diff --git a/MTCNN for face detection/.ipynb_checkpoints/Face Cropping from Dataset-checkpoint.ipynb b/MTCNN for face detection/.ipynb_checkpoints/Face Cropping from Dataset-checkpoint.ipynb
index 7034f76..c6a8642 100644
--- a/MTCNN for face detection/.ipynb_checkpoints/Face Cropping from Dataset-checkpoint.ipynb	
+++ b/MTCNN for face detection/.ipynb_checkpoints/Face Cropping from Dataset-checkpoint.ipynb	
@@ -8,8 +8,8 @@
    },
    "outputs": [],
    "source": [
-    "%load_ext autoreload\n",
-    "%autoreload 2"
+    "# %load_ext autoreload\n",
+    "# %autoreload 2"
    ]
   },
   {
@@ -19,6 +19,18 @@
     "collapsed": true
    },
    "outputs": [],
+   "source": [
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
    "source": [
     "from src import detect_faces, show_bboxes\n",
     "from PIL import Image\n",
@@ -31,7 +43,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "dataset_path = '../Dataset/emotiw/'\n",
+    "\n",
+    "processed_dataset_path = '../Dataset/CroppedFaces/'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
    "metadata": {
     "collapsed": true
    },
@@ -43,12 +68,11 @@
     "#     'val' : transforms.Compose([transforms.ToPILImage()])\n",
     "# }\n",
     "\n",
-    "data_dir = '../Dataset/emotiw/'\n",
     "\n",
-    "# image_datasets = {x : datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x])\n",
+    "# image_datasets = {x : datasets.ImageFolder(os.path.join(dataset_path, x), data_transforms[x])\n",
     "#                     for x in ['train', 'val']}\n",
     "\n",
-    "image_datasets = {x : datasets.ImageFolder(os.path.join(data_dir, x))\n",
+    "image_datasets = {x : datasets.ImageFolder(os.path.join(dataset_path, x))\n",
     "                    for x in ['train', 'val']}\n",
     "\n",
     "# dataloaders = { x : torch.utils.data.DataLoader(image_datasets[x], batch_size = 1, shuffle=True, num_workers= 4)\n",
@@ -63,7 +87,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -72,7 +96,7 @@
        "['Negative', 'Neutral', 'Positive']"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -83,18 +107,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "train_data = image_datasets['train']"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "metadata": {
     "collapsed": true
    },
@@ -120,7 +133,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "metadata": {
     "collapsed": true
    },
@@ -141,215 +154,351 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "metadata": {
     "collapsed": true
    },
    "outputs": [],
    "source": [
-    "pos_train_count = 0\n",
-    "neg_train_count = 0\n",
-    "neut_train_count = 0"
+    "training_dataset = image_datasets['train']\n",
+    "validation_dataset = image_datasets['val']"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "neg_train = sorted(os.listdir(dataset_path + 'train/Negative/'))\n",
+    "neu_train = sorted(os.listdir(dataset_path + 'train/Neutral/'))\n",
+    "pos_train = sorted(os.listdir(dataset_path + 'train/Positive/'))\n",
+    "\n",
+    "neg_val = sorted(os.listdir(dataset_path + 'val/Negative/'))\n",
+    "neu_val = sorted(os.listdir(dataset_path + 'val/Neutral/'))\n",
+    "pos_val = sorted(os.listdir(dataset_path + 'val/Positive/'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "neg_train_filelist = [x.split('.')[0] for x in neg_train]\n",
+    "neu_train_filelist = [x.split('.')[0] for x in neu_train]\n",
+    "pos_train_filelist = [x.split('.')[0] for x in pos_train]\n",
+    "\n",
+    "neg_val_filelist = [x.split('.')[0] for x in neg_val]\n",
+    "neu_val_filelist = [x.split('.')[0] for x in neu_val]\n",
+    "pos_val_filelist = [x.split('.')[0] for x in pos_val]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['neg_1', 'neg_10', 'neg_100', 'neg_1000', 'neg_1001', 'neg_1002', 'neg_1003', 'neg_1004', 'neg_1005', 'neg_1006']\n",
+      "['neu_1', 'neu_10', 'neu_100', 'neu_1000', 'neu_1001', 'neu_1002', 'neu_1003', 'neu_1004', 'neu_1005', 'neu_1006']\n",
+      "['pos_1', 'pos_10', 'pos_100', 'pos_1000', 'pos_1001', 'pos_1002', 'pos_1003', 'pos_1004', 'pos_1005', 'pos_1006']\n",
+      "['neg_1', 'neg_10', 'neg_100', 'neg_1000', 'neg_1001', 'neg_1002', 'neg_1003', 'neg_1004', 'neg_1005', 'neg_1006']\n",
+      "['neu_1', 'neu_10', 'neu_100', 'neu_1000', 'neu_1001', 'neu_1002', 'neu_1003', 'neu_1004', 'neu_1005', 'neu_1006']\n",
+      "['pos_1', 'pos_10', 'pos_100', 'pos_1000', 'pos_1001', 'pos_1002', 'pos_1003', 'pos_1004', 'pos_1005', 'pos_1006']\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(neg_train_filelist[:10])\n",
+    "print(neu_train_filelist[:10])\n",
+    "print(pos_train_filelist[:10])\n",
+    "\n",
+    "print(neg_val_filelist[:10])\n",
+    "print(neu_val_filelist[:10])\n",
+    "print(pos_val_filelist[:10])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "train_filelist = neg_train_filelist + neu_train_filelist + pos_train_filelist\n",
+    "val_filelist = neg_val_filelist + neu_val_filelist + pos_val_filelist"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "0\n",
-      "100\n",
-      "200\n",
-      "300\n",
-      "400\n",
-      "500\n",
-      "600\n",
-      "700\n",
-      "800\n",
-      "900\n",
-      "1000\n",
-      "1100\n",
-      "1200\n",
-      "1300\n",
-      "1400\n",
-      "1500\n",
-      "1600\n",
-      "1700\n",
-      "1800\n",
-      "1900\n",
-      "2000\n",
-      "2100\n",
-      "2200\n",
-      "2300\n",
-      "2400\n",
-      "2500\n",
-      "2600\n",
-      "2700\n",
-      "2800\n",
-      "2900\n",
-      "3000\n",
-      "3100\n",
-      "3200\n",
-      "3300\n",
-      "3400\n",
-      "3500\n",
-      "3600\n",
-      "3700\n",
-      "3800\n",
-      "3900\n",
-      "4000\n",
-      "4100\n",
-      "4200\n",
-      "4300\n",
-      "4400\n",
-      "4500\n",
-      "4600\n",
-      "4700\n",
-      "4800\n",
-      "4900\n",
-      "5000\n",
-      "5100\n",
-      "5200\n",
-      "5300\n",
-      "5400\n",
-      "5500\n",
-      "5600\n",
-      "5700\n",
-      "5800\n",
-      "5900\n",
-      "6000\n",
-      "6100\n",
-      "6200\n",
-      "6300\n",
-      "6400\n",
-      "6500\n",
-      "6600\n",
-      "6700\n",
-      "6800\n",
-      "6900\n",
-      "7000\n",
-      "7100\n",
-      "7200\n",
-      "7300\n",
-      "7400\n",
-      "7500\n",
-      "7600\n",
-      "7700\n",
-      "7800\n",
-      "7900\n",
-      "8000\n",
-      "8100\n",
-      "8200\n",
-      "8300\n",
-      "8400\n",
-      "8500\n",
-      "8600\n",
-      "8700\n",
-      "8800\n",
-      "8900\n",
-      "9000\n",
-      "9100\n",
-      "9200\n",
-      "9300\n",
-      "9400\n",
-      "9500\n",
-      "9600\n"
+      "9815\n",
+      "4346\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(len(training_dataset))\n",
+    "print(len(validation_dataset))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "face_coordinates_directory = '../Dataset/FaceCoordinates/'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "# pos_train_count = 0\n",
+    "# neg_train_count = 0\n",
+    "# neut_train_count = 0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "# for i in range(len(image_datasets['train'])):\n",
+    "# # for i in range(1):\n",
+    "#     image, label = image_datasets['train'][i]\n",
+    "# #     bounding_boxes, landmarks = detect_faces(image)\n",
+    "#     face_list = []\n",
+    "#     if label == 0:\n",
+    "#         bbox_lm = np.load('../Dataset/FaceFeatures/train/Negative/neg_' + str(neg_train_count + 1) +'.npz')\n",
+    "#         bounding_boxes = bbox_lm['a']\n",
+    "#         landmarks = bbox_lm['b']\n",
+    "        \n",
+    "#         for j in range(len(bounding_boxes)):\n",
+    "#             bbox_coordinates = bounding_boxes[j]\n",
+    "#             img_face = image.crop((bbox_coordinates[0], bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "# #             if(len(face_list) != 0 and face_list[-1].shape[0] == int(bbox_coordinates[2] - bbox_coordinates[0])):\n",
+    "# #                 img_face = image.crop((bbox_coordinates[0] -1, bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "#             img_face = np.array(img_face)\n",
+    "            \n",
+    "#             if len(face_list) != 0:\n",
+    "#                 if img_face.shape[0] == face_list[-1].shape[0]:\n",
+    "#                     img_face = image.crop((bbox_coordinates[0] - 1, bbox_coordinates[1] - 1, bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "#                     img_face = np.array(img_face)\n",
+    "            \n",
+    "#             face_list.append(img_face)\n",
+    "#         face_list = np.asarray(face_list)\n",
+    "#         np.savez('../Dataset/SingleFaceFeatures/train/Negative/neg_' + str(neg_train_count + 1), a = face_list)\n",
+    "        \n",
+    "#         neg_train_count += 1\n",
+    "# #         print('neg' + str(neg_train_count+1))\n",
+    "        \n",
+    "#     elif label == 1:\n",
+    "#         bbox_lm = np.load('../Dataset/FaceFeatures/train/Neutral/neu_' + str(neut_train_count + 1) +'.npz')\n",
+    "#         bounding_boxes = bbox_lm['a']\n",
+    "#         landmarks = bbox_lm['b']\n",
+    "        \n",
+    "#         for j in range(len(bounding_boxes)):\n",
+    "#             bbox_coordinates = bounding_boxes[j]\n",
+    "#             img_face = image.crop((bbox_coordinates[0], bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "# #             if(len(face_list) != 0 and face_list[-1].shape[0] == int(bbox_coordinates[2] - bbox_coordinates[0])):\n",
+    "# #                 img_face = image.crop((bbox_coordinates[0] -1, bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "#             img_face = np.array(img_face)\n",
+    "            \n",
+    "#             if len(face_list) != 0:\n",
+    "#                 if img_face.shape[0] == face_list[-1].shape[0]:\n",
+    "#                     img_face = image.crop((bbox_coordinates[0] - 1, bbox_coordinates[1] - 1, bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "#                     img_face = np.array(img_face)\n",
+    "            \n",
+    "#             face_list.append(img_face)\n",
+    "#         face_list = np.asarray(face_list)\n",
+    "#         np.savez('../Dataset/SingleFaceFeatures/train/Neutral/neu_' + str(neut_train_count + 1), a = face_list)\n",
+    "        \n",
+    "#         neut_train_count += 1\n",
+    "\n",
+    "        \n",
+    "#     else:\n",
+    "#         bbox_lm = np.load('../Dataset/FaceFeatures/train/Positive/pos_' + str(pos_train_count + 1) +'.npz')\n",
+    "#         bounding_boxes = bbox_lm['a']\n",
+    "#         landmarks = bbox_lm['b']\n",
+    "        \n",
+    "#         for j in range(len(bounding_boxes)):\n",
+    "#             bbox_coordinates = bounding_boxes[j]\n",
+    "#             img_face = image.crop((bbox_coordinates[0], bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "# #             if (len(face_list) != 0 and face_list[-1].shape[0] == bbox_coordinates[2] - bbox_coordinates[0]):\n",
+    "# #                 img_face = image.crop((bbox_coordinates[0] -1, bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "#             img_face = np.array(img_face)\n",
+    "\n",
+    "#             if len(face_list) != 0:\n",
+    "#                 if img_face.shape[0] == face_list[-1].shape[0]:\n",
+    "#                     img_face = image.crop((bbox_coordinates[0] - 1, bbox_coordinates[1] - 1, bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "#                     img_face = np.array(img_face)\n",
+    "            \n",
+    "#             face_list.append(img_face)\n",
+    "#         face_list = np.asarray(face_list)\n",
+    "#         np.savez('../Dataset/SingleFaceFeatures/train/Positive/pos_' + str(pos_train_count + 1), a = face_list)\n",
+    "        \n",
+    "#         pos_train_count += 1\n",
+    "#     if i % 100 == 0:\n",
+    "#         print(i)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "IndentationError",
+     "evalue": "expected an indented block (<ipython-input-5-cfe01df4bb19>, line 47)",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;36m  File \u001b[1;32m\"<ipython-input-5-cfe01df4bb19>\"\u001b[1;36m, line \u001b[1;32m47\u001b[0m\n\u001b[1;33m    landmarks = bbox_lm['b']\u001b[0m\n\u001b[1;37m            ^\u001b[0m\n\u001b[1;31mIndentationError\u001b[0m\u001b[1;31m:\u001b[0m expected an indented block\n"
      ]
     }
    ],
    "source": [
-    "for i in range(len(image_datasets['train'])):\n",
-    "# for i in range(1):\n",
-    "    image, label = image_datasets['train'][i]\n",
+    "# for i in range(len(training_dataset)):\n",
+    "for i in range(10):\n",
+    "    image, label = training_dataset[i]\n",
     "#     bounding_boxes, landmarks = detect_faces(image)\n",
     "    face_list = []\n",
+    "    landmarks_new_coordinates = []\n",
     "    if label == 0:\n",
-    "        bbox_lm = np.load('../Dataset/FaceFeatures/train/Negative/neg_' + str(neg_train_count + 1) +'.npz')\n",
+    "        bbox_lm = np.load(face_coordinates_directory + 'train/Negative/' + train_filelist[i] +'.npz')\n",
     "        bounding_boxes = bbox_lm['a']\n",
+    "        if((bounding_boxes == 0)[0]):\n",
+    "            print(\"No bounding boxes for \" + train_filelist[i] + \". Adding empty file for the same\")\n",
+    "            np.savez(processed_dataset_path + 'train/Negative' + train_filelist[i], a = np.zeros(1), b = np.zeros(1))\n",
+    "            continue\n",
     "        landmarks = bbox_lm['b']\n",
     "        \n",
     "        for j in range(len(bounding_boxes)):\n",
     "            bbox_coordinates = bounding_boxes[j]\n",
+    "            landmark = landmarks[j]\n",
     "            img_face = image.crop((bbox_coordinates[0], bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
     "#             if(len(face_list) != 0 and face_list[-1].shape[0] == int(bbox_coordinates[2] - bbox_coordinates[0])):\n",
     "#                 img_face = image.crop((bbox_coordinates[0] -1, bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "            x = bbox_coordinates[0]\n",
+    "            y = bbox_coordinates[1]\n",
+    "            for k in range(5):\n",
+    "                landmark[k] -= x\n",
+    "                landmark[k+5] -= y\n",
     "            img_face = np.array(img_face)\n",
+    "            landmark = np.array(landmark)\n",
+    "            \n",
     "            \n",
     "            if len(face_list) != 0:\n",
     "                if img_face.shape[0] == face_list[-1].shape[0]:\n",
     "                    img_face = image.crop((bbox_coordinates[0] - 1, bbox_coordinates[1] - 1, bbox_coordinates[2], bbox_coordinates[3]))\n",
     "                    img_face = np.array(img_face)\n",
+    "                    landmark -=1\n",
     "            \n",
     "            face_list.append(img_face)\n",
+    "            landmarks_new_coordinates.append(landmark)\n",
     "        face_list = np.asarray(face_list)\n",
-    "        np.savez('../Dataset/SingleFaceFeatures/train/Negative/neg_' + str(neg_train_count + 1), a = face_list)\n",
-    "        \n",
-    "        neg_train_count += 1\n",
-    "#         print('neg' + str(neg_train_count+1))\n",
+    "        landmarks_new_coordinates = np.asarray(landmarks_new_coordinates)\n",
+    "        np.savez(processed_dataset_path + 'train/Negative/' + train_filelist[i], a = face_list, b = landmarks_new_coordinates)\n",
     "        \n",
     "    elif label == 1:\n",
-    "        bbox_lm = np.load('../Dataset/FaceFeatures/train/Neutral/neu_' + str(neut_train_count + 1) +'.npz')\n",
+    "        bbox_lm = np.load(face_coordinates_directory + 'train/Neutral/' + train_filelist[i] +'.npz')\n",
     "        bounding_boxes = bbox_lm['a']\n",
+    "        if((bounding_boxes == 0)[0]):\n",
+    "            print(\"No bounding boxes for \" + train_filelist[i] + \". Adding empty file for the same\")\n",
+    "            np.savez(processed_dataset_path + 'train/Neutral' + train_filelist[i], a = np.zeros(1), b = np.zeros(1))\n",
+    "            continue\n",
     "        landmarks = bbox_lm['b']\n",
     "        \n",
     "        for j in range(len(bounding_boxes)):\n",
     "            bbox_coordinates = bounding_boxes[j]\n",
+    "            landmark = landmarks[j]\n",
     "            img_face = image.crop((bbox_coordinates[0], bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
     "#             if(len(face_list) != 0 and face_list[-1].shape[0] == int(bbox_coordinates[2] - bbox_coordinates[0])):\n",
     "#                 img_face = image.crop((bbox_coordinates[0] -1, bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "            x = bbox_coordinates[0]\n",
+    "            y = bbox_coordinates[1]\n",
+    "            for k in range(5):\n",
+    "                landmark[k] -= x\n",
+    "                landmark[k+5] -= y\n",
     "            img_face = np.array(img_face)\n",
+    "            landmark = np.array(landmark)\n",
     "            \n",
     "            if len(face_list) != 0:\n",
     "                if img_face.shape[0] == face_list[-1].shape[0]:\n",
     "                    img_face = image.crop((bbox_coordinates[0] - 1, bbox_coordinates[1] - 1, bbox_coordinates[2], bbox_coordinates[3]))\n",
     "                    img_face = np.array(img_face)\n",
+    "                    landmark -= 1\n",
     "            \n",
     "            face_list.append(img_face)\n",
+    "            landmarks_new_coordinates.append(landmark)\n",
     "        face_list = np.asarray(face_list)\n",
-    "        np.savez('../Dataset/SingleFaceFeatures/train/Neutral/neu_' + str(neut_train_count + 1), a = face_list)\n",
-    "        \n",
-    "        neut_train_count += 1\n",
-    "\n",
+    "        landmarks_new_coordinates = np.asarray(landmarks_new_coordinates)\n",
+    "        np.savez(processed_dataset_path + 'train/Neutral/' + train_filelist[i], a = face_list, b = landmarks_new_coordinates)\n",
     "        \n",
     "    else:\n",
-    "        bbox_lm = np.load('../Dataset/FaceFeatures/train/Positive/pos_' + str(pos_train_count + 1) +'.npz')\n",
+    "        bbox_lm = np.load(face_coordinates_directory + 'train/Positive/' + train_filelist[i] +'.npz')\n",
     "        bounding_boxes = bbox_lm['a']\n",
+    "        if((bounding_boxes == 0)[0]):\n",
+    "            print(\"No bounding boxes for \" + train_filelist[i] + \". Adding empty file for the same\")\n",
+    "            np.savez(processed_dataset_path + 'train/Positive' + train_filelist[i], a = np.zeros(1), b = np.zeros(1))\n",
+    "            continue\n",
     "        landmarks = bbox_lm['b']\n",
     "        \n",
     "        for j in range(len(bounding_boxes)):\n",
     "            bbox_coordinates = bounding_boxes[j]\n",
+    "            landmark = landmarks[j]\n",
     "            img_face = image.crop((bbox_coordinates[0], bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
-    "#             if (len(face_list) != 0 and face_list[-1].shape[0] == bbox_coordinates[2] - bbox_coordinates[0]):\n",
+    "#             if(len(face_list) != 0 and face_list[-1].shape[0] == int(bbox_coordinates[2] - bbox_coordinates[0])):\n",
     "#                 img_face = image.crop((bbox_coordinates[0] -1, bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "            x = bbox_coordinates[0]\n",
+    "            y = bbox_coordinates[1]\n",
+    "            for k in range(5):\n",
+    "                landmark[k] -= x\n",
+    "                landmark[k+5] -= y\n",
     "            img_face = np.array(img_face)\n",
-    "\n",
+    "            landmark = np.array(landmark)\n",
+    "            \n",
     "            if len(face_list) != 0:\n",
     "                if img_face.shape[0] == face_list[-1].shape[0]:\n",
     "                    img_face = image.crop((bbox_coordinates[0] - 1, bbox_coordinates[1] - 1, bbox_coordinates[2], bbox_coordinates[3]))\n",
     "                    img_face = np.array(img_face)\n",
+    "                    landmark -= 1\n",
     "            \n",
     "            face_list.append(img_face)\n",
+    "            landmarks_new_coordinates.append(landmark)\n",
     "        face_list = np.asarray(face_list)\n",
-    "        np.savez('../Dataset/SingleFaceFeatures/train/Positive/pos_' + str(pos_train_count + 1), a = face_list)\n",
+    "        landmarks_new_coordinates = np.asarray(landmarks_new_coordinates)\n",
+    "        np.savez(processed_dataset_path + 'train/Positive/' + train_filelist[i], a = face_list, b = landmarks_new_coordinates)\n",
     "        \n",
-    "        pos_train_count += 1\n",
     "    if i % 100 == 0:\n",
     "        print(i)"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": []
-  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -382,7 +531,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "image = image_datasets['train'][155][0]\n",
@@ -392,7 +543,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "show_bboxes(image, bounding_boxes, landmarks)"
@@ -401,7 +554,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "print(len(bounding_boxes))\n",
@@ -411,7 +566,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "face_list = []\n",
@@ -432,7 +589,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "face_list.shape"
@@ -453,7 +612,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "img1"
@@ -517,7 +678,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "image"
@@ -547,7 +710,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "a"
@@ -567,7 +732,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "print(arr[0].shape)\n",
@@ -582,6 +749,122 @@
    },
    "outputs": [],
    "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "arr = np.zeros(0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "arr.size"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "bbox_lm = np.load('../Dataset/FaceFeatures/val/Negative/neg_' + str(3) +'.npz')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "bb = bbox_lm['a']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([], shape=(0, 5), dtype=float64)"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "bb"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "testing = np.load('../Dataset/SingleFaceFeatures/train/Negative/neg_' + str(2) + '.npz')['a']\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([], dtype=float64)"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "detect_faces(image_datasets['train'][1])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAoAAAAFQCAIAAACgeVjGAAEAAElEQVR4nOz9y5blOK4mCH8AKe1t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\nQmCC\n",
+      "text/plain": [
+       "<PIL.Image.Image image mode=RGB size=640x336 at 0x1EC9C80EAC8>"
+      ]
+     },
+     "execution_count": 37,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "image_datasets['train'][1][0]"
+   ]
   }
  ],
  "metadata": {
diff --git a/MTCNN for face detection/.ipynb_checkpoints/Face Extraction -checkpoint.ipynb b/MTCNN for face detection/.ipynb_checkpoints/Face Extraction -checkpoint.ipynb
index 8bb0f85..5c56777 100644
--- a/MTCNN for face detection/.ipynb_checkpoints/Face Extraction -checkpoint.ipynb	
+++ b/MTCNN for face detection/.ipynb_checkpoints/Face Extraction -checkpoint.ipynb	
@@ -8,8 +8,8 @@
    },
    "outputs": [],
    "source": [
-    "%load_ext autoreload\n",
-    "%autoreload 2"
+    "# %load_ext autoreload\n",
+    "# %autoreload 2"
    ]
   },
   {
@@ -19,6 +19,29 @@
     "collapsed": true
    },
    "outputs": [],
+   "source": [
+    "#needs to be updated for exception handling from other pc"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
    "source": [
     "from src import detect_faces, show_bboxes\n",
     "from PIL import Image\n",
@@ -31,7 +54,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "dataset_path = '../Dataset/emotiw/'\n",
+    "\n",
+    "processed_dataset_path = '../Dataset/FaceCoordinates/'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
    "metadata": {
     "collapsed": true
    },
@@ -43,12 +79,11 @@
     "#     'val' : transforms.Compose([transforms.ToPILImage()])\n",
     "# }\n",
     "\n",
-    "data_dir = '../Dataset/emotiw/'\n",
     "\n",
-    "# image_datasets = {x : datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x])\n",
+    "# image_datasets = {x : datasets.ImageFolder(os.path.join(dataset_path, x), data_transforms[x])\n",
     "#                     for x in ['train', 'val']}\n",
     "\n",
-    "image_datasets = {x : datasets.ImageFolder(os.path.join(data_dir, x))\n",
+    "image_datasets = {x : datasets.ImageFolder(os.path.join(dataset_path, x))\n",
     "                    for x in ['train', 'val']}\n",
     "\n",
     "# dataloaders = { x : torch.utils.data.DataLoader(image_datasets[x], batch_size = 1, shuffle=True, num_workers= 4)\n",
@@ -63,7 +98,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -72,7 +107,7 @@
        "['Negative', 'Neutral', 'Positive']"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -83,18 +118,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "train_data = image_datasets['train']"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "metadata": {
     "collapsed": true
    },
@@ -120,7 +144,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "metadata": {
     "collapsed": true
    },
@@ -141,162 +165,272 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 10,
    "metadata": {
     "collapsed": true
    },
    "outputs": [],
    "source": [
-    "pos_train_count = 0\n",
-    "neg_train_count = 0\n",
-    "neut_train_count = 0"
+    "training_dataset = image_datasets['train']\n",
+    "validation_dataset = image_datasets['val']"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 11,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "neg_train = sorted(os.listdir(dataset_path + 'train/Negative/'))\n",
+    "neu_train = sorted(os.listdir(dataset_path + 'train/Neutral/'))\n",
+    "pos_train = sorted(os.listdir(dataset_path + 'train/Positive/'))\n",
+    "\n",
+    "neg_val = sorted(os.listdir(dataset_path + 'val/Negative/'))\n",
+    "neu_val = sorted(os.listdir(dataset_path + 'val/Neutral/'))\n",
+    "pos_val = sorted(os.listdir(dataset_path + 'val/Positive/'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "neg_train_filelist = [x.split('.')[0] for x in neg_train]\n",
+    "neu_train_filelist = [x.split('.')[0] for x in neu_train]\n",
+    "pos_train_filelist = [x.split('.')[0] for x in pos_train]\n",
+    "\n",
+    "neg_val_filelist = [x.split('.')[0] for x in neg_val]\n",
+    "neu_val_filelist = [x.split('.')[0] for x in neu_val]\n",
+    "pos_val_filelist = [x.split('.')[0] for x in pos_val]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['neg_1', 'neg_10', 'neg_100', 'neg_1000', 'neg_1001', 'neg_1002', 'neg_1003', 'neg_1004', 'neg_1005', 'neg_1006']\n",
+      "['neu_1', 'neu_10', 'neu_100', 'neu_1000', 'neu_1001', 'neu_1002', 'neu_1003', 'neu_1004', 'neu_1005', 'neu_1006']\n",
+      "['pos_1', 'pos_10', 'pos_100', 'pos_1000', 'pos_1001', 'pos_1002', 'pos_1003', 'pos_1004', 'pos_1005', 'pos_1006']\n",
+      "['neg_1', 'neg_10', 'neg_100', 'neg_1000', 'neg_1001', 'neg_1002', 'neg_1003', 'neg_1004', 'neg_1005', 'neg_1006']\n",
+      "['neu_1', 'neu_10', 'neu_100', 'neu_1000', 'neu_1001', 'neu_1002', 'neu_1003', 'neu_1004', 'neu_1005', 'neu_1006']\n",
+      "['pos_1', 'pos_10', 'pos_100', 'pos_1000', 'pos_1001', 'pos_1002', 'pos_1003', 'pos_1004', 'pos_1005', 'pos_1006']\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(neg_train_filelist[:10])\n",
+    "print(neu_train_filelist[:10])\n",
+    "print(pos_train_filelist[:10])\n",
+    "\n",
+    "print(neg_val_filelist[:10])\n",
+    "print(neu_val_filelist[:10])\n",
+    "print(pos_val_filelist[:10])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "train_filelist = neg_train_filelist + neu_train_filelist + pos_train_filelist\n",
+    "val_filelist = neg_val_filelist + neu_val_filelist + pos_val_filelist"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "# pos_train_count = 0\n",
+    "# neg_train_count = 0\n",
+    "# neut_train_count = 0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
-     "name": "stderr",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
-      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\first_stage.py:32: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.\n",
-      "  img = Variable(torch.FloatTensor(_preprocess(img)), volatile=True)\n",
-      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\get_nets.py:70: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.\n",
-      "  a = F.softmax(a)\n",
-      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\detector.py:79: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.\n",
-      "  img_boxes = Variable(torch.FloatTensor(img_boxes), volatile=True)\n",
-      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\get_nets.py:115: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.\n",
-      "  a = F.softmax(a)\n",
-      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\detector.py:100: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.\n",
-      "  img_boxes = Variable(torch.FloatTensor(img_boxes), volatile=True)\n",
-      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\get_nets.py:168: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.\n",
-      "  a = F.softmax(a)\n"
+      "9815\n",
+      "4346\n"
      ]
-    },
+    }
+   ],
+   "source": [
+    "print(len(training_dataset))\n",
+    "print(len(validation_dataset))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "#No faces detected for pos_928. Empty file stored"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "for i in range(len(training_dataset)):\n",
+    "# for i in range(5):\n",
+    "    image, label = training_dataset[i]\n",
+    "    print(train_filelist[i])\n",
+    "    try:\n",
+    "        bounding_boxes, landmarks = detect_faces(image)\n",
+    "        if bounding_boxes.size == 0:\n",
+    "            print('MTCNN model handling empty face condition at ' + train_filelist[i])\n",
+    "        if label == 0:\n",
+    "            np.savez(processed_dataset_path + 'train/Negative/' + train_filelist[i] , a=bounding_boxes, b=landmarks)\n",
+    "#             neg_train_count = neg_train_count + 1\n",
+    "        elif label == 1:\n",
+    "            np.savez(processed_dataset_path + 'train/Neutral/' + train_filelist[i] , a=bounding_boxes, b=landmarks)\n",
+    "#             neut_train_count += 1\n",
+    "        else:\n",
+    "            np.savez(processed_dataset_path + 'train/Positive/' + train_filelist[i] , a=bounding_boxes, b=landmarks)\n",
+    "#             pos_train_count += 1\n",
+    "#         if i % 100 == 0:\n",
+    "#             print(i)\n",
+    "            \n",
+    "            \n",
+    "    except ValueError:\n",
+    "        print('No faces detected for ' + train_filelist[i] + \". Also MTCNN failed.\")\n",
+    "        if label == 0:\n",
+    "#             print('File ' + train_filelist[i] + \" empty\")\n",
+    "            np.savez(processed_dataset_path + 'train/Negative/' + train_filelist[i] , a=np.zeros(1), b=np.zeros(1))\n",
+    "#             neg_train_count += 1\n",
+    "        elif label == 1:\n",
+    "#             print('File ' + train_filelist[i] + \" empty\")\n",
+    "            np.savez(processed_dataset_path + 'train/Neutral/' + train_filelist[i] , a=np.zeros(1), b=np.zeros(1))\n",
+    "#             neut_train_count += 1\n",
+    "        else:\n",
+    "#             print('File ' + train_filelist[i] + \" empty\")\n",
+    "            np.savez(processed_dataset_path + 'train/Positive/' + train_filelist[i] , a=np.zeros(1), b=np.zeros(1))\n",
+    "#             pos_train_count += 1\n",
+    "        continue"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "0\n",
-      "100\n",
-      "200\n",
-      "300\n",
-      "400\n",
-      "500\n",
-      "600\n",
-      "700\n",
-      "800\n",
-      "900\n",
-      "1000\n",
-      "1100\n",
-      "1200\n",
-      "1300\n",
-      "1400\n",
-      "1500\n",
-      "1600\n",
-      "1700\n",
-      "1800\n",
-      "1900\n",
-      "2000\n",
-      "2100\n",
-      "2200\n",
-      "2300\n",
-      "2400\n",
-      "2500\n",
-      "2600\n",
-      "2700\n",
-      "2800\n",
-      "2900\n",
-      "3000\n",
-      "3100\n",
-      "3200\n",
-      "3300\n",
-      "3400\n",
-      "3500\n",
-      "3600\n",
-      "3700\n",
-      "3800\n",
-      "3900\n",
-      "4000\n",
-      "4100\n",
-      "4200\n",
-      "4300\n",
-      "4400\n",
-      "4500\n",
-      "4600\n",
-      "4700\n",
-      "4800\n",
-      "4900\n",
-      "5000\n",
-      "5100\n",
-      "5200\n",
-      "5300\n",
-      "5400\n",
-      "5500\n",
-      "5600\n",
-      "5700\n",
-      "5800\n",
-      "5900\n",
-      "6000\n",
-      "6100\n",
-      "6200\n",
-      "6300\n",
-      "6400\n",
-      "6500\n",
-      "6600\n",
-      "6700\n",
-      "6800\n",
-      "6900\n",
-      "7000\n",
-      "7100\n",
-      "7200\n",
-      "7300\n",
-      "7400\n",
-      "7500\n",
-      "7600\n",
-      "7700\n",
-      "7800\n",
-      "7900\n",
-      "8000\n",
-      "8100\n",
-      "8200\n",
-      "8300\n",
-      "8400\n",
-      "8500\n",
-      "8600\n",
-      "8700\n",
-      "8800\n",
-      "8900\n",
-      "9000\n",
-      "9100\n",
-      "9200\n",
-      "9300\n",
-      "9400\n",
-      "9500\n",
-      "9600\n",
-      "9700\n",
-      "9800\n"
+      "neg_1\n",
+      "neg_10\n",
+      "neg_100\n",
+      "MTCNN model handling empty face condition at neg_100\n",
+      "neg_1000\n",
+      "neg_1001\n",
+      "neg_1002\n",
+      "neg_1003\n",
+      "neg_1004\n",
+      "neg_1005\n",
+      "neg_1006\n",
+      "neg_1007\n",
+      "neg_1008\n",
+      "neg_1009\n",
+      "MTCNN model handling empty face condition at neg_1009\n",
+      "neg_101\n",
+      "neg_1010\n",
+      "neg_1011\n",
+      "neg_1012\n",
+      "neg_1013\n",
+      "neg_1014\n",
+      "MTCNN model handling empty face condition at neg_1014\n",
+      "neg_1015\n",
+      "neg_1016\n",
+      "neg_1017\n",
+      "neg_1018\n",
+      "neg_1019\n",
+      "neg_102\n",
+      "neg_1020\n",
+      "neg_1021\n",
+      "neg_1022\n",
+      "neg_1023\n",
+      "neg_1024\n",
+      "neg_1025\n",
+      "neg_1026\n",
+      "neg_1027\n",
+      "neg_1028\n",
+      "neg_1029\n",
+      "neg_103\n",
+      "neg_1030\n",
+      "neg_1031\n",
+      "neg_1032\n",
+      "neg_1033\n",
+      "neg_1034\n"
      ]
     }
    ],
    "source": [
-    "for i in range(len(image_datasets['train'])):\n",
-    "# for i in range(1):\n",
-    "    image, label = image_datasets['train'][i]\n",
-    "    bounding_boxes, landmarks = detect_faces(image)\n",
-    "    if label == 0:\n",
-    "        np.savez('../Dataset/FaceFeatures/train/Negative/neg_' + str(neg_train_count + 1), a=bounding_boxes, b=landmarks)\n",
-    "        neg_train_count = neg_train_count + 1\n",
-    "    elif label == 1:\n",
-    "        np.savez('../Dataset/FaceFeatures/train/Neutral/neu_' + str(neut_train_count + 1), a=bounding_boxes, b=landmarks)\n",
-    "        neut_train_count += 1\n",
-    "    else:\n",
-    "        np.savez('../Dataset/FaceFeatures/train/Positive/pos_' + str(pos_train_count + 1), a=bounding_boxes, b=landmarks)\n",
-    "        pos_train_count += 1\n",
-    "    if i % 100 == 0:\n",
-    "        print(i)"
+    "for i in range(len(validation_dataset)):\n",
+    "# for i in range(5):\n",
+    "    image, label = validation_dataset[i]\n",
+    "    print(val_filelist[i])\n",
+    "    try:\n",
+    "        bounding_boxes, landmarks = detect_faces(image)\n",
+    "        if bounding_boxes.size == 0:\n",
+    "            print('MTCNN model handling empty face condition at ' + val_filelist[i])\n",
+    "        if label == 0:\n",
+    "            np.savez(processed_dataset_path + 'val/Negative/' + val_filelist[i] , a=bounding_boxes, b=landmarks)\n",
+    "#             neg_val_count = neg_val_count + 1\n",
+    "        elif label == 1:\n",
+    "            np.savez(processed_dataset_path + 'val/Neutral/' + val_filelist[i] , a=bounding_boxes, b=landmarks)\n",
+    "#             neut_val_count += 1\n",
+    "        else:\n",
+    "            np.savez(processed_dataset_path + 'val/Positive/' + val_filelist[i] , a=bounding_boxes, b=landmarks)\n",
+    "#             pos_val_count += 1\n",
+    "#         if i % 100 == 0:\n",
+    "#             print(i)\n",
+    "            \n",
+    "            \n",
+    "    except ValueError:\n",
+    "        print('No faces detected for ' + val_filelist[i] + \". Also MTCNN failed.\")\n",
+    "        if label == 0:\n",
+    "#             print('File ' + val_filelist[i] + \" empty\")\n",
+    "            np.savez(processed_dataset_path + 'val/Negative/' + val_filelist[i] , a=np.zeros(1), b=np.zeros(1))\n",
+    "#             neg_val_count += 1\n",
+    "        elif label == 1:\n",
+    "#             print('File ' + val_filelist[i] + \" empty\")\n",
+    "            np.savez(processed_dataset_path + 'val/Neutral/' + val_filelist[i] , a=np.zeros(1), b=np.zeros(1))\n",
+    "#             neut_val_count += 1\n",
+    "        else:\n",
+    "#             print('File ' + val_filelist[i] + \" empty\")\n",
+    "            np.savez(processed_dataset_path + 'val/Positive/' + val_filelist[i] , a=np.zeros(1), b=np.zeros(1))\n",
+    "#             pos_val_count += 1\n",
+    "        continue"
    ]
   },
   {
@@ -334,6 +468,111 @@
     "bounding_boxes, landmarks = detect_faces(image_datasets['train'][7][0])"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "for i in range(1000):\n",
+    "        bbox_ld = np.load('../Dataset/FaceFeatures/train/Negative/neg_' + str(i + 1) + '.npz')\n",
+    "        bbox = bbox_ld['a']\n",
+    "#         landmarks = bbox_ld['b']\n",
+    "        if bbox.size == 0:\n",
+    "            print(bbox.shape, i + 1)\n",
+    "#             print(landmarks.shape)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "bboxes, landmarks = detect_faces(image_datasets['train'][457][0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "image_datasets['train'][1][0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "show_bboxes(image_datasets['train'][457][0], bboxes, landmarks)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "dataloaders['train'][0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "sorted(os.listdir('../Dataset/emotiw/train/Negative/'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "a = np.zeros(1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "(a == 0)[0]"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
diff --git a/MTCNN for face detection/LocalCNN.ipynb b/MTCNN for face detection/.ipynb_checkpoints/LocalCNN-checkpoint.ipynb
similarity index 75%
rename from MTCNN for face detection/LocalCNN.ipynb
rename to MTCNN for face detection/.ipynb_checkpoints/LocalCNN-checkpoint.ipynb
index 1bd70ce..bd85a7b 100644
--- a/MTCNN for face detection/LocalCNN.ipynb	
+++ b/MTCNN for face detection/.ipynb_checkpoints/LocalCNN-checkpoint.ipynb	
@@ -3,7 +3,9 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "%load_ext autoreload\n",
@@ -13,7 +15,9 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "from src import detect_faces, show_bboxes\n",
@@ -28,7 +32,9 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "# data_transforms = {\n",
@@ -78,16 +84,20 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
-    "train_data = image_datasets['train']"
+    "val_data = image_datasets['val']"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 6,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "# type(train_data[0:5])\n",
@@ -111,7 +121,9 @@
   {
    "cell_type": "code",
    "execution_count": 7,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "# neg_images = 2758\n",
@@ -130,7 +142,9 @@
   {
    "cell_type": "code",
    "execution_count": 8,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "pos_train_count = 0\n",
@@ -141,26 +155,35 @@
   {
    "cell_type": "code",
    "execution_count": 9,
+   "metadata": {
+    "collapsed": true,
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "# for i in range(len(image_datasets['val'])):\n",
+    "# # for i in range(1):\n",
+    "    \n",
+    "#     image, label = image_datasets['val'][i]\n",
+    "#     bounding_boxes, landmarks = detect_faces(image)\n",
+    "#     if label == 0:\n",
+    "#         np.savez('../Dataset/FaceFeatures/val/Negative/neg_' + str(neg_train_count + 1), a=bounding_boxes, b=landmarks)\n",
+    "#         neg_train_count = neg_train_count + 1\n",
+    "#     elif label == 1:\n",
+    "#         np.savez('../Dataset/FaceFeatures/val/Neutral/neu_' + str(neut_train_count + 1), a=bounding_boxes, b=landmarks)\n",
+    "#         neut_train_count += 1\n",
+    "#     else:\n",
+    "#         np.savez('../Dataset/FaceFeatures/val/Positive/pos_' + str(pos_train_count + 1), a=bounding_boxes, b=landmarks)\n",
+    "#         pos_train_count += 1\n",
+    "#     if i % 100 == 0:\n",
+    "#         print(i)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\first_stage.py:32: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.\n",
-      "  img = Variable(torch.FloatTensor(_preprocess(img)), volatile=True)\n",
-      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\get_nets.py:70: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.\n",
-      "  a = F.softmax(a)\n",
-      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\detector.py:79: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.\n",
-      "  img_boxes = Variable(torch.FloatTensor(img_boxes), volatile=True)\n",
-      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\get_nets.py:115: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.\n",
-      "  a = F.softmax(a)\n",
-      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\detector.py:100: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.\n",
-      "  img_boxes = Variable(torch.FloatTensor(img_boxes), volatile=True)\n",
-      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\get_nets.py:168: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.\n",
-      "  a = F.softmax(a)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
@@ -190,7 +213,31 @@
       "2200\n",
       "2300\n",
       "2400\n",
-      "2500\n",
+      "2500\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\first_stage.py:32: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.\n",
+      "  img = Variable(torch.FloatTensor(_preprocess(img)), volatile=True)\n",
+      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\get_nets.py:70: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.\n",
+      "  a = F.softmax(a)\n",
+      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\detector.py:79: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.\n",
+      "  img_boxes = Variable(torch.FloatTensor(img_boxes), volatile=True)\n",
+      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\get_nets.py:115: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.\n",
+      "  a = F.softmax(a)\n",
+      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\detector.py:100: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.\n",
+      "  img_boxes = Variable(torch.FloatTensor(img_boxes), volatile=True)\n",
+      "C:\\Users\\biplab\\Desktop\\EmotiW\\MTCNN for face detection\\src\\get_nets.py:168: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.\n",
+      "  a = F.softmax(a)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
       "2600\n",
       "2700\n",
       "2800\n",
@@ -201,6 +248,7 @@
       "3300\n",
       "3400\n",
       "3500\n",
+      "No faces detected for pos_928. Empty file stored\n",
       "3600\n",
       "3700\n",
       "3800\n",
@@ -208,79 +256,25 @@
       "4000\n",
       "4100\n",
       "4200\n",
-      "4300\n",
-      "4400\n",
-      "4500\n",
-      "4600\n",
-      "4700\n",
-      "4800\n",
-      "4900\n",
-      "5000\n",
-      "5100\n",
-      "5200\n",
-      "5300\n",
-      "5400\n",
-      "5500\n",
-      "5600\n",
-      "5700\n",
-      "5800\n",
-      "5900\n",
-      "6000\n",
-      "6100\n",
-      "6200\n",
-      "6300\n",
-      "6400\n",
-      "6500\n",
-      "6600\n",
-      "6700\n",
-      "6800\n",
-      "6900\n",
-      "7000\n",
-      "7100\n",
-      "7200\n",
-      "7300\n",
-      "7400\n",
-      "7500\n",
-      "7600\n",
-      "7700\n",
-      "7800\n",
-      "7900\n",
-      "8000\n",
-      "8100\n",
-      "8200\n",
-      "8300\n",
-      "8400\n",
-      "8500\n",
-      "8600\n",
-      "8700\n",
-      "8800\n",
-      "8900\n",
-      "9000\n",
-      "9100\n",
-      "9200\n",
-      "9300\n",
-      "9400\n",
-      "9500\n",
-      "9600\n",
-      "9700\n",
-      "9800\n"
+      "4300\n"
      ]
     }
    ],
    "source": [
-    "for i in range(len(image_datasets['train'])):\n",
+    "for i in range(len(image_datasets['val'])):\n",
     "# for i in range(1):\n",
-    "    image, label = image_datasets['train'][i]\n",
-    "    bounding_boxes, landmarks = detect_faces(image)\n",
-    "    if label == 0:\n",
-    "        np.savez('../Dataset/FaceFeatures/train/Negative/neg_' + str(neg_train_count + 1), a=bounding_boxes, b=landmarks)\n",
-    "        neg_train_count = neg_train_count + 1\n",
-    "    elif label == 1:\n",
-    "        np.savez('../Dataset/FaceFeatures/train/Neutral/neu_' + str(neut_train_count + 1), a=bounding_boxes, b=landmarks)\n",
-    "        neut_train_count += 1\n",
-    "    else:\n",
-    "        np.savez('../Dataset/FaceFeatures/train/Positive/pos_' + str(pos_train_count + 1), a=bounding_boxes, b=landmarks)\n",
-    "        pos_train_count += 1\n",
+    "    \n",
+    "    image, label = image_datasets['val'][i]\n",
+    "    if label == 2:\n",
+    "        try:\n",
+    "            bounding_boxes, landmarks = detect_faces(image)\n",
+    "            np.savez('../Dataset/FaceFeatures/val/Positive/pos_' + str(pos_train_count + 1), a=bounding_boxes, b=landmarks)\n",
+    "            pos_train_count +=1\n",
+    "        except ValueError:\n",
+    "            print('No faces detected for pos_' + str(pos_train_count + 1) + \". Empty file stored\")\n",
+    "            np.savez('../Dataset/FaceFeatures/val/Positive/pos_' + str(pos_train_count + 1), a=np.empty(1), b=np.empty(1))\n",
+    "            pos_train_count +=1\n",
+    "            continue\n",
     "    if i % 100 == 0:\n",
     "        print(i)"
    ]
@@ -288,7 +282,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "# img = Image.open('images/office1.jpg')\n",
@@ -299,7 +295,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "# type(bounding_boxes)"
@@ -308,7 +306,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "bounding_boxes, landmarks = detect_faces(image_datasets['train'][7][0])"
@@ -317,7 +317,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": []
   }
@@ -338,7 +340,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.5"
+   "version": "3.5.4"
   }
  },
  "nbformat": 4,
diff --git a/MTCNN for face detection/Face Cropping from Dataset.ipynb b/MTCNN for face detection/Face Cropping from Dataset.ipynb
index 7034f76..c6a8642 100644
--- a/MTCNN for face detection/Face Cropping from Dataset.ipynb	
+++ b/MTCNN for face detection/Face Cropping from Dataset.ipynb	
@@ -8,8 +8,8 @@
    },
    "outputs": [],
    "source": [
-    "%load_ext autoreload\n",
-    "%autoreload 2"
+    "# %load_ext autoreload\n",
+    "# %autoreload 2"
    ]
   },
   {
@@ -19,6 +19,18 @@
     "collapsed": true
    },
    "outputs": [],
+   "source": [
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
    "source": [
     "from src import detect_faces, show_bboxes\n",
     "from PIL import Image\n",
@@ -31,7 +43,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "dataset_path = '../Dataset/emotiw/'\n",
+    "\n",
+    "processed_dataset_path = '../Dataset/CroppedFaces/'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
    "metadata": {
     "collapsed": true
    },
@@ -43,12 +68,11 @@
     "#     'val' : transforms.Compose([transforms.ToPILImage()])\n",
     "# }\n",
     "\n",
-    "data_dir = '../Dataset/emotiw/'\n",
     "\n",
-    "# image_datasets = {x : datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x])\n",
+    "# image_datasets = {x : datasets.ImageFolder(os.path.join(dataset_path, x), data_transforms[x])\n",
     "#                     for x in ['train', 'val']}\n",
     "\n",
-    "image_datasets = {x : datasets.ImageFolder(os.path.join(data_dir, x))\n",
+    "image_datasets = {x : datasets.ImageFolder(os.path.join(dataset_path, x))\n",
     "                    for x in ['train', 'val']}\n",
     "\n",
     "# dataloaders = { x : torch.utils.data.DataLoader(image_datasets[x], batch_size = 1, shuffle=True, num_workers= 4)\n",
@@ -63,7 +87,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -72,7 +96,7 @@
        "['Negative', 'Neutral', 'Positive']"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -83,18 +107,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "train_data = image_datasets['train']"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "metadata": {
     "collapsed": true
    },
@@ -120,7 +133,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "metadata": {
     "collapsed": true
    },
@@ -141,215 +154,351 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "metadata": {
     "collapsed": true
    },
    "outputs": [],
    "source": [
-    "pos_train_count = 0\n",
-    "neg_train_count = 0\n",
-    "neut_train_count = 0"
+    "training_dataset = image_datasets['train']\n",
+    "validation_dataset = image_datasets['val']"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "neg_train = sorted(os.listdir(dataset_path + 'train/Negative/'))\n",
+    "neu_train = sorted(os.listdir(dataset_path + 'train/Neutral/'))\n",
+    "pos_train = sorted(os.listdir(dataset_path + 'train/Positive/'))\n",
+    "\n",
+    "neg_val = sorted(os.listdir(dataset_path + 'val/Negative/'))\n",
+    "neu_val = sorted(os.listdir(dataset_path + 'val/Neutral/'))\n",
+    "pos_val = sorted(os.listdir(dataset_path + 'val/Positive/'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "neg_train_filelist = [x.split('.')[0] for x in neg_train]\n",
+    "neu_train_filelist = [x.split('.')[0] for x in neu_train]\n",
+    "pos_train_filelist = [x.split('.')[0] for x in pos_train]\n",
+    "\n",
+    "neg_val_filelist = [x.split('.')[0] for x in neg_val]\n",
+    "neu_val_filelist = [x.split('.')[0] for x in neu_val]\n",
+    "pos_val_filelist = [x.split('.')[0] for x in pos_val]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['neg_1', 'neg_10', 'neg_100', 'neg_1000', 'neg_1001', 'neg_1002', 'neg_1003', 'neg_1004', 'neg_1005', 'neg_1006']\n",
+      "['neu_1', 'neu_10', 'neu_100', 'neu_1000', 'neu_1001', 'neu_1002', 'neu_1003', 'neu_1004', 'neu_1005', 'neu_1006']\n",
+      "['pos_1', 'pos_10', 'pos_100', 'pos_1000', 'pos_1001', 'pos_1002', 'pos_1003', 'pos_1004', 'pos_1005', 'pos_1006']\n",
+      "['neg_1', 'neg_10', 'neg_100', 'neg_1000', 'neg_1001', 'neg_1002', 'neg_1003', 'neg_1004', 'neg_1005', 'neg_1006']\n",
+      "['neu_1', 'neu_10', 'neu_100', 'neu_1000', 'neu_1001', 'neu_1002', 'neu_1003', 'neu_1004', 'neu_1005', 'neu_1006']\n",
+      "['pos_1', 'pos_10', 'pos_100', 'pos_1000', 'pos_1001', 'pos_1002', 'pos_1003', 'pos_1004', 'pos_1005', 'pos_1006']\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(neg_train_filelist[:10])\n",
+    "print(neu_train_filelist[:10])\n",
+    "print(pos_train_filelist[:10])\n",
+    "\n",
+    "print(neg_val_filelist[:10])\n",
+    "print(neu_val_filelist[:10])\n",
+    "print(pos_val_filelist[:10])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "train_filelist = neg_train_filelist + neu_train_filelist + pos_train_filelist\n",
+    "val_filelist = neg_val_filelist + neu_val_filelist + pos_val_filelist"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "0\n",
-      "100\n",
-      "200\n",
-      "300\n",
-      "400\n",
-      "500\n",
-      "600\n",
-      "700\n",
-      "800\n",
-      "900\n",
-      "1000\n",
-      "1100\n",
-      "1200\n",
-      "1300\n",
-      "1400\n",
-      "1500\n",
-      "1600\n",
-      "1700\n",
-      "1800\n",
-      "1900\n",
-      "2000\n",
-      "2100\n",
-      "2200\n",
-      "2300\n",
-      "2400\n",
-      "2500\n",
-      "2600\n",
-      "2700\n",
-      "2800\n",
-      "2900\n",
-      "3000\n",
-      "3100\n",
-      "3200\n",
-      "3300\n",
-      "3400\n",
-      "3500\n",
-      "3600\n",
-      "3700\n",
-      "3800\n",
-      "3900\n",
-      "4000\n",
-      "4100\n",
-      "4200\n",
-      "4300\n",
-      "4400\n",
-      "4500\n",
-      "4600\n",
-      "4700\n",
-      "4800\n",
-      "4900\n",
-      "5000\n",
-      "5100\n",
-      "5200\n",
-      "5300\n",
-      "5400\n",
-      "5500\n",
-      "5600\n",
-      "5700\n",
-      "5800\n",
-      "5900\n",
-      "6000\n",
-      "6100\n",
-      "6200\n",
-      "6300\n",
-      "6400\n",
-      "6500\n",
-      "6600\n",
-      "6700\n",
-      "6800\n",
-      "6900\n",
-      "7000\n",
-      "7100\n",
-      "7200\n",
-      "7300\n",
-      "7400\n",
-      "7500\n",
-      "7600\n",
-      "7700\n",
-      "7800\n",
-      "7900\n",
-      "8000\n",
-      "8100\n",
-      "8200\n",
-      "8300\n",
-      "8400\n",
-      "8500\n",
-      "8600\n",
-      "8700\n",
-      "8800\n",
-      "8900\n",
-      "9000\n",
-      "9100\n",
-      "9200\n",
-      "9300\n",
-      "9400\n",
-      "9500\n",
-      "9600\n"
+      "9815\n",
+      "4346\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(len(training_dataset))\n",
+    "print(len(validation_dataset))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "face_coordinates_directory = '../Dataset/FaceCoordinates/'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "# pos_train_count = 0\n",
+    "# neg_train_count = 0\n",
+    "# neut_train_count = 0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "# for i in range(len(image_datasets['train'])):\n",
+    "# # for i in range(1):\n",
+    "#     image, label = image_datasets['train'][i]\n",
+    "# #     bounding_boxes, landmarks = detect_faces(image)\n",
+    "#     face_list = []\n",
+    "#     if label == 0:\n",
+    "#         bbox_lm = np.load('../Dataset/FaceFeatures/train/Negative/neg_' + str(neg_train_count + 1) +'.npz')\n",
+    "#         bounding_boxes = bbox_lm['a']\n",
+    "#         landmarks = bbox_lm['b']\n",
+    "        \n",
+    "#         for j in range(len(bounding_boxes)):\n",
+    "#             bbox_coordinates = bounding_boxes[j]\n",
+    "#             img_face = image.crop((bbox_coordinates[0], bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "# #             if(len(face_list) != 0 and face_list[-1].shape[0] == int(bbox_coordinates[2] - bbox_coordinates[0])):\n",
+    "# #                 img_face = image.crop((bbox_coordinates[0] -1, bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "#             img_face = np.array(img_face)\n",
+    "            \n",
+    "#             if len(face_list) != 0:\n",
+    "#                 if img_face.shape[0] == face_list[-1].shape[0]:\n",
+    "#                     img_face = image.crop((bbox_coordinates[0] - 1, bbox_coordinates[1] - 1, bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "#                     img_face = np.array(img_face)\n",
+    "            \n",
+    "#             face_list.append(img_face)\n",
+    "#         face_list = np.asarray(face_list)\n",
+    "#         np.savez('../Dataset/SingleFaceFeatures/train/Negative/neg_' + str(neg_train_count + 1), a = face_list)\n",
+    "        \n",
+    "#         neg_train_count += 1\n",
+    "# #         print('neg' + str(neg_train_count+1))\n",
+    "        \n",
+    "#     elif label == 1:\n",
+    "#         bbox_lm = np.load('../Dataset/FaceFeatures/train/Neutral/neu_' + str(neut_train_count + 1) +'.npz')\n",
+    "#         bounding_boxes = bbox_lm['a']\n",
+    "#         landmarks = bbox_lm['b']\n",
+    "        \n",
+    "#         for j in range(len(bounding_boxes)):\n",
+    "#             bbox_coordinates = bounding_boxes[j]\n",
+    "#             img_face = image.crop((bbox_coordinates[0], bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "# #             if(len(face_list) != 0 and face_list[-1].shape[0] == int(bbox_coordinates[2] - bbox_coordinates[0])):\n",
+    "# #                 img_face = image.crop((bbox_coordinates[0] -1, bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "#             img_face = np.array(img_face)\n",
+    "            \n",
+    "#             if len(face_list) != 0:\n",
+    "#                 if img_face.shape[0] == face_list[-1].shape[0]:\n",
+    "#                     img_face = image.crop((bbox_coordinates[0] - 1, bbox_coordinates[1] - 1, bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "#                     img_face = np.array(img_face)\n",
+    "            \n",
+    "#             face_list.append(img_face)\n",
+    "#         face_list = np.asarray(face_list)\n",
+    "#         np.savez('../Dataset/SingleFaceFeatures/train/Neutral/neu_' + str(neut_train_count + 1), a = face_list)\n",
+    "        \n",
+    "#         neut_train_count += 1\n",
+    "\n",
+    "        \n",
+    "#     else:\n",
+    "#         bbox_lm = np.load('../Dataset/FaceFeatures/train/Positive/pos_' + str(pos_train_count + 1) +'.npz')\n",
+    "#         bounding