First commit

.gitignore

@@ -0,0 +1,4 @@
+flickr/img/
+flickr/.ipynb_checkpoints/
+model/.ipynb_checkpoints/
+data_augmentation/.ipynb_checkpoints/

LICENSE.md

@@ -0,0 +1,29 @@
+BSD 3-Clause License
+
+Copyright (c) 2017, Bert Carremans
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

README.md

@@ -0,0 +1,2 @@
+# vlindervinder
+Tool built with Python and convolutional neural networks to classifiy butterfly images

data_augmentation/data_augmentation_flickr_images.ipynb

@@ -0,0 +1,62 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "# Copyright 2014-2017 Bert Carremans\n",
+    "# Author: Bert Carremans <bertcarremans.be>\n",
+    "#\n",
+    "# License: BSD 3 clause\n",
+    "from keras.preprocessing.image import ImageDataGenerator, img_to_array, load_img\n",
+    "\n",
+    "train_datagen = ImageDataGenerator(\n",
+    "    rotation_range = 40,                  \n",
+    "    width_shift_range = 0.2,                  \n",
+    "    height_shift_range = 0.2,                  \n",
+    "    rescale = 1./255,                  \n",
+    "    shear_range = 0.2,                  \n",
+    "    zoom_range = 0.2,                     \n",
+    "    horizontal_flip = True)\n",
+    "\n",
+    "validation_datagen = ImageDataGenerator(rescale=1./255)\n",
+    "\n",
+    "train_generator = train_datagen.flow_from_directory(\n",
+    "        'data/train',\n",
+    "        target_size\n",
+    "        batch_size=32,\n",
+    "        class_mode='binary')\n",
+    "\n",
+    "validation_generator = validation_datagen.flow_from_directory(\n",
+    "        'data/validation',\n",
+    "        batch_size=32,\n",
+    "        class_mode='binary')\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

flickr/config.py

@@ -0,0 +1,4 @@
+API_KEY = 'a269db2de679d8ff1186c3e385a9a30a'
+API_SECRET = '68d696140c83cfa8'
+
+IMG_FOLDER = '/Users/bertcarremans/Data Science/Projecten/Vlindervinder/flickr/img/'

flickr/download_flickr_photos.ipynb

@@ -0,0 +1,137 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "# Copyright 2014-2017 Bert Carremans\n",
+    "# Author: Bert Carremans <bertcarremans.be>\n",
+    "#\n",
+    "# License: BSD 3 clause\n",
+    "\n",
+    "\n",
+    "from flickrapi import FlickrAPI  # https://pypi.python.org/pypi/flickrapi\n",
+    "import urllib\n",
+    "import os\n",
+    "import config\n",
+    "from random import randint\n",
+    "import time\n",
+    "\n",
+    "def download_flickr_photos(keywords, size='original', max_nb_img=-1):\n",
+    "    \"\"\"\n",
+    "    Downloads images based on keyword search on the Flickr website\n",
+    "    \n",
+    "    Parameters\n",
+    "    ----------\n",
+    "    keywords : string, list of strings\n",
+    "        Keyword to search for or a list of keywords should be given.\n",
+    "    size : one of the following strings 'thumbnail', 'square', 'medium', default: 'original'.\n",
+    "        Size of the image to download. In this function we only provide\n",
+    "        four options. More options are explained at \n",
+    "        http://librdf.org/flickcurl/api/flickcurl-searching-search-extras.html\n",
+    "    max_nb_img : int, default: -1\n",
+    "        Maximum number of images per keyword to download. If given a value of -1, all images\n",
+    "        will be downloaded\n",
+    "    \n",
+    "    Returns\n",
+    "    ------\n",
+    "    Images found based on the keyword are saved in a separate subfolder.\n",
+    "    \n",
+    "    Notes\n",
+    "    -----\n",
+    "    This function uses the Python package flickrapi and its walk method. \n",
+    "    FlickrAPI.walk has same parameters as FlickrAPI.search\n",
+    "    http://www.flickr.com/services/api/flickr.photos.search.html\n",
+    "    \n",
+    "    To use the Flickr API a set of API keys needs to be created on \n",
+    "    https://www.flickr.com/services/api/misc.api_keys.html\n",
+    "    \"\"\"\n",
+    "    if not (isinstance(keywords, str) or isinstance(keywords, list)):\n",
+    "        raise AttributeError('keywords must be a string or a list of strings')\n",
+    "        \n",
+    "    if not (size in ['thumbnail', 'square', 'medium', 'original']):\n",
+    "        raise AttributeError('size must be \"thumbnail\", \"square\", \"medium\" or \"original\"')\n",
+    "                             \n",
+    "    if not (max_nb_img == -1 or (max_nb_img > 0 and isinstance(max_nb_img, int))):\n",
+    "        raise AttributeError('max_nb_img must be an integer greater than zero or equal to -1')\n",
+    "    \n",
+    "    flickr = FlickrAPI(config.API_KEY, config.API_SECRET)\n",
+    "    \n",
+    "    if isinstance(keywords, str):\n",
+    "        keywords_list = []\n",
+    "        keywords_list.append(keywords)\n",
+    "    else:\n",
+    "        keywords_list = keywords\n",
+    "        \n",
+    "    if size == 'thumbnail':\n",
+    "        size_url = 'url_t'\n",
+    "    elif size == 'square':\n",
+    "        size_url = 'url_q'\n",
+    "    elif size == 'medium':\n",
+    "        size_url = 'url_c'\n",
+    "    elif size == 'original':\n",
+    "        size_url = 'url_o'\n",
+    "    \n",
+    "    for keyword in keywords_list:\n",
+    "        count = 0\n",
+    "                             \n",
+    "        #print('Downloading images for', keyword)\n",
+    "\n",
+    "        results_folder = config.IMG_FOLDER + keyword.replace(\" \", \"_\") + \"/\"\n",
+    "        if not os.path.exists(results_folder):\n",
+    "            os.makedirs(results_folder)\n",
+    "\n",
+    "        photos = flickr.walk(\n",
+    "                     text=keyword,\n",
+    "                     extras=size_url,\n",
+    "                     license='1,2,4,5',\n",
+    "                     per_page=50)\n",
+    "        \n",
+    "        urls = []\n",
+    "        for photo in photos:\n",
+    "            t = randint(1, 3)\n",
+    "            time.sleep(t)\n",
+    "            count += 1\n",
+    "            if max_nb_img != -1:\n",
+    "                if count > max_nb_img:\n",
+    "                    print('Reached maximum number of images to download')\n",
+    "                    break\n",
+    "            try:\n",
+    "                url=photo.get(size_url)\n",
+    "                urls.append(url)\n",
+    "                \n",
+    "                urllib.request.urlretrieve(url,  results_folder + str(count) +\".jpg\")\n",
+    "                print('Downloading image #' + str(count) + ' from url ' + url)\n",
+    "            except Exception as e:\n",
+    "                print(e, 'Download failure')\n",
+    "                             \n",
+    "        print(\"Total images downloaded:\", str(count - 1))        "
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}