comparison of input formats

cnn_channel order.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Populating the interactive namespace from numpy and matplotlib\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using TensorFlow backend.\n"
     ]
    }
   ],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2\n",
    "%pylab inline\n",
    "\n",
    "import glob\n",
    "from pathlib import Path\n",
    "\n",
    "import cv2\n",
    "from keras import applications\n",
    "from keras.applications.vgg16 import  decode_predictions\n",
    "from keras.preprocessing.image import array_to_img, img_to_array, load_img\n",
    "from skimage.transform import resize\n",
    "import seaborn as sns\n",
    "\n",
    "sns.set(style='ticks', context='poster')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "cnn_model = applications.VGG16(input_shape=(224, 224, 3))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "img_nr = 8\n",
    "img_fnames = glob.glob('/data/master_thesis/Flicker8k_Dataset/*.jpg')\n",
    "img_fnames = np.random.choice(img_fnames, img_nr, replace=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {