn.neural_network import MLPClassifier\n",
+    "\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.metrics import classification_report\n",
+    "from skimage.transform import resize\n",
+    "from jupyter_progressbar import ProgressBar\n",
+    "from keras.optimizers import SGD, Adam\n",
+    "\n",
+    "from matplotlib import pyplot, rcParams\n",
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_model = InceptionV3(weights='imagenet', include_top=False)\n",
+    "\n",
+    "x = base_model.output\n",
+    "x = GlobalAveragePooling2D()(x)\n",
+    "x = Dense(1024, activation='relu')(x)\n",
+    "predictions = Dense(2, activation='softmax')(x)\n",
+    "\n",
+    "model = Model(inputs=base_model.input, outputs=predictions)\n",
+    "\n",
+    "for layer in base_model.layers:\n",
+    "    layer.trainable = False\n",
+    "\n",
+    "model.compile(optimizer=Adam(lr=0.00001), loss='sparse_categorical_crossentropy', metrics=['accuracy'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/herbert/.virtualenvs/medical/lib/python3.5/site-packages/skimage/transform/_warps.py:84: UserWarning: The default mode, 'constant', will be changed to 'reflect' in skimage 0.15.\n",
+      "  warn(\"The default mode, 'constant', will be changed to 'reflect' in \"\n"
+     ]
+    }
+   ],
+   "source": [
+    "with open('true_false_data.p3', 'rb') as file:\n",
+    "    X, y = pickle.load(file)\n",
+    "\n",
+    "garbage = numpy.array([(x.shape[0] * x.shape[1]) < 5000 for x in X])\n",
+    "X = [x for x, g in zip(X, garbage) if not g]\n",
+    "y = [y for y, g in zip(y, garbage) if not g]\n",
+    "    \n",
+    "size = (256, 256)\n",
+    "\n",
+    "X = numpy.concatenate([\n",
+    "        preprocess_input(resize(x, size).astype(numpy.float32))[None]\n",
+    "        for x in X\n",
+    "    ], axis=0)\n",
+    "\n",
+    "F = base_model.predict(X)\n",
+    "F = F.reshape(F.shape[0], F.shape[1] * F.shape[2] * F.shape[3])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Original_train, Original_test, X_train, X_test, y_train, y_test = train_test_split(X, F, y)\n",
+    "\n",
+    "# X_dev, X_test, y_dev, y_test = train_test_split(X_test, y_test, test_size=0.5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/herbert/.virtualenvs/medical/lib/python3.5/site-packages/sklearn/neural_network/multilayer_perceptron.py:565: UserWarning: Training interrupted by user.\n",
+      "  warnings.warn(\"Training interrupted by user.\")\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "             precision    recall  f1-score   support\n",
+      "\n",
+      "      False       0.75      0.88      0.81       219\n",
+      "       True       0.91      0.81      0.85       328\n",
+      "\n",
+      "avg / total       0.85      0.84      0.84       547\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "# mlp = MLPClassifier()\n",
+    "\n",
+    "# mlp.fit(X_train, y_train)\n",
+    "# y_pred = mlp.predict(X_test)\n",
+    "\n",
+    "# print(classification_report(y_pred, y_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "             precision    recall  f1-score   support\n",
+      "\n",
+      "      False       0.89      0.92      0.90       247\n",
+      "       True       0.93      0.91      0.92       300\n",
+      "\n",
+      "avg / total       0.91      0.91      0.91       547\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "lr = LogisticRegression()\n",
+    "\n",
+    "lr.fit(X_train, y_train)\n",
+    "y_pred = lr.predict(X_test)\n",
+    "\n",
+    "print(classification_report(y_pred, y_test))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Wrong test cases\n",
+    "\n",
+    " * red: false positive\n",
+    " * orange: false negative"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f20e8dd3320>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f20e8c800b8>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f20e8bb36a0>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f20e8a6f978>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f20e8929c50>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f20e87e3f28>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f20e86a4240>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f2114e48dd8>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABHEAAAEICAYAAADY/WjvAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAIABJREFUeJzsvT2vJFmSpveYnXPcI+J+ZVV1Te8uSXCA/Qv8A6RKiQpBgKBKgZQJiqvwB1CiSoWUSZEq9V2FIECsRMyCg53t6crKzJv3Rrj7OWYU7LhHZFbWdHUXdnqrxt/ui3szKiLc/XyavfaaHXF3duzYsWPHjh07duzYsWPHjh07dvy7Df1z38COHTt27NixY8eOHTt27NixY8eOP4ydxNmxY8eOHTt27NixY8eOHTt27PgFYCdxduzYsWPHjh07duzYsWPHjh07fgHYSZwdO3bs2LFjx44dO3bs2LFjx45fAHYSZ8eOHTt27NixY8eOHTt27Nix4xeAncTZsWPHjh07duzYsWPHjh07duz4BWAncXbs2LFjx44dO3bs2LFjx44dO34B2EmcHTt27NixY8eOHTt27NixY8eOXwB2EmfHjh07duzYsWPHjh07duzYseMXgJ3E2bFjx44dO3bs2LFjx44dO3bs+AUg/zFv/o2I/+W/pRvZsWPH3w/+73HkcrnIn/s+fg72tWjHjl8+/p+7O14+fvxlr0UP4n/57Z/7Lnbs2PFz8S/+X37v7r/Y2bzbRTt2/DrwL/hpa9EfReL8JfDP/9Q72rFjx78T+M3d3Z/7Fn42/pJ9Ldqx45eOf+/rr//ct/Cz8Zffwj//H/7cd7Fjx46fC/kv+as/9z38HPwlu120Y8evAcJPW4v2dKodO3bs2LFjx9873P3PfQs7duzYsWPHjh2/OOwkzo4d/9Agv+jshR07dvxasHM4O3bs2LFjx44dfzT+qHSqz/Hf/uf/FZMYqgkR+cQ3HP2GHxIwM5ImLn6O19wxN8yc1ZJznJIzooqIkFRRVcwcd8PdMQN3wb0CznjIpCxcWkKao83JImRRZleMuKm4P0FVqdlRoGj8xhcSRquFeZ55++FCkwwIViqqypgy6pBdURVqFlTiPj+JJo6GOCSHNi/QHC+KmWFNcU8IGRHBspIQkjQyhtBQh+lHesVr+sFrRa7tnEsBoLWK6bK9bu5b22ka4rlaA0DVEOntb4aqRm+4k1LG3bCb59MfIQBauraHqKIipH4P4sEWJgRFEP0xyz3hZjSz6zPxSiklvi+laEdzznrgcrnA0igoWIyPKgqeAME9YQ3chCWlrS20j4VSlDIoqTSG0TkcCkmdPJ+pHxsvz43fv594e2lcTCAppSzk6iyvwqUqVRM+CukOHgblzWnkmBPCl6LMFTfv4zeztYpcUFVEoy/dHVXiNVHo/bfUBfMx+qRFG4kKqmmbH59crVbMjP/5f/1fPnn91+g3/Sf/2X9KStLXIqAPIXOjLpW6LMzLgtVGs4Yg5JTQUjgcDpRhIOeYlyklUl+DmhnWGu6N1seYqqIpxfeIRB8pgJDJiPT1Rp3DYUQEVAWIfnSLHoj1KKFJyTn368a/VQRHkTSQUooxq/G++G8xX92dpI5qvw9i/JS+FmhfQ+N+FlIqiAqYYGa4g4hiDtYcc8Eo25jzvjzX1oB+v6Ig0JKSRBAM3GnLgtVKrTPL5cLlcsGTb+uPaiLlRM4ZRHAcW+d7c7wardatzVtfoyD2D4BlmTATUlKGYaCUTM6KpEYpMB6UcSyYKdNk1AXMMmU8ktKAi7MsC+fLmenFWV6VeTZaS6geKMORu4d7nt488uarR776+pHf/vYbhjExlIbwircXnr//W969/VveffeWl+dX5svE+2bRflVYFqcuTmuGe8N8odmF2ma8LdRaWZZlm6PucV+tj093p1klOkAAQRA0JbZp7jHmWmvUtuDuCM7p7sQ4jtzf35FzYppmLq+V6bJwmS6YCzkXtCQ0D+RhiPGimaxt2yvXn5wzqhrjsK9R65haXwd+8L7U94FtbKfE//jP/tkn89Z/hXzyf/1//ve01vpeZZg1zA0363Oh2zIeY2PrTnfMa38PsK3p3vdk2eYjOOKOGLixrSkY25hxFxpgEu1sCI7QhJh/KqCKiyDujEslmcfVfP1iB1+v1eK6WF+PovNcHJe1Lx1Xi/Xpk751RCoi1p+1v9d9fbptzQkIfRO9toFff2xtm/55lwlnbddYY219BJz4f79JF8yc1tZrKeLRNoLCasdIvFdESHKNfYis/wibVzT+fX29d4OsTw5oPI9vn79tGkUsI/1at9dQkZj9t3Ny+9JPsT7n9YV1n3FyWhBiXLkJ1n9qVdyEZoJ7/L1UpzbHDZo5zRpmvV0FVGL/S5pQFTQZqSzcPRwZh5FhLIzDwGHMjENhGAqtVpZ5ZpoutLrgLcYSvjaFgPi20mlfW1yEpn2/28bJTZ/e2Dzb869t9ElT+Pb7ton+j//if/thQ/6K8N/9T/87iKMJcgLU+tBNsNoWmsLGuWmZJom7oZC8gTRy3+edBpoQEmKKLxWVStIZ0YqcCgnBG9gCtjiJzDI3vv+r/4sPH7/j/bvv+e7tW37/uw88f1h4+TjzfH7PtDTcwTRRxgOHw4m7xzccHgqn04mUB9JwgFT45tu/oAwDx6NwdzoxpIw34/n7d7z97i2tVuThiW++eeLh4QRqvP3umecPE+IHyt2Rx68e+fr+De3SePf9M3IcOT2+YfxmRhdY3l24vJ9YLhXNR8bTHePhwDAOjIcRE9CSyEOmHAZKzlgaGOWekjLiM84ZfKIwh79bF+p8oU4TdTrz8eMzb3//O97/7nf869/9a/76b/4/XJ3DceTNt1/x9ddf8zCcubw2Xt4vzK/O5bmxTM7rywuLXWgKXhI6ZEYSgyhanZpnRBLTsjAtDVLmeHpiGI+UYeAwHijHEVMYT0eOpxOlDKRD4XA8cCyJpCCtcX79yLu337F8D54y6f6O+7/4R6RUaJeF6fVC80weBobDiJaMpoSWhIsweiMlYRgLw5hjTSqKe2NZXpjOv8enVwZxRnWkVabzK68fX3n74ZkFWKozkGmvM8+/e8u/+du/5fvn97x9/45lqUxWORwP3D8+8hdv/hHleAQt4cuXI8f7Nxzv71GBnBPjYWQoAylncg671nHq3Ne3VBAyKplSRqo4wzBwPI6UoTCMKXzIUkglUaWQc978iNV/czeG9pZFMo2B86xka2SvwAtSKjmd+G/+4//oT5rjP4vEKQaN2NxVlNrq5jTYrcbHuoEiRkrxH8wcdUHEqOqkFERQbQ3V2AulO6qrkbs6He5Biog4rTVElHM11JykimuKDdSCJIEfl217d+pzymBhdJoZrRsbP2ZjuhkmV4due73vzyJ0w9h5bXO/f0fl+t61oxWHG+LiD8H9+t7zzQ0mr+SUMARZHcWf/K2fwsxQtXAaat2W9x8jdNLcGMcwRDSoGj4WIVmMk2wwoBRXXu1KMK2G4A+esbeH5oXULajapm6gGXONMZBVo01FwJ1qX+5n+5H+T2mdiM44jpQMxwO0YpTcuJhyljNuQBJKVkqLsXmpRq2OJZCmmNHJuujbnD4n3RQTD6Op3bzax771sZySknMnRlWwFkaxtPajDIz7/IlDBVAlf3lc/QpTGESsrz3xO+V1nelGpyZEG1bALBZWEUGTdkJhHfO6/aa/FmNH+xoiqGZyypQ8fOFOEjkHESTqlKH3I45LGMNunQghxv9mcoqEQ4SHQyFCN5e6e3H9G8IpM3eaLSAJ5Wqomq/kXxjnqROLQhA4YTQHOYQrbmCtUs1p1B88lSvXZ5Dedjps7YZZEAS1UetMqzOGY+RYhBREU4x17duOd4cQA4zmS7yxt7eqbPNdJAVhlbSP80xOAzkPqDZSglKgDEIZgEVo4kGEkRDP4SwB5jPNDbygnknukBIljYyHIw+PD3z1zRu+/uaJr75+4OvffkVKQk5LNERTUqo0m5jnibo0llYRI5zBTq4Isbe4CLjRTLtfvHq8fe3SdT+zcGS6l6afO3sxSFgdWtyD+JV473XHUqw5tXqsK52w665ljB03xFN36sKxA/lRbe66/8YwjX4RQPrr2152Q+6szq3hqID9KunjHyKVgqjSzGLNNgFrmEgf64GYNuuctR7YivHj3eGO/9ZtGLuSOOKEXdUJlD6woRM1K6EHgnjf/0QxgSRy/cy6Kqh0ErwTuysLs13LEY/+3kgdNL7HHZfwxl2CUHLp/M/6sOLbPL8lrVZCaiV1ttdvCImVTHa4klj93qJtrnMG4jrG+gw3cwWN53XdAkvr84N020yh2y9BMGhfcXu/dbL+llQJlr6/DkEi3D58byNZ+/GzOSawkfTSiSHk02vcvr4+z/bE20CJ8bD93W9A3JB5JT3YCK7m0JYg76OLezv7SmY5KTma1zECkqQT8WkjZ3NxxtPE/cMpHJpO2A4p9smclGWRvm5Eu9ZmfZdbh4BeWS/pY7j3y3XVkE7abY+44Wb4/Mk2768Rmz3o0Gq3N0QRZYuuho1juHmsA5o4ygG1WBfcoRLB+rT6L/kAaaCVBa+vSGsUc8ap4ElZ1KmpYV5pdUKkcbr/lqbK8+WVw8Mdx3nitc0slxeS3aHLmcUr1WasOpgw5HCe8ZHDAYZcEMtcfn+hloX24JgvnB4OoJWLTtRlYn5eKC1zUSEXGI8H8pjIIrSPZ9oFLnXkeXollZF0fAJNjOme4ifGY+HMmUWfYV7AHANqVvKQkeOBQykMw0BKYY+klKhZGLOT6Ou+HxE7YrxE8LVONBoUo9UzaUgMD0fy8sT48pHH4xvefvd7puXCa3klpQEZnGlqTItRgTYIc1uQOyFXkOZ4M9JkuCpVQaXgPSCvSSneg0XzK5JBLEhaWyCPR5iNKobXytjA0sBcxi3wRsuMp4yn8PlVBzQfES3o/ZHD6Q12BlELIiMJmon5n4U8P+BW8aUx+UQ5QTkk0IpMM+n1wvu/+Y45F+z+CT2deB0OSJ4YckGnyp2OYPF80+GOu8OF88vCMVWLine truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f2114c83fd0>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f2114a8d630>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f21148ed6d8>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f2114680b38>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "rcParams['figure.figsize'] = (20,5)\n",
+    "axes = (axis for _ in range(10000) for axis in pyplot.subplots(1,4)[1])\n",
+    "\n",
+    "sub = y_pred != y_test\n",
+    "for image, class_ in zip(Original_test[sub], numpy.array(y_test)[sub]):\n",
+    "    axis = next(axes)\n",
+    "    image = image - image.min()\n",
+    "    image = image / image.max()\n",
+    "    axis.imshow(image)\n",
+    "    axis.set_xticks([])\n",
+    "    axis.set_yticks([])\n",
+    "    h, w, _ = image.shape\n",
+    "    axis.plot([w, 0, 0, w, w], [0, 0, h, h, 0], color='orange' if class_ else 'red', linewidth=8)\n",
+    "    axis.set_xlim(0, w)\n",
+    "    axis.set_ylim(0, h)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# (Some) Correct cases\n",
+    " * green: true positive\n",
+    " * red: true negative"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f20e8b62c50>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f21142b4cc0>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f21140b2748>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f20eadc4128>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f2114dfdc18>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f20eac81b70>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f20e8ef5e48>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f20e8fa3160>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f20e92f6438>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABHEAAAEICAYAAADY/WjvAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAIABJREFUeJzsvU2PLcmypvWYucdaK3PvXaeqzr0N3WrEle4EiTESE0Yg8Qv6/gXGDBjAiAESEhMGTJnCkBk/ATEBWkI0jYRo0aK5zb33fFXVrsxcK9zNGJh5RKz82lW16+NUnXhLWWtnrq8IDw93s9deMxN3Z8eOHTt27NixY8eOHTt27NixY8cfN/SnPoAdO3bs2LFjx44dO3bs2LFjx44dH8ZO4uzYsWPHjh07duzYsWPHjh07dvwMsJM4O3bs2LFjx44dO3bs2LFjx44dPwPsJM6OHTt27NixY8eOHTt27NixY8fPADuJs2PHjh07duzYsWPHjh07duzY8TPATuLs2LFjx44dO3bs2LFjx44dO3b8DLCTODt27NixY8eOHTt27NixY8eOHT8D7CTOjh07duzYsWPHjh07duzYsWPHzwA7ibNjx44dO3bs2LFjx44dO3bs2PEzwE7i7NixY8eOHTt27NixY8eOHTt2/AxQv82L/0zE/+IHOpAdO3b8OPgnh4n780V+6uP4GOxr0Y4dP3/8b4cTD+f7n/VaJLfifPpTH8WOHTs+Gv+S37j7n//Uh/FdsdtFO3b8MvA/883Wom9F4vwF8D991yPasWPHHwX+/pubn/oQPhp/wb4W7djxc8ef3/7qpz6Ej8enwH/wUx/Ejh07Phr/Kf/8pz6Ej8FfsNtFO3b8EiB8s7VoT6faseNPDOI/9RHs2LFjB4iWn/oQduzYsWPHjh07fnbYSZwdO3bs2LFjx4+Pn3Ui1Y4dO3bs2LFjx0+Db5VO9Rj/0V/9+6gqqoqIUrRwkLr8rdRKLYVSKyrX1lrvhrstv7tdMHPcDXfH3ZHNe+Z5fvE4zH35wR13wQ3cBREFhN4NM6PNPf/d4/smwd3p/UKzC71dmNsljgHwLrgV3BR3BUr8FIdigCPSQQxRA3FEAAdzwx3mM1gXegd3p/QCxDkCy+P6nvX8x88Y08O7SqnCVCuHw4HToVJroQhMtVJFESUeN5ILxylKjrkhYogIpRRAcRPm2ZnPzvnc+fr9hS+/+Jr37+/4u/nA1024XGaagWulq+AoHedwKByq8vc++4RP3hx4c3Pi5jRxLJ1f8TtElbLMk/WausdxjV98jIU7ZjkgHwWJayES808k58fL7+gC/h0cC/X4+RDGtY15E/PTrL/yjrj2r0EAtXislsfhLGP9n/x3//2jN/zyPKe/+kf/CAB3xS3v0/kc64k5Tl73nGcx9vl4OFx91rgvYj3yZd7q8RT3WC1MVRF3ejuDdaw1Lpc7WmvcvTdab5gZOEzThJZ1/o/jeW56W05OAUoplFKQvHfG+1ubUYl/i2pMa1VKUVRK3FcuWBfmS6f1hnvMI/nk76PqCB2ze7Azbhe83dPsgd4a2ipKvVp/3B03wzzOSVRBKqKCe6f1mdZmHh7u6DbTewd6rq1vKUWoVahV0QpVj5gVrBd6q1iH+99f0PKeP/v1A//2v/Ur/t1/5+/xb/7lG94V5fIvvuRf/O9/x//6z/6cf/rbX/HX53vOt0eYjmhTbsyhz5z9ga/1wnx3z2XuNOsgoKUgtaD1wHQ4oLXENb27w8yx3mmzYw6tdcwE67FfPDzc0+3CuT/Q+wXTRp0mSp2QckB1wqlMbkx04sLGHNJc+0qtcS1FuLOZ3jp9brgZ4lBFUAQFrMVexXTK+ajLfHVAN9dFRNGiMVcWVcu6r1iuN+bObP1qfokqZhbHIEKplds6xWeqohrfYe6UUpjqtKxFX9YHtDvSOtoMnQ0sJ3QRTAVDEJRSJmopqE781//Nf/XoXjN+afiPv/wPgWW7AaC7Y7mxqDgqIDiqQtH4d1EoKlBmRI2pKFMtTFVQdUpxpiJMBWoRpqlwPB749AYOp8rh9obDdGC6wOlrePNlYf5njb/+2y/5P/75X/NP/vn/w//w26/56/MDX5YGn97w5rO3fPrmls/rgbcu3Ioi6syT4JOgpghhk3S7x2m0dgbpiDiqjhaJudIKIoVSjlQ9UeotWg/Ueoz5VAUtoDVspIPKExtIxl43/p5j6nK4ep25JwEoIOB5fwBwbotdISKxVqrkupVz2ozeO2ZGQa/2AxDm+ZL3QEE1/iYC9pJN4rm3Xz0vCB1E8lDDMDR7OufHmj3u6a2d9PSrnOYxhkJ8tiy2jYfSNm0eye+25XvSOBivUd3YXoYbyHMGUH6O5B4keX7mnW5tGevxHe5+dQxxzTr+jK0j+vz5+jPHMfZAM1/O19ypnsed19DT7htXo6e97UBZjh/+i8/+yxfH+ZeAf++v/vMYo2fm3DdBKeE/jXGPfeKI1puw6UthmiamCW5vbzjeHKhT4ZN373j37g2nm4nbNzfc3FZAOJ/fM7eZf/E39/zd777id3/3G776u99x//svefjyPZev7rj7+j0PDw88PDzEPFKFQ6WcDpTbE3p75M27t3zCBIBZ+HSXy5mHhzOXy4V5nuPeLuXJ+dQ6UWtBtVCrUqtyOt0wTRXNPVTyXv3QvQg88Wu+G1628d354PVTNWp1VMNmnKYJcnxAMXPa7PRZMI/vEgTVY9gPWrA3XyPV0VJinBDUwHKd1A6tNXzutHmm3d9j3RafzQ3+0O+XMQSWObMepy520LAlxhwrRReb+/Vz1WVOb8dlfGYpJe3P7w53p7X2wde8hpL/uTvdDS95fOkPHN++oR4P6FSoh4n/9j/7q+90rB9F4jyF4cxYmqOxaCYpMRb48VJ1ZDMIgqJKGM9J5ojosvl9cFPrFkSOGd7jSNwlL3Z+hwi1VkQsCRmQ2nCHbkrrBSsHLjLj4UZhHXpzWvOcsMAgWnoSNtKTwDFkkDiAutO7w8XBFFoYayZBSC1Eka8b0vh7POaNJooTPzE306nsndbSllGotS7Ou4giaqiMxcGxsdkSG2cphcPhgKD05ph1LjTm1ri/v+f9+/d88eV7/nCu3FvBEUQrUhUXpVs4SfPlgXOBgzjWDvT5Qp8P2FH41c+//Mr3gmE8xaW2dPNA+TgnJk0yTGMbEHLeOIj7s4TUtaH5y8BYzAXNOS9IKbgJJnl/8YgcJR7nboshGRtLLOCPSRw403unNGGWGN9SBLyBdYasQFQoXuI4ZPnzFRYi5/HfF+dFEHfEjbI4f0FEujmmHkZU/k2mPAfNtcbB6XhtgKXR7uj9XThe0qk0Wj+jXFBxmjnWGrMphj0ikSWIEAvDWFW5eBxDrFIFcaMeD9SxcfUwpI4z+X4oxVAmMMcb+MXp505vQnl3xJry//628T/+46/5w1d/zT/7Nz7jL/7sE8r7iYev/lUe/AYtHS0d0Y5Lx8VofcbnC2e/4yxnznamecccRGqQCVoQrXg9IklWTNMcJE5RJO/PUiruQm+dWoyuitoJtRPmM64NqYLoBHpAZMJNUT9T2nm5lkU1iBJ3NOedplPpYjE/VVGEPs/hbA1ncLMfxBohOIKbhcOqGvM3GdvtFBvf83heWRJx+SJIAmd5H4TxI4b01Sn2JHGsdzSNYpMOPeYnbs+aoGakM94RBPfL0/n+kevfHyPc8qYf5CcOHtc5r2LSdWFoWu7ZQZTAAc17Pl6LSBB9Wikt7CYVRb3A7LSjUl3BldKFY3dOM7zzwr12bk6Vw7uJ+qbw5qvCdDdTbKa3wuX8QDsdmdVwqTjh1HNxEEWK5zoZx2bmOX8dvGHeY70BKBU8ZqtLBHmq68LtqSflYGkXboJMw74b7vVYBcc9cJht2esgAi0mIHm4fftZ5els9DFmuSarKJYE4ko+rPu0akkSLojdcTc9b4XGvnHlVEis1+Zl4Uzif5LX/vEngGEosaYPx83d0efOp8hY0uP97qhIrMc91nu1IAnjjJ7eZ0rMq7A/Y0+KY3vqFohLEGCxw+a4WHyq5v6UzlsQ/SsJN/Y5dwF/Jn3SZPmMx2Py9JhjbyuycsYKuMozto5v3scvMnj1IfTer/YS4INBQXhKGmyD6qIT0whQlJIBp2EHxOe33nl4eADplKJMB/j0s8/41a9uAefmE+XzP3zNbz79jN+//Vvev/sdXyeR8/6LL7i7u+P3v/99fHkpcKjocUJvj5Q3N9y+ueGdHgGY58Y8z1dkK8Dlcubu7u7qPAaJM00TpQwSp1BKzPlpGgHzsM7djd4/RKC8YOR9Twhb6nVS4nJ5oLVzBBiniVonSjnltY5r411pTdYAY5LM4zo2fw/VKFqotTKpUn0lvYvlPV7AzSiH4yLEEMIuvb9c27RjDfs+EcGlkr59iDGAJWgGfHC8yjNr6ha+CYI/BzP7IMnzIZS8VjoVpkeB5G+D753EMXos8mg4EdR81GuFSQ72YPXFpnxOQ9nC+jyMG+V5OKAlBrZbx8RT6RNR1eV70uEZN6y7M00SN6o5vUE3p8qEmTHPjQ6LE+OiLOIhrcEQ44im4ZskzlUkVKG4Yy2ik+7Gud/luabTTVgJy2TfhPBEJSJ3Gj8j8rQdjdQW0OY5DCcU1CnO4tmPiM1yOyXh1XtHZSW8fETah/MmQtFCkULr6w0pIpTcOFveML01esvobrLYOwKDQFg21LyUph+3/JumMetj4VmCbE827/VYfnlwOwWBqkkYSDrRUlARWmvM8znndRKakpEBuYlNzQxrK9FZBvHTWqwxFwE1TJU2IoIC5qFkc1fcjxTpSLEkTYNgWOm2+PyLJJE6Ij3uiHl4vt0p7oh1fHqDqYIo53SKZXpDN4vIvlTqNOFTA1W6O94bfW60uYXj3W1RH7n9DlRyzXC0zUFKm6NeEL/h0judtpBaqrmeLxPV6a1BSSJMw1GhxtrqloRBjfVirg+ogojR3ZntQi03XLxx7oohUI68/9f/IaVfmN/f8n9+9Tt+80+F//tv4S///g2fvznglwe+PBfuaw3lSzN8bvTLine truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f20e9335710>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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 truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f20e90ee9e8>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABHUAAAEzCAYAAAC/qz/7AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAIABJREFUeJzsvU2vJMuWpvWsZWYeEXtnnnNu3apCTQO6E9QFEgygJJCYMAQmjJkgIaTuluAH9ATBhD/AoCnVACEmMO4BPwAJiUGVhFAxQT0paGjdW7fvR37sCHc3W4uBmXt87IidHyf3yZN57DnKk7l3eHh4uJubm732rrXE3el0Op1Op9PpdDqdTqfT6XxZ6Oc+gE6n0+l0Op1Op9PpdDqdzofTRZ1Op9PpdDqdTqfT6XQ6nS+QLup0Op1Op9PpdDqdTqfT6XyBdFGn0+l0Op1Op9PpdDqdTucLpIs6nU6n0+l0Op1Op9PpdDpfIF3U6XQ6nU6n0+l0Op1Op9P5AumiTqfT6XQ6nU6n0+k8MyLy34nIr0Tkr268LiLy34jIPxaR/0NE/o0f+hg7nc6XRxd1Op1Op9PpdDqdTuf5+e+Bf++J1/994F9uf/4u8N/+AMfU6XS+cLqo0+l0Op1Op9PpdDrPjLv/L8BvntjkPwT+B6/8b8B3IvK3fpij63Q6Xypd1Ol0Op1Op9PpdDqdz8/fBv6fk5//Sftdp9Pp3CR+7gPodDqdTqfT6XQ6nc77IyJ/lxqixf39/b/5J3/yJ5/5iDqdzvflL//yL3/t7n/0oe/rok6n0+l0Op1Op9PpfH7+X+BfPPn5X2i/e4S7/znw5wB/+qd/6n/xF3/x/EfX6XSeFRH56495Xw+/6nQ6nU6n0+l0Op3Pzz8C/uNWBevfBn7v7v/0cx9Up9P5cdOdOp1Op9PpdDqdTqfzzIjI/wj8u8Afisg/Af5LIAG4+58B/zPwHwD/GHgA/pPPc6SdTudLoos6nU6n0+l0Op1Op/PMuPt/9I7XHfjPfqDD6XQ6Xwk9/KrT6XQ6nU6n0+l0Op1O5wukizqdTqfT6XQ6nU6n0+l0Ol8gXdTpdDqdTqfT6XQ6nU6n0/kC6aJOp9PpdDqdTqfT6XQ6nc4XSBd1Op1Op9PpdDqdTqfT6XS+QLqo0+l0Op1Op9PpdDqdTqfzBdJFnU6n0+l0Op1Op9PpdDqdL5Au6nQ6nU6n0+l0Op1Op9PpfIF0UafT6XQ6nU6n0+l0Op1O5wukizqdTqfT6XQ6nU6n0+l0Ol8g8UM2/kMR/8UzHUin0/lh+Ks0cJhG+dzH8X3ofVGn8+Xzf2537PcPX3RfJHfifPe5j6LT6Xxv/im/dvc/+tyH0el0Oh/DB4k6vwD+4nmOo9Pp/ED80d3d5z6E780v6H1Rp/Ol88cvv/3ch/D9+Q74e5/7IDqdzvfmv+KvP/chdDqdzsfSw686nU6n0+l0Op1Op9PpdL5AuqjT6XQ6nU7nB+eLjrvqdDqdTqfT+ZHwQeFXl/yD//TvX/39kBIA0zyTc6bkTAgBEUFEcHe22y3TNFFKYc6ZGM4PpSSlxHD2u91uxzzPTNNEjJFBlKE4Dw8PvHzxgrdvH84PREDl6WGju/P24QEVYbvbMaTENM1n27zWgpkzzzOlFBCIIaCqmDtWCsN+JqWBGCMigqoSwvH4c8mICEEV1aqlmfnZ55gbbo67IaLEGIjtXC7MJ8dmVvjd737HZrtlSInNZkPOGT/fLaVk5rm+L8bIZrPB3SmlME3T+vsQIjEGXr16xTRNDMNQf5ciQc+vxVQyrsJmM1BKYRwnQtC2X0OB4eKa5nkmhEgI2tqD1vN5wn6/B1jPneMIoKqICA8PD4/O2/39eTiRmeEXJ2GeZ8ZpIobAbrdjGDZnr4/j4eznEAIxpie3uSTG+n1zzu06OGbOy5cvERFKye17nbfJw2GPSP1+QQRB6j5KrufAHBHWbdCEcH495nlGg7IZNrhHrAS8nYc/+0d/fnmkT36PL5G//5//F2c/i8rNe7+U6b33awEsCGJtv4A4qNe+ZfmEcNLc3qKIt+3a79QcdWrfIALmiANmjIPd/PxSajta2r+owo3v5XZ9PzGH+lkCTvsjYFL/duD0nemG1q9a++96f9X+R1p7NTestVMVRVQe3YPrcZLrdnr8HLtx7PUN19urqra+znH3em8gqAJSWj/h63HI2XmT9TRqcbAbx9r6yXru23dNgXrWjn3N6TW6xunvQ2sbbq1vo/68ngsJ2AfIHcXq1svzldZXnHyJ1hcZrRmcnftTrl0HV8H1yvE4lJM2IG0bEcHDHeYZMUcwsIwK/MN/+F8/3slXxj/45d8jl4y5o7yo50aEYdgQh5HNsKnPAQHSDpmNjQZe6z2DjajPmDlpMOKQMZ8Y8zdM04SZMdqIuCGlEKy1d+TYTnMdo+Q5Y0HWZ2yIhRDiep/sbMCsEGPEgaIzZlbHNToAyzMHJhnBN+ABLRM6FwYNTMPJM18UtPatZlbbkmzXezMaRFXMjJgSL+4iM5Fhu8NeOC82kW92kfHtxOEw8/B2X7/v9GptlyrKy5wpAsRASAFJwjAbY3LSkHD3+vwue0II61hCPKEqqArpMKEJwr0y2YzMkRAD7lBKIWkdy02bSJwKyWZ+72/53a//hv/7b/6Av/3P/x3+rX/9F/yrv3gL8msefvUr/uaXB97sjbdTYD8HyrRj2EDaHlAJlHlAoyHbzCYlhn1mm2FPItvE7BOZkTLCxESWGYJCvmcW59tJeBu25Fyv56Hd9+5OjJGUtmQBgjKmws9C4l5gigaWar/vxjTPx2eFCCpKzjPjOLHNL7FyoMget5GZbym5YGZknOJGCAErhTwdx5AiwpgLQes5POzrfV1K4S31vOdcxzMz9f2bzYZSCm4PiNR2sXdnMyk+wf/6v/8z/uRf+1f4d/408Iuf/5L/6692/LO3zht5S8iRcZwYDyMpJX5bDrwoShoS+0EYsq5tpqizjDI3BGjPLoA/+zv/06fvADqdTucz8SyzO9XjoNfNKKWgGtrguv4+xsicM5RSHzDnc1QMyBfjzn2ZOUyHOohwYUgJtYKVcn2Q6mA3JhanG7k7onpzEhh2W8SM0QulTX+KG5TjTG8Qwdt/i7BzyqlodSlKLKhoOw9tEPIOQQqgFFvPsZm3c3+5Ta7b4cSYCCFyOZgWkSZkRGKMlFIIIZBSfCRQAUQrCMo2JLIJ5hM2ZYTaqFQD4eKaZOrEcPmcs4nHcg7axMC9TkCqEBRWoQwRRM6P/VIYuoaZkZuwtXzXd/NhE47T67VMonLOrf3Luke5cu7XyWeIIIIbWGnb6TqFBK+tQ/T8O6cNQCHbA5R7sCpaXWtB0g1674/Xa3l2yZwqJty4P9OV5rgIKaf/XgSVDz6eG++6JaIsre774rb0cJW1z/3AL6Gqq0C0iPxV9Hz3ffx9WO75oyi1iL/Cla6oIcc/KvXe9HPhY/keT/XXp9fm5DH4vHi7Wu2z5ESEvMW17+C3RESO38sBNeqpcsg8VIGgCUriTri6n6/Pq1PPC4hXyU5UmjhSn6N6urDD8Zo40tS+1rVIfb4Xq4KpU7XH2h/VNujuTY+si0GIsuhvy35luU+l1P23542sB3valS3Xswl07Wnlcvby2iaEU/H2olF7Uy/Fq9DYjknb4oVZVb3dFPdSRcJS2r150r6EVawE6n2oYFEgOIM6QZ0YA+KONuF8EXSW+z6cDHe1nSdpfzZpQIPi5hQRxJWggYHAgBFE6rhGlKU/FY3Q+rG0GdjtIFtmLE4sAYKg6qQ0YMURCe24qjCCGqKQJCJaUFM8GxIVR3AiHiCgGEaMShDB29Aluraz7iiKmiDq7ZIK2tqWtOslOCK6jqOg9oEitW+sopZiAriCKlIc1XoNw3Ivi4EaGkIbU7bzWwxVwR00lOWTiRLa59TP1Nae3G1dwFyug1DHeSaOSljH5qKQkhKCo7R7SI7CvKgQXNf2es5xO07bU6fT6XxlPIuos6zgLoTw+GNOVwSvve5uXI7xY4zYKhLpOpgIIbyHeHObZZXT/dZ0ibOH0jU2w4A2sSKlBG316vvg7pT89EQnnriZbjlB1hVk9zaZ4pGb55SUhvXzFyfP/f2LDz36p1ffPxIVwW+sMn9KFlHmk++3rZZ3vgwcfzQJX+Yqt4in27a/jeqMoTlkrO3H5EM7Yb95736fPvC9Pvl0/ycixm0x6el9Hd//cfv4mM+8RES41cMuQs1yxy4OJGsrzqdCzvL8eJ/PNmN1bT0ni/Pz6N559zW7dkxNp7mCry4lEcG8iXQCztQEsHbzuGB2RTDyr3BydXablDa+MULwdfJ8/YQ2B1uwdr1qW7FS22B18R6Fuqtn7lobv3GYsxuIVNcLUJZ+6eQNVcBsbaYqSpjWX5UnLl0VpRY/aVWwVRYHpRJiYM4Fj22Sb4IZlBk8F7RktGS8FBKGN6uhCOTB6rEOzfkcAsFgiGkdGwZRYqgO45hqDzu41MUtt7ZQRRM0IkMT2syMYErJdcy0c9ggDKpkS7wWRREIUl00RNDEsNlxf5fI88jDYSaHSF2jCQxxy8weiqIKKUQ2MUJogooKWgLFBM/VHSoSEaprTyShbkSUUBaZBmY9jk9UDc+lCj4iaAT1ev6jCPMi7KpWYao9wMy9iY1KSo5aAdEqKCFkEVwEd63CrC8OWKeuH/q6OJcttn7wKKCLwFaVecoEXRXB2s8UQ8xAl75JWTyj9WerjreywU3ZbJW0N9QDUmRd6BOaKHW5MnzaHi9+fr9FvU6n0/myeBZRJ+e8Dg5ruM1jN8VixdQQUA2PXl9WUk8ppTRHip24ICDGRGn7+xgWJ8hivb2krh6dCEhXwnuGYUC0DiRSSlgpn0DUWQZV1xERUkrrhGJurpZr36+GRsmJ6HN7ApJSRATGcVydJh8q6ixhC58aDeFpReoT8VzH/9xuhM4n5imnzg1iYQ1vOh1NLpMlO5k8mZ+LQO9xOLfDmm6JkJ/odjGvy+fSBtKLsH5bCr+xn1JXqBeXzCIAP7fIkUtZBXw4uvVmt6uLine truncated
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f20e85a8cc0>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "rcParams['figure.figsize'] = (20,5)\n",
+    "axes = (axis for _ in range(10000) for axis in pyplot.subplots(1,4)[1])\n",
+    "\n",
+    "sub = y_pred == y_test\n",
+    "for image, class_ in zip(Original_test[sub], numpy.array(y_test)[sub]):\n",
+    "    if numpy.random.rand() < 0.1:\n",
+    "        axis = next(axes)\n",
+    "        image = image - image.min()\n",
+    "        image = image / image.max()\n",
+    "        axis.imshow(image)\n",
+    "        axis.set_xticks([])\n",
+    "        axis.set_yticks([])\n",
+    "        h, w, _ = image.shape\n",
+    "        axis.plot([w, 0, 0, w, w], [0, 0, h, h, 0], color='green' if class_ else 'red', linewidth=8)\n",
+    "        axis.set_xlim(0, w)\n",
+    "        axis.set_ylim(0, h)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model.fit(\n",
+    "    X_train, y_train,\n",
+    "    verbose=1, batch_size=32, epochs=10,\n",
+    "    validation_data=(X_dev, y_dev)\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for layer in model.layers[:249]:\n",
+    "   layer.trainable = False\n",
+    "for layer in model.layers[249:]:\n",
+    "   layer.trainable = True\n",
+    "\n",
+    "from keras.optimizers import SGD\n",
+    "model.compile(optimizer=SGD(lr=0.0001, momentum=0.9), loss='sparse_categorical_crossentropy', metrics=['accuracy'])\n",
+    "\n",
+    "model.fit(X_train, y_train, verbose=1, batch_size=64, validation_data=(X_dev, y_dev), epochs=10)"
+   ]
+  }
+ ],
+ "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
+}

README.md

@@ -1,2 +1,4 @@
-# diatoms_detector
+# Diatoms detector
+
+Detects diatoms in 256 x 256 microscopic images, based on bounding box annotations. Negative samples are extracted as randomly created bounding boxes outside of the manual annotations. Uses a (the) imagenet-pretrained inceptionv3 model from `keras`.
 

annotations/Achanthidium delmontii-!-Achnanthidium delmontii.xml

@@ -0,0 +1,62 @@
+<annotation>
+	<folder>ACHNANTHIDIUM</folder>
+	<filename>Achanthidium delmontii-!-Achnanthidium delmontii.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ACHNANTHIDIUM\Achanthidium delmontii-!-Achnanthidium delmontii.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>526</xmin>
+			<ymin>507</ymin>
+			<xmax>866</xmax>
+			<ymax>1165</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1034</xmin>
+			<ymin>578</ymin>
+			<xmax>1378</xmax>
+			<ymax>1137</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1717</xmin>
+			<ymin>163</ymin>
+			<xmax>2066</xmax>
+			<ymax>405</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1541</xmin>
+			<ymin>61</ymin>
+			<xmax>1703</xmax>
+			<ymax>444</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Achanthidium delmontii-!-Achnantidium delmontii.xml

@@ -0,0 +1,62 @@
+<annotation>
+	<folder>ACHNANTHIDIUM</folder>
+	<filename>Achanthidium delmontii-!-Achnantidium delmontii.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ACHNANTHIDIUM\Achanthidium delmontii-!-Achnantidium delmontii.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>848</xmin>
+			<ymin>197</ymin>
+			<xmax>1148</xmax>
+			<ymax>731</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1361</xmin>
+			<ymin>883</ymin>
+			<xmax>1534</xmax>
+			<ymax>1219</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>561</xmin>
+			<ymin>1366</ymin>
+			<xmax>848</xmax>
+			<ymax>1512</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1937</xmin>
+			<ymin>1005</ymin>
+			<xmax>2058</xmax>
+			<ymax>1227</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Achanthidium delmontii.xml

@@ -0,0 +1,74 @@
+<annotation>
+	<folder>ACHNANTHIDIUM</folder>
+	<filename>Achanthidium delmontii.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ACHNANTHIDIUM\Achanthidium delmontii.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>758</xmin>
+			<ymin>192</ymin>
+			<xmax>1436</xmax>
+			<ymax>399</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>320</xmin>
+			<ymin>514</ymin>
+			<xmax>602</xmax>
+			<ymax>714</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>751</xmin>
+			<ymin>717</ymin>
+			<xmax>1448</xmax>
+			<ymax>890</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>653</xmin>
+			<ymin>1222</ymin>
+			<xmax>1041</xmax>
+			<ymax>1543</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1473</xmin>
+			<ymin>483</ymin>
+			<xmax>1832</xmax>
+			<ymax>763</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Achnantes (Lemnicola) hungarica.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>Lemnicola hungarica</folder>
+	<filename>Achnantes (Lemnicola) hungarica.JPG</filename>
+	<path>/home/herbert/RuG/data_science_kennisgroep/Image-recognition/data/diatomeeen/mine/LEMNICOLA/Lemnicola hungarica/Achnantes (Lemnicola) hungarica.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>935</xmin>
+			<ymin>670</ymin>
+			<xmax>1187</xmax>
+			<ymax>1114</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1054</xmin>
+			<ymin>44</ymin>
+			<xmax>2080</xmax>
+			<ymax>485</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Achnanthes coarctata.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>ACHNANTHES</folder>
+	<filename>Achnanthes coarctata.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ACHNANTHES\Achnanthes coarctata.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>692</xmin>
+			<ymin>674</ymin>
+			<xmax>1517</xmax>
+			<ymax>996</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>991</xmin>
+			<ymin>1024</ymin>
+			<xmax>1976</xmax>
+			<ymax>1425</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Achnanthidium affine.xml

@@ -0,0 +1,62 @@
+<annotation>
+	<folder>ACHNANTHIDIUM</folder>
+	<filename>Achnanthidium affine.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ACHNANTHIDIUM\Achnanthidium affine.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>915</xmin>
+			<ymin>5</ymin>
+			<xmax>1068</xmax>
+			<ymax>295</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1098</xmin>
+			<ymin>543</ymin>
+			<xmax>1536</xmax>
+			<ymax>1115</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>293</xmin>
+			<ymin>1292</ymin>
+			<xmax>720</xmax>
+			<ymax>1451</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>10</xmin>
+			<ymin>476</ymin>
+			<xmax>259</xmax>
+			<ymax>615</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Achnanthidium druarti-!-Achnanthidium druarti.xml

@@ -0,0 +1,50 @@
+<annotation>
+	<folder>ACHNANTHIDIUM</folder>
+	<filename>Achnanthidium druarti-!-Achnanthidium druarti.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ACHNANTHIDIUM\Achnanthidium druarti-!-Achnanthidium druarti.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>768</xmin>
+			<ymin>495</ymin>
+			<xmax>970</xmax>
+			<ymax>868</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1300</xmin>
+			<ymin>744</ymin>
+			<xmax>1849</xmax>
+			<ymax>1302</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>929</xmin>
+			<ymin>395</ymin>
+			<xmax>1429</xmax>
+			<ymax>956</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Achnanthidium druarti.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>ACHNANTHIDIUM</folder>
+	<filename>Achnanthidium druarti.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ACHNANTHIDIUM\Achnanthidium druarti.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>488</xmin>
+			<ymin>224</ymin>
+			<xmax>1034</xmax>
+			<ymax>715</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>881</xmin>
+			<ymin>512</ymin>
+			<xmax>1410</xmax>
+			<ymax>968</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Achnanthidium gr minutissima.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>ACHNANTHIDIUM</folder>
+	<filename>Achnanthidium gr minutissima.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ACHNANTHIDIUM\Achnanthidium gr minutissima.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>842</xmin>
+			<ymin>510</ymin>
+			<xmax>1339</xmax>
+			<ymax>1136</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Achnanthidium jackii-!-Achnanthidium jackii 1.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>ACHNANTHIDIUM</folder>
+	<filename>Achnanthidium jackii-!-Achnanthidium jackii 1.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ACHNANTHIDIUM\Achnanthidium jackii-!-Achnanthidium jackii 1.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>937</xmin>
+			<ymin>493</ymin>
+			<xmax>1354</xmax>
+			<ymax>734</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1107</xmin>
+			<ymin>388</ymin>
+			<xmax>1346</xmax>
+			<ymax>636</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Achnanthidium jackii-!-Achnanthidium jackii 421402 01.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>ACHNANTHIDIUM</folder>
+	<filename>Achnanthidium jackii-!-Achnanthidium jackii 421402 01.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ACHNANTHIDIUM\Achnanthidium jackii-!-Achnanthidium jackii 421402 01.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2592</width>
+		<height>1944</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>655</xmin>
+			<ymin>363</ymin>
+			<xmax>1466</xmax>
+			<ymax>1672</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Achnanthidium jackii-!-Achnanthidium jackii.xml

@@ -0,0 +1,62 @@
+<annotation>
+	<folder>ACHNANTHIDIUM</folder>
+	<filename>Achnanthidium jackii-!-Achnanthidium jackii.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ACHNANTHIDIUM\Achnanthidium jackii-!-Achnanthidium jackii.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>19</xmin>
+			<ymin>539</ymin>
+			<xmax>663</xmax>
+			<ymax>1226</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1131</xmin>
+			<ymin>590</ymin>
+			<xmax>1364</xmax>
+			<ymax>860</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1687</xmin>
+			<ymin>593</ymin>
+			<xmax>1900</xmax>
+			<ymax>737</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>398</xmin>
+			<ymin>1336</ymin>
+			<xmax>714</xmax>
+			<ymax>1524</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Achnanthidium jackii.xml

@@ -0,0 +1,50 @@
+<annotation>
+	<folder>ACHNANTHIDIUM</folder>
+	<filename>Achnanthidium jackii.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ACHNANTHIDIUM\Achnanthidium jackii.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>424</xmin>
+			<ymin>9</ymin>
+			<xmax>848</xmax>
+			<ymax>388</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>405</xmin>
+			<ymin>707</ymin>
+			<xmax>919</xmax>
+			<ymax>1278</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1061</xmin>
+			<ymin>653</ymin>
+			<xmax>1220</xmax>
+			<ymax>993</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Achnanthidium minutissimum-!-Achnanthidium minutissimum.xml

@@ -0,0 +1,74 @@
+<annotation>
+	<folder>ACHNANTHIDIUM</folder>
+	<filename>Achnanthidium minutissimum-!-Achnanthidium minutissimum.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ACHNANTHIDIUM\Achnanthidium minutissimum-!-Achnanthidium minutissimum.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>546</xmin>
+			<ymin>780</ymin>
+			<xmax>961</xmax>
+			<ymax>960</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>946</xmin>
+			<ymin>331</ymin>
+			<xmax>1053</xmax>
+			<ymax>963</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1336</xmin>
+			<ymin>797</ymin>
+			<xmax>1802</xmax>
+			<ymax>1231</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>961</xmin>
+			<ymin>578</ymin>
+			<xmax>1376</xmax>
+			<ymax>982</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1902</xmin>
+			<ymin>5</ymin>
+			<xmax>2049</xmax>
+			<ymax>660</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Achnanthidium minutissimum.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>ACHNANTHIDIUM</folder>
+	<filename>Achnanthidium minutissimum.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ACHNANTHIDIUM\Achnanthidium minutissimum.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>975</xmin>
+			<ymin>602</ymin>
+			<xmax>1476</xmax>
+			<ymax>934</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Achnanthidium saprophillum-!-Achnanthidium saprophillum.xml

@@ -0,0 +1,110 @@
+<annotation>
+	<folder>ACHNANTHIDIUM</folder>
+	<filename>Achnanthidium saprophillum-!-Achnanthidium saprophillum.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ACHNANTHIDIUM\Achnanthidium saprophillum-!-Achnanthidium saprophillum.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>198</xmin>
+			<ymin>187</ymin>
+			<xmax>468</xmax>
+			<ymax>317</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>815</xmin>
+			<ymin>265</ymin>
+			<xmax>1048</xmax>
+			<ymax>395</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>395</xmin>
+			<ymin>804</ymin>
+			<xmax>615</xmax>
+			<ymax>1048</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1068</xmin>
+			<ymin>617</ymin>
+			<xmax>1319</xmax>
+			<ymax>778</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1690</xmin>
+			<ymin>824</ymin>
+			<xmax>2078</xmax>
+			<ymax>1029</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>703</xmin>
+			<ymin>1324</ymin>
+			<xmax>959</xmax>
+			<ymax>1490</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1261</xmin>
+			<ymin>1258</ymin>
+			<xmax>1447</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1283</xmin>
+			<ymin>992</ymin>
+			<xmax>1500</xmax>
+			<ymax>1122</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Achnanthidium saprophillum.xml

@@ -0,0 +1,50 @@
+<annotation>
+	<folder>ACHNANTHIDIUM</folder>
+	<filename>Achnanthidium saprophillum.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ACHNANTHIDIUM\Achnanthidium saprophillum.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>580</xmin>
+			<ymin>560</ymin>
+			<xmax>839</xmax>
+			<ymax>797</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1014</xmin>
+			<ymin>612</ymin>
+			<xmax>1241</xmax>
+			<ymax>919</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>100</xmin>
+			<ymin>1019</ymin>
+			<xmax>478</xmax>
+			<ymax>1336</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Adlafia bryphila.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>ADLAFIA</folder>
+	<filename>Adlafia bryphila.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ADLAFIA\Adlafia bryphila.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>997</xmin>
+			<ymin>807</ymin>
+			<xmax>1193</xmax>
+			<ymax>1193</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Adlafia minuscula var.muralis.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>ADLAFIA</folder>
+	<filename>Adlafia minuscula var.muralis.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\ADLAFIA\Adlafia minuscula var.muralis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>319</xmin>
+			<ymin>1087</ymin>
+			<xmax>1002</xmax>
+			<ymax>1483</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1195</xmin>
+			<ymin>824</ymin>
+			<xmax>1341</xmax>
+			<ymax>1097</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Amphipleura pellucida.xml

@@ -0,0 +1,62 @@
+<annotation>
+	<folder>AMPHIPLEURA</folder>
+	<filename>Amphipleura pellucida.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\AMPHIPLEURA\Amphipleura pellucida.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>39</xmin>
+			<ymin>819</ymin>
+			<xmax>353</xmax>
+			<ymax>1071</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1076</xmin>
+			<ymin>44</ymin>
+			<xmax>1753</xmax>
+			<ymax>461</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1595</xmin>
+			<ymin>563</ymin>
+			<xmax>1941</xmax>
+			<ymax>1339</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>787</xmin>
+			<ymin>778</ymin>
+			<xmax>1346</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Amphora copulata.xml

@@ -0,0 +1,62 @@
+<annotation>
+	<folder>AMPHORA</folder>
+	<filename>Amphora copulata.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\AMPHORA\Amphora copulata.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>929</xmin>
+			<ymin>575</ymin>
+			<xmax>1305</xmax>
+			<ymax>1080</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1531</xmin>
+			<ymin>426</ymin>
+			<xmax>2080</xmax>
+			<ymax>821</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1651</xmin>
+			<ymin>848</ymin>
+			<xmax>1971</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>37</xmin>
+			<ymin>39</ymin>
+			<xmax>932</xmax>
+			<ymax>212</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Amphora lange-bertalotti.xml

@@ -0,0 +1,50 @@
+<annotation>
+	<folder>AMPHORA</folder>
+	<filename>Amphora lange-bertalotti.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\AMPHORA\Amphora lange-bertalotti.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>334</xmin>
+			<ymin>122</ymin>
+			<xmax>1278</xmax>
+			<ymax>290</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>448</xmin>
+			<ymin>302</ymin>
+			<xmax>1136</xmax>
+			<ymax>593</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>563</xmin>
+			<ymin>436</ymin>
+			<xmax>1861</xmax>
+			<ymax>887</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Amphora minutisima-!-Amphora minutissima.xml

@@ -0,0 +1,50 @@
+<annotation>
+	<folder>AMPHORA</folder>
+	<filename>Amphora minutisima-!-Amphora minutissima.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\AMPHORA\Amphora minutisima-!-Amphora minutissima.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>764</xmin>
+			<ymin>765</ymin>
+			<xmax>1620</xmax>
+			<ymax>1409</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1283</xmin>
+			<ymin>1185</ymin>
+			<xmax>1636</xmax>
+			<ymax>1541</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1648</xmin>
+			<ymin>565</ymin>
+			<xmax>2080</xmax>
+			<ymax>791</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Amphora minutisima.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>AMPHORA</folder>
+	<filename>Amphora minutisima.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\AMPHORA\Amphora minutisima.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1066</xmin>
+			<ymin>466</ymin>
+			<xmax>1495</xmax>
+			<ymax>1080</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Amphora pediculus.xml

@@ -0,0 +1,50 @@
+<annotation>
+	<folder>AMPHORA</folder>
+	<filename>Amphora pediculus.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\AMPHORA\Amphora pediculus.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1058</xmin>
+			<ymin>693</ymin>
+			<xmax>1446</xmax>
+			<ymax>973</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>514</xmin>
+			<ymin>822</ymin>
+			<xmax>729</xmax>
+			<ymax>985</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>5</xmin>
+			<ymin>1236</ymin>
+			<xmax>229</xmax>
+			<ymax>1451</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Bacillaria paxillifera.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>BACILLARIA</folder>
+	<filename>Bacillaria paxillifera.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\BACILLARIA\Bacillaria paxillifera.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>141</xmin>
+			<ymin>5</ymin>
+			<xmax>1624</xmax>
+			<ymax>1453</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Brachysira liliana.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>BRACHYSIRA</folder>
+	<filename>Brachysira liliana.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\BRACHYSIRA\Brachysira liliana.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>7</xmin>
+			<ymin>302</ymin>
+			<xmax>568</xmax>
+			<ymax>1002</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>666</xmin>
+			<ymin>348</ymin>
+			<xmax>1627</xmax>
+			<ymax>1224</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Brachysira neoexilis-!-Brachysira neoexcilis.xml

@@ -0,0 +1,62 @@
+<annotation>
+	<folder>BRACHYSIRA</folder>
+	<filename>Brachysira neoexilis-!-Brachysira neoexcilis.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\BRACHYSIRA\Brachysira neoexilis-!-Brachysira neoexcilis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>566</xmin>
+			<ymin>482</ymin>
+			<xmax>1015</xmax>
+			<ymax>760</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1085</xmin>
+			<ymin>468</ymin>
+			<xmax>1800</xmax>
+			<ymax>848</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1154</xmin>
+			<ymin>839</ymin>
+			<xmax>1707</xmax>
+			<ymax>1160</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>571</xmin>
+			<ymin>860</ymin>
+			<xmax>1020</xmax>
+			<ymax>1331</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Brachysira neoexilis-!-Brachysira neoexilis.xml

@@ -0,0 +1,50 @@
+<annotation>
+	<folder>BRACHYSIRA</folder>
+	<filename>Brachysira neoexilis-!-Brachysira neoexilis.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\BRACHYSIRA\Brachysira neoexilis-!-Brachysira neoexilis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>288</xmin>
+			<ymin>236</ymin>
+			<xmax>858</xmax>
+			<ymax>368</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1024</xmin>
+			<ymin>534</ymin>
+			<xmax>1371</xmax>
+			<ymax>1141</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>10</xmin>
+			<ymin>673</ymin>
+			<xmax>763</xmax>
+			<ymax>851</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Brachysira neoexilis.xml

@@ -0,0 +1,50 @@
+<annotation>
+	<folder>BRACHYSIRA</folder>
+	<filename>Brachysira neoexilis.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\BRACHYSIRA\Brachysira neoexilis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1063</xmin>
+			<ymin>644</ymin>
+			<xmax>1324</xmax>
+			<ymax>1114</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>297</xmin>
+			<ymin>483</ymin>
+			<xmax>546</xmax>
+			<ymax>758</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>305</xmin>
+			<ymin>934</ymin>
+			<xmax>671</xmax>
+			<ymax>1361</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/CONTROL_ Amphora ovalis.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>AMPHORA</folder>
+	<filename>CONTROL_ Amphora ovalis.JPG</filename>
+	<path>C:\Temp\Image-recognition-master\unique_names\Anwar\AMPHORA\CONTROL_ Amphora ovalis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>212</xmin>
+			<ymin>217</ymin>
+			<xmax>1641</xmax>
+			<ymax>956</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/CONTROL_ Gomphonema agur.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>diatomeeenpic</folder>
+	<filename>CONTROL_ Gomphonema agur.JPG</filename>
+	<path>/Users/markoost/Documents/kennis/data/diatomeeenpic/CONTROL_ Gomphonema agur.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1353</xmin>
+			<ymin>46</ymin>
+			<xmax>1685</xmax>
+			<ymax>1052</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/CONTROL_ Gomphonema supertergestinum.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>diatomeeenpic</folder>
+	<filename>CONTROL_ Gomphonema supertergestinum.JPG</filename>
+	<path>/Users/markoost/Documents/kennis/data/diatomeeenpic/CONTROL_ Gomphonema supertergestinum.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>706</xmin>
+			<ymin>238</ymin>
+			<xmax>1779</xmax>
+			<ymax>1056</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/CONTROL_ Gyrosigma obtusatum.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>diatomeeenpic</folder>
+	<filename>CONTROL_ Gyrosigma obtusatum.JPG</filename>
+	<path>/Users/markoost/Documents/kennis/data/diatomeeenpic/CONTROL_ Gyrosigma obtusatum.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>104</xmin>
+			<ymin>279</ymin>
+			<xmax>2080</xmax>
+			<ymax>1201</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Caloneis amphisbaena.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CALONEIS</folder>
+	<filename>Caloneis amphisbaena.JPG</filename>
+	<path>C:/Users/snijd507/Documents/Python Scripts/DataScience - ImageRecognition/Image-recognition-master/data/diatomeeen/CALONEIS/Caloneis amphisbaena.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>631</xmin>
+			<ymin>587</ymin>
+			<xmax>1898</xmax>
+			<ymax>1386</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Caloneis lancetulla.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CALONEIS</folder>
+	<filename>Caloneis lancetulla.JPG</filename>
+	<path>C:/Users/snijd507/Documents/Python Scripts/DataScience - ImageRecognition/Image-recognition-master/data/diatomeeen/CALONEIS/Caloneis lancetulla.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>Diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1136</xmin>
+			<ymin>337</ymin>
+			<xmax>1352</xmax>
+			<ymax>981</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Caloneis silicula-!-Caloneis silicula 1.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CALONEIS</folder>
+	<filename>Caloneis silicula-!-Caloneis silicula 1.JPG</filename>
+	<path>C:/Users/snijd507/Documents/Python Scripts/DataScience - ImageRecognition/Image-recognition-master/data/unique_names/Pieter Jan/CALONEIS/Caloneis silicula-!-Caloneis silicula 1.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>596</xmin>
+			<ymin>45</ymin>
+			<xmax>1511</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Caloneis silicula-!-Caloneis silicula.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>CALONEIS</folder>
+	<filename>Caloneis silicula-!-Caloneis silicula.JPG</filename>
+	<path>C:/Users/snijd507/Documents/Python Scripts/DataScience - ImageRecognition/Image-recognition-master/data/unique_names/Pieter Jan/CALONEIS/Caloneis silicula-!-Caloneis silicula.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>821</xmin>
+			<ymin>412</ymin>
+			<xmax>1565</xmax>
+			<ymax>1160</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1100</xmin>
+			<ymin>528</ymin>
+			<xmax>1964</xmax>
+			<ymax>1094</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Caloneis silicula.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>CALONEIS</folder>
+	<filename>Caloneis silicula.JPG</filename>
+	<path>C:/Users/snijd507/Documents/Python Scripts/DataScience - ImageRecognition/Image-recognition-master/data/unique_names/Pieter Jan/CALONEIS/Caloneis silicula.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1723</xmin>
+			<ymin>507</ymin>
+			<xmax>1970</xmax>
+			<ymax>774</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>498</xmin>
+			<ymin>669</ymin>
+			<xmax>1923</xmax>
+			<ymax>1215</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cavinula cocconeiformis.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>CAVINULA</folder>
+	<filename>Cavinula cocconeiformis.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CAVINULA\Cavinula cocconeiformis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1116</xmin>
+			<ymin>581</ymin>
+			<xmax>1536</xmax>
+			<ymax>1110</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1023</xmin>
+			<ymin>1191</ymin>
+			<xmax>1292</xmax>
+			<ymax>1379</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Chamaepinnularia evanida 421402 01.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CHAMAEPINNULARIA</folder>
+	<filename>Chamaepinnularia evanida 421402 01.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CHAMAEPINNULARIA\Chamaepinnularia evanida 421402 01.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2592</width>
+		<height>1944</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1582</xmin>
+			<ymin>1526</ymin>
+			<xmax>2109</xmax>
+			<ymax>1944</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Chamaepinnularia krookiformis.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>PINNULARIA</folder>
+	<filename>Chamaepinnularia krookiformis.JPG</filename>
+	<path>/Users/sharonverlaan/Downloads/unique_names/Sharon/PINNULARIA/Chamaepinnularia krookiformis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>850</xmin>
+			<ymin>644</ymin>
+			<xmax>1407</xmax>
+			<ymax>1216</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1250</xmin>
+			<ymin>344</ymin>
+			<xmax>1718</xmax>
+			<ymax>952</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cocconeis neothumensis.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>COCCONEIS</folder>
+	<filename>Cocconeis neothumensis.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\COCCONEIS\Cocconeis neothumensis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1064</xmin>
+			<ymin>746</ymin>
+			<xmax>1287</xmax>
+			<ymax>925</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cocconeis placentula .xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>COCCONEIS</folder>
+	<filename>Cocconeis placentula .JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\COCCONEIS\Cocconeis placentula .JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>806</xmin>
+			<ymin>594</ymin>
+			<xmax>1316</xmax>
+			<ymax>953</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>31</xmin>
+			<ymin>863</ymin>
+			<xmax>1293</xmax>
+			<ymax>1215</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cocconeis-!-Cocconeis.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>COCCONEIS</folder>
+	<filename>Cocconeis-!-Cocconeis.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\COCCONEIS\Cocconeis-!-Cocconeis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>533</xmin>
+			<ymin>510</ymin>
+			<xmax>1465</xmax>
+			<ymax>1328</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cocconeis.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>COCCONEIS</folder>
+	<filename>Cocconeis.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\COCCONEIS\Cocconeis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>759</xmin>
+			<ymin>632</ymin>
+			<xmax>1464</xmax>
+			<ymax>1096</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Craticula accomoda 421402 01.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CRATICULA</folder>
+	<filename>Craticula accomoda 421402 01.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CRATICULA\Craticula accomoda 421402 01.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2592</width>
+		<height>1944</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1659</xmin>
+			<ymin>517</ymin>
+			<xmax>1934</xmax>
+			<ymax>1382</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Craticula ambigua-!-Craticula ambigua.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>CRATICULA</folder>
+	<filename>Craticula ambigua-!-Craticula ambigua.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CRATICULA\Craticula ambigua-!-Craticula ambigua.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>155</xmin>
+			<ymin>1</ymin>
+			<xmax>2078</xmax>
+			<ymax>1412</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1855</xmin>
+			<ymin>91</ymin>
+			<xmax>2060</xmax>
+			<ymax>663</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Craticula buderi.xml

@@ -0,0 +1,50 @@
+<annotation>
+	<folder>CRATICULA</folder>
+	<filename>Craticula buderi.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CRATICULA\Craticula buderi.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>770</xmin>
+			<ymin>1022</ymin>
+			<xmax>1619</xmax>
+			<ymax>1263</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>928</xmin>
+			<ymin>261</ymin>
+			<xmax>1508</xmax>
+			<ymax>1215</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>342</xmin>
+			<ymin>155</ymin>
+			<xmax>890</xmax>
+			<ymax>509</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Craticula halophila.xml

@@ -0,0 +1,50 @@
+<annotation>
+	<folder>CRATICULA</folder>
+	<filename>Craticula halophila.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CRATICULA\Craticula halophila.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>216</xmin>
+			<ymin>351</ymin>
+			<xmax>660</xmax>
+			<ymax>901</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>911</xmin>
+			<ymin>104</ymin>
+			<xmax>1275</xmax>
+			<ymax>1476</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1639</xmin>
+			<ymin>1171</ymin>
+			<xmax>1997</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Craticula-!-Craticula.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CRATICULA</folder>
+	<filename>Craticula-!-Craticula.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CRATICULA\Craticula-!-Craticula.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1</xmin>
+			<ymin>1</ymin>
+			<xmax>1813</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Craticula.xml

@@ -0,0 +1,50 @@
+<annotation>
+	<folder>CRATICULA</folder>
+	<filename>Craticula.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CRATICULA\Craticula.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>918</xmin>
+			<ymin>543</ymin>
+			<xmax>1241</xmax>
+			<ymax>769</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>455</xmin>
+			<ymin>215</ymin>
+			<xmax>1878</xmax>
+			<ymax>1524</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1883</xmin>
+			<ymin>532</ymin>
+			<xmax>2080</xmax>
+			<ymax>964</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymatopleura librile.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CYMATOPLEURA</folder>
+	<filename>Cymatopleura librile.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMATOPLEURA\Cymatopleura librile.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1059</xmin>
+			<ymin>63</ymin>
+			<xmax>2019</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymatopleura solea var.apiculata.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CYMATOPLEURA</folder>
+	<filename>Cymatopleura solea var.apiculata.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMATOPLEURA\Cymatopleura solea var.apiculata.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>790</xmin>
+			<ymin>122</ymin>
+			<xmax>2070</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella affiniformis _.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella affiniformis _.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella affiniformis _.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>818</xmin>
+			<ymin>401</ymin>
+			<xmax>1146</xmax>
+			<ymax>1281</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella compacta-!-Cymbella compacta 1.xml

@@ -0,0 +1,50 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella compacta-!-Cymbella compacta 1.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella compacta-!-Cymbella compacta 1.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>616</xmin>
+			<ymin>669</ymin>
+			<xmax>1680</xmax>
+			<ymax>1102</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1693</xmin>
+			<ymin>814</ymin>
+			<xmax>2005</xmax>
+			<ymax>1128</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>441</xmin>
+			<ymin>1240</ymin>
+			<xmax>738</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella compacta-!-Cymbella compacta 2.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella compacta-!-Cymbella compacta 2.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella compacta-!-Cymbella compacta 2.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>934</xmin>
+			<ymin>191</ymin>
+			<xmax>1429</xmax>
+			<ymax>1263</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>283</xmin>
+			<ymin>222</ymin>
+			<xmax>723</xmax>
+			<ymax>1322</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella compacta-!-Cymbella compacta-!-Cymbella compacta.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella compacta-!-Cymbella compacta-!-Cymbella compacta.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella compacta-!-Cymbella compacta-!-Cymbella compacta.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>736</xmin>
+			<ymin>178</ymin>
+			<xmax>1888</xmax>
+			<ymax>1294</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella compacta-!-Cymbella compacta.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella compacta-!-Cymbella compacta.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella compacta-!-Cymbella compacta.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>551</xmin>
+			<ymin>702</ymin>
+			<xmax>1724</xmax>
+			<ymax>1091</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1495</xmin>
+			<ymin>202</ymin>
+			<xmax>2039</xmax>
+			<ymax>753</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella compacta.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella compacta.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella compacta.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>688</xmin>
+			<ymin>156</ymin>
+			<xmax>1342</xmax>
+			<ymax>1176</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella cymbiformis-!-Cymbella cymbiformis.xml

@@ -0,0 +1,62 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella cymbiformis-!-Cymbella cymbiformis.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella cymbiformis-!-Cymbella cymbiformis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>949</xmin>
+			<ymin>394</ymin>
+			<xmax>1828</xmax>
+			<ymax>1109</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>121</xmin>
+			<ymin>576</ymin>
+			<xmax>964</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1111</xmin>
+			<ymin>940</ymin>
+			<xmax>1731</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>651</xmin>
+			<ymin>1</ymin>
+			<xmax>1276</xmax>
+			<ymax>709</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella cymbiformis.xml

@@ -0,0 +1,62 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella cymbiformis.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella cymbiformis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1134</xmin>
+			<ymin>142</ymin>
+			<xmax>1667</xmax>
+			<ymax>1428</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>580</xmin>
+			<ymin>568</ymin>
+			<xmax>905</xmax>
+			<ymax>868</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>167</xmin>
+			<ymin>655</ymin>
+			<xmax>657</xmax>
+			<ymax>1150</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>459</xmin>
+			<ymin>442</ymin>
+			<xmax>903</xmax>
+			<ymax>561</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella hustedtii.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella hustedtii.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella hustedtii.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>955</xmin>
+			<ymin>686</ymin>
+			<xmax>1308</xmax>
+			<ymax>1084</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella lanceolata-!-Cymbella lanceolata.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella lanceolata-!-Cymbella lanceolata.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella lanceolata-!-Cymbella lanceolata.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1146</xmin>
+			<ymin>940</ymin>
+			<xmax>1826</xmax>
+			<ymax>1319</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1</xmin>
+			<ymin>1</ymin>
+			<xmax>2073</xmax>
+			<ymax>1424</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella lange-bertalotii-!-Cymbella lange-bertalotii.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella lange-bertalotii-!-Cymbella lange-bertalotii.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella lange-bertalotii-!-Cymbella lange-bertalotii.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>211</xmin>
+			<ymin>251</ymin>
+			<xmax>1865</xmax>
+			<ymax>1455</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella neocistula-!-Cymbella neocistula.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella neocistula-!-Cymbella neocistula.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella neocistula-!-Cymbella neocistula.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>236</xmin>
+			<ymin>128</ymin>
+			<xmax>1716</xmax>
+			<ymax>1237</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>88</xmin>
+			<ymin>37</ymin>
+			<xmax>624</xmax>
+			<ymax>445</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella neocistula.xml

@@ -0,0 +1,50 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella neocistula.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella neocistula.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1308</xmin>
+			<ymin>633</ymin>
+			<xmax>1833</xmax>
+			<ymax>1104</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>278</xmin>
+			<ymin>220</ymin>
+			<xmax>1744</xmax>
+			<ymax>1346</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1474</xmin>
+			<ymin>1137</ymin>
+			<xmax>1755</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella parva-!-Cymbella parva _.xml

@@ -0,0 +1,74 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella parva-!-Cymbella parva _.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella parva-!-Cymbella parva _.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1095</xmin>
+			<ymin>389</ymin>
+			<xmax>1590</xmax>
+			<ymax>1235</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>985</xmin>
+			<ymin>951</ymin>
+			<xmax>1239</xmax>
+			<ymax>1179</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1537</xmin>
+			<ymin>164</ymin>
+			<xmax>1736</xmax>
+			<ymax>374</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>792</xmin>
+			<ymin>304</ymin>
+			<xmax>983</xmax>
+			<ymax>435</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>942</xmin>
+			<ymin>425</ymin>
+			<xmax>1073</xmax>
+			<ymax>727</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella parva-!-Cymbella parva.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella parva-!-Cymbella parva.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella parva-!-Cymbella parva.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1070</xmin>
+			<ymin>519</ymin>
+			<xmax>1398</xmax>
+			<ymax>1150</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella parva.xml

@@ -0,0 +1,50 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella parva.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella parva.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>847</xmin>
+			<ymin>628</ymin>
+			<xmax>1359</xmax>
+			<ymax>1038</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>467</xmin>
+			<ymin>433</ymin>
+			<xmax>759</xmax>
+			<ymax>605</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1159</xmin>
+			<ymin>432</ymin>
+			<xmax>1342</xmax>
+			<ymax>705</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella proxima-!-Cymbella proxima.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella proxima-!-Cymbella proxima.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella proxima-!-Cymbella proxima.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>5</xmin>
+			<ymin>92</ymin>
+			<xmax>2080</xmax>
+			<ymax>778</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>452</xmin>
+			<ymin>615</ymin>
+			<xmax>839</xmax>
+			<ymax>1317</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella proxima.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella proxima.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella proxima.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>731</xmin>
+			<ymin>27</ymin>
+			<xmax>1492</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella subcistula-!-Cymbella subcistula.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella subcistula-!-Cymbella subcistula.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella subcistula-!-Cymbella subcistula.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>805</xmin>
+			<ymin>37</ymin>
+			<xmax>1436</xmax>
+			<ymax>1328</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella subcistula.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella subcistula.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella subcistula.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>246</xmin>
+			<ymin>194</ymin>
+			<xmax>1837</xmax>
+			<ymax>1314</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella subleptoceros-!-Cymbella subleptoceros.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella subleptoceros-!-Cymbella subleptoceros.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella subleptoceros-!-Cymbella subleptoceros.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>955</xmin>
+			<ymin>299</ymin>
+			<xmax>1572</xmax>
+			<ymax>1143</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1</xmin>
+			<ymin>161</ymin>
+			<xmax>403</xmax>
+			<ymax>707</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella subleptoceros.xml

@@ -0,0 +1,62 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella subleptoceros.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella subleptoceros.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>121</xmin>
+			<ymin>1117</ymin>
+			<xmax>424</xmax>
+			<ymax>1450</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>726</xmin>
+			<ymin>1283</ymin>
+			<xmax>918</xmax>
+			<ymax>1537</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>400</xmin>
+			<ymin>838</ymin>
+			<xmax>701</xmax>
+			<ymax>950</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1075</xmin>
+			<ymin>186</ymin>
+			<xmax>1508</xmax>
+			<ymax>1217</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella-!-Cymbella.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella-!-Cymbella.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella-!-Cymbella.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>946</xmin>
+			<ymin>438</ymin>
+			<xmax>1264</xmax>
+			<ymax>1020</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1</xmin>
+			<ymin>491</ymin>
+			<xmax>1847</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbella.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>CYMBELLA</folder>
+	<filename>Cymbella.JPG</filename>
+	<path>C:\Users\snijd507\Documents\Python Scripts\DataScience - ImageRecognition\Image-recognition-master\data\unique_names\Pieter Jan\CYMBELLA\Cymbella.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>913</xmin>
+			<ymin>542</ymin>
+			<xmax>1198</xmax>
+			<ymax>1135</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbopleura amphicephala.xml

@@ -0,0 +1,50 @@
+<annotation>
+	<folder>CYMBOPLEURA</folder>
+	<filename>Cymbopleura amphicephala.JPG</filename>
+	<path>/home/leslie/Downloads/unique_names/Leslie/CYMBOPLEURA/Cymbopleura amphicephala.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>845</xmin>
+			<ymin>519</ymin>
+			<xmax>1279</xmax>
+			<ymax>1202</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1545</xmin>
+			<ymin>1022</ymin>
+			<xmax>1766</xmax>
+			<ymax>1478</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1321</xmin>
+			<ymin>77</ymin>
+			<xmax>1603</xmax>
+			<ymax>356</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbopleura florentina var. brevis

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>CYMBOPLEURA</folder>
+	<filename>Cymbopleura florentina var. brevis.JPG</filename>
+	<path>/home/leslie/Downloads/unique_names/Leslie/CYMBOPLEURA/Cymbopleura florentina var. brevis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>64</xmin>
+			<ymin>614</ymin>
+			<xmax>440</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>359</xmin>
+			<ymin>485</ymin>
+			<xmax>1872</xmax>
+			<ymax>1215</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbopleura florentina var. brevis-!-Cymbopleura florentina var. brevis

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>CYMBOPLEURA</folder>
+	<filename>Cymbopleura florentina var. brevis-!-Cymbopleura florentina var. brevis.JPG</filename>
+	<path>/home/leslie/Downloads/unique_names/Leslie/CYMBOPLEURA/Cymbopleura florentina var. brevis-!-Cymbopleura florentina var. brevis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>326</xmin>
+			<ymin>435</ymin>
+			<xmax>1888</xmax>
+			<ymax>1240</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>53</xmin>
+			<ymin>664</ymin>
+			<xmax>426</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbopleura naviculiformis-!-Cymbopleura naviculiformis 1.xml

@@ -0,0 +1,122 @@
+<annotation>
+	<folder>CYMBOPLEURA</folder>
+	<filename>Cymbopleura naviculiformis-!-Cymbopleura naviculiformis 1.JPG</filename>
+	<path>/home/leslie/Downloads/unique_names/Leslie/CYMBOPLEURA/Cymbopleura naviculiformis-!-Cymbopleura naviculiformis 1.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1</xmin>
+			<ymin>464</ymin>
+			<xmax>130</xmax>
+			<ymax>952</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1</xmin>
+			<ymin>952</ymin>
+			<xmax>263</xmax>
+			<ymax>1102</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>669</xmin>
+			<ymin>427</ymin>
+			<xmax>927</xmax>
+			<ymax>922</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>753</xmin>
+			<ymin>388</ymin>
+			<xmax>1540</xmax>
+			<ymax>1007</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1329</xmin>
+			<ymin>170</ymin>
+			<xmax>1642</xmax>
+			<ymax>678</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>740</xmin>
+			<ymin>1167</ymin>
+			<xmax>1114</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>949</xmin>
+			<ymin>664</ymin>
+			<xmax>1903</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1661</xmin>
+			<ymin>978</ymin>
+			<xmax>1938</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1937</xmin>
+			<ymin>933</ymin>
+			<xmax>2080</xmax>
+			<ymax>1038</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbopleura naviculiformis-!-Cymbopleura naviculiformis.xml

@@ -0,0 +1,158 @@
+<annotation>
+	<folder>CYMBOPLEURA</folder>
+	<filename>Cymbopleura naviculiformis-!-Cymbopleura naviculiformis.JPG</filename>
+	<path>/home/leslie/Downloads/unique_names/Leslie/CYMBOPLEURA/Cymbopleura naviculiformis-!-Cymbopleura naviculiformis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>3</xmin>
+			<ymin>433</ymin>
+			<xmax>135</xmax>
+			<ymax>959</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1</xmin>
+			<ymin>941</ymin>
+			<xmax>296</xmax>
+			<ymax>1113</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>656</xmin>
+			<ymin>420</ymin>
+			<xmax>917</xmax>
+			<ymax>912</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>763</xmin>
+			<ymin>385</ymin>
+			<xmax>1534</xmax>
+			<ymax>996</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1317</xmin>
+			<ymin>149</ymin>
+			<xmax>1658</xmax>
+			<ymax>667</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>727</xmin>
+			<ymin>1157</ymin>
+			<xmax>1117</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>950</xmin>
+			<ymin>670</ymin>
+			<xmax>1884</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1105</xmin>
+			<ymin>1033</ymin>
+			<xmax>1595</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1653</xmin>
+			<ymin>970</ymin>
+			<xmax>1932</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1843</xmin>
+			<ymin>1135</ymin>
+			<xmax>2080</xmax>
+			<ymax>1352</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1921</xmin>
+			<ymin>938</ymin>
+			<xmax>2080</xmax>
+			<ymax>1034</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>567</xmin>
+			<ymin>1</ymin>
+			<xmax>686</xmax>
+			<ymax>117</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Cymbopleura naviculiformis.xml

@@ -0,0 +1,158 @@
+<annotation>
+	<folder>CYMBOPLEURA</folder>
+	<filename>Cymbopleura naviculiformis.JPG</filename>
+	<path>/home/leslie/Downloads/unique_names/Leslie/CYMBOPLEURA/Cymbopleura naviculiformis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2076</width>
+		<height>1541</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1</xmin>
+			<ymin>434</ymin>
+			<xmax>144</xmax>
+			<ymax>959</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1</xmin>
+			<ymin>939</ymin>
+			<xmax>299</xmax>
+			<ymax>1107</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>717</xmin>
+			<ymin>1142</ymin>
+			<xmax>1117</xmax>
+			<ymax>1541</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>670</xmin>
+			<ymin>415</ymin>
+			<xmax>914</xmax>
+			<ymax>907</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>764</xmin>
+			<ymin>378</ymin>
+			<xmax>1541</xmax>
+			<ymax>1000</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>583</xmin>
+			<ymin>1</ymin>
+			<xmax>679</xmax>
+			<ymax>112</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1327</xmin>
+			<ymin>160</ymin>
+			<xmax>1636</xmax>
+			<ymax>625</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>954</xmin>
+			<ymin>659</ymin>
+			<xmax>1878</xmax>
+			<ymax>1541</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1087</xmin>
+			<ymin>1038</ymin>
+			<xmax>1586</xmax>
+			<ymax>1541</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1661</xmin>
+			<ymin>967</ymin>
+			<xmax>1930</xmax>
+			<ymax>1541</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1833</xmin>
+			<ymin>1123</ymin>
+			<xmax>2076</xmax>
+			<ymax>1365</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1912</xmin>
+			<ymin>920</ymin>
+			<xmax>2076</xmax>
+			<ymax>1037</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Denticula subtilis.xml

@@ -0,0 +1,158 @@
+<annotation>
+	<folder>DENTICULA</folder>
+	<filename>Denticula subtilis.JPG</filename>
+	<path>/home/leslie/Downloads/unique_names/Leslie/DENTICULA/Denticula subtilis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>179</xmin>
+			<ymin>144</ymin>
+			<xmax>398</xmax>
+			<ymax>546</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>653</xmin>
+			<ymin>819</ymin>
+			<xmax>837</xmax>
+			<ymax>925</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>674</xmin>
+			<ymin>836</ymin>
+			<xmax>911</xmax>
+			<ymax>1073</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>830</xmin>
+			<ymin>1004</ymin>
+			<xmax>1414</xmax>
+			<ymax>1319</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1703</xmin>
+			<ymin>1180</ymin>
+			<xmax>1822</xmax>
+			<ymax>1422</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1788</xmin>
+			<ymin>901</ymin>
+			<xmax>1992</xmax>
+			<ymax>1533</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>942</xmin>
+			<ymin>783</ymin>
+			<xmax>1282</xmax>
+			<ymax>896</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1188</xmin>
+			<ymin>420</ymin>
+			<xmax>1272</xmax>
+			<ymax>646</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1266</xmin>
+			<ymin>393</ymin>
+			<xmax>1634</xmax>
+			<ymax>785</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1313</xmin>
+			<ymin>314</ymin>
+			<xmax>1753</xmax>
+			<ymax>451</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1034</xmin>
+			<ymin>1</ymin>
+			<xmax>1371</xmax>
+			<ymax>264</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1241</xmin>
+			<ymin>1</ymin>
+			<xmax>1429</xmax>
+			<ymax>112</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Denticula tenuis.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>DENTICULA</folder>
+	<filename>Denticula tenuis.JPG</filename>
+	<path>/home/leslie/Downloads/unique_names/Leslie/DENTICULA/Denticula tenuis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>911</xmin>
+			<ymin>546</ymin>
+			<xmax>1263</xmax>
+			<ymax>940</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1146</xmin>
+			<ymin>1219</ymin>
+			<xmax>1482</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Denticulata sundaysensis.xml

@@ -0,0 +1,62 @@
+<annotation>
+	<folder>DENTICULATA</folder>
+	<filename>Denticulata sundaysensis.JPG</filename>
+	<path>/home/leslie/Downloads/unique_names/Leslie/DENTICULATA/Denticulata sundaysensis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>340</xmin>
+			<ymin>967</ymin>
+			<xmax>598</xmax>
+			<ymax>1448</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>356</xmin>
+			<ymin>1036</ymin>
+			<xmax>584</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>882</xmin>
+			<ymin>828</ymin>
+			<xmax>1353</xmax>
+			<ymax>1099</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1292</xmin>
+			<ymin>1069</ymin>
+			<xmax>1895</xmax>
+			<ymax>1340</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Diadesmis cf.brekkaensis

@@ -0,0 +1,74 @@
+<annotation>
+	<folder>DIADESMIS</folder>
+	<filename>Diadesmis cf.brekkaensis.JPG</filename>
+	<path>/home/leslie/Downloads/unique_names/Leslie/DIADESMIS/Diadesmis cf.brekkaensis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1000</xmin>
+			<ymin>483</ymin>
+			<xmax>1229</xmax>
+			<ymax>872</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1321</xmin>
+			<ymin>483</ymin>
+			<xmax>1538</xmax>
+			<ymax>862</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>171</xmin>
+			<ymin>1130</ymin>
+			<xmax>413</xmax>
+			<ymax>1375</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>413</xmin>
+			<ymin>1327</ymin>
+			<xmax>684</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1</xmin>
+			<ymin>117</ymin>
+			<xmax>217</xmax>
+			<ymax>339</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Diadesmis cf.brekkaensis-!-Diadesmis cf.brekkaensis

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>DIADESMIS</folder>
+	<filename>Diadesmis cf.brekkaensis-!-Diadesmis cf.brekkaensis.JPG</filename>
+	<path>/home/leslie/Downloads/unique_names/Leslie/DIADESMIS/Diadesmis cf.brekkaensis-!-Diadesmis cf.brekkaensis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1192</xmin>
+			<ymin>657</ymin>
+			<xmax>1476</xmax>
+			<ymax>833</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Diatoma moniliformis-!-Diatoma moniliformis.xml

@@ -0,0 +1,134 @@
+<annotation>
+	<folder>DIATOMA</folder>
+	<filename>Diatoma moniliformis-!-Diatoma moniliformis.JPG</filename>
+	<path>/home/leslie/Downloads/unique_names/Leslie/DIATOMA/Diatoma moniliformis-!-Diatoma moniliformis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>80</xmin>
+			<ymin>386</ymin>
+			<xmax>271</xmax>
+			<ymax>894</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>459</xmin>
+			<ymin>248</ymin>
+			<xmax>743</xmax>
+			<ymax>1364</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>350</xmin>
+			<ymin>1214</ymin>
+			<xmax>469</xmax>
+			<ymax>1372</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>387</xmin>
+			<ymin>1459</ymin>
+			<xmax>542</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>613</xmin>
+			<ymin>1043</ymin>
+			<xmax>1029</xmax>
+			<ymax>1540</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>445</xmin>
+			<ymin>680</ymin>
+			<xmax>540</xmax>
+			<ymax>957</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>725</xmin>
+			<ymin>1</ymin>
+			<xmax>842</xmax>
+			<ymax>751</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>926</xmin>
+			<ymin>169</ymin>
+			<xmax>1306</xmax>
+			<ymax>1211</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1569</xmin>
+			<ymin>93</ymin>
+			<xmax>1751</xmax>
+			<ymax>1264</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1711</xmin>
+			<ymin>491</ymin>
+			<xmax>1816</xmax>
+			<ymax>1143</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Diatoma moniliformis.xml

@@ -0,0 +1,62 @@
+<annotation>
+	<folder>DIATOMA</folder>
+	<filename>Diatoma moniliformis.JPG</filename>
+	<path>/home/leslie/Downloads/unique_names/Leslie/DIATOMA/Diatoma moniliformis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1</xmin>
+			<ymin>102</ymin>
+			<xmax>290</xmax>
+			<ymax>443</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1146</xmin>
+			<ymin>988</ymin>
+			<xmax>1563</xmax>
+			<ymax>1167</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1500</xmin>
+			<ymin>617</ymin>
+			<xmax>2027</xmax>
+			<ymax>959</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1440</xmin>
+			<ymin>577</ymin>
+			<xmax>2034</xmax>
+			<ymax>907</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Diatoma problematica-!-Diatoma problematica.xml

@@ -0,0 +1,26 @@
+<annotation>
+	<folder>DIATOMA</folder>
+	<filename>Diatoma problematica-!-Diatoma problematica.JPG</filename>
+	<path>/home/leslie/Downloads/unique_names/Leslie/DIATOMA/Diatoma problematica-!-Diatoma problematica.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>971</xmin>
+			<ymin>412</ymin>
+			<xmax>1477</xmax>
+			<ymax>1135</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Diatoma problematica.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>DIATOMA</folder>
+	<filename>Diatoma problematica.JPG</filename>
+	<path>/home/leslie/Downloads/unique_names/Leslie/DIATOMA/Diatoma problematica.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>688</xmin>
+			<ymin>606</ymin>
+			<xmax>1158</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1043</xmin>
+			<ymin>715</ymin>
+			<xmax>1608</xmax>
+			<ymax>1165</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Diatoma tenuis-!-Diatoma tenuis.xml

@@ -0,0 +1,38 @@
+<annotation>
+	<folder>DIATOMA</folder>
+	<filename>Diatoma tenuis-!-Diatoma tenuis.JPG</filename>
+	<path>/home/leslie/Downloads/unique_names/Leslie/DIATOMA/Diatoma tenuis-!-Diatoma tenuis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>128</xmin>
+			<ymin>15</ymin>
+			<xmax>684</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>851</xmin>
+			<ymin>569</ymin>
+			<xmax>1501</xmax>
+			<ymax>1091</ymax>
+		</bndbox>
+	</object>
+</annotation>

annotations/Diatoma tenuis.xml

@@ -0,0 +1,50 @@
+<annotation>
+	<folder>DIATOMA</folder>
+	<filename>Diatoma tenuis.JPG</filename>
+	<path>/home/leslie/Downloads/unique_names/Leslie/DIATOMA/Diatoma tenuis.JPG</path>
+	<source>
+		<database>Unknown</database>
+	</source>
+	<size>
+		<width>2080</width>
+		<height>1544</height>
+		<depth>3</depth>
+	</size>
+	<segmented>0</segmented>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>0</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>627</xmin>
+			<ymin>594</ymin>
+			<xmax>1398</xmax>
+			<ymax>1157</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1337</xmin>
+			<ymin>373</ymin>
+			<xmax>1812</xmax>
+			<ymax>1544</ymax>
+		</bndbox>
+	</object>
+	<object>
+		<name>diatomeen</name>
+		<pose>Unspecified</pose>
+		<truncated>1</truncated>
+		<difficult>0</difficult>
+		<bndbox>
+			<xmin>1235</xmin>
+			<ymin>5</ymin>
+			<xmax>2080</xmax>
+			<ymax>361</ymax>
+		</bndbox>
+	</object>
+</annotation>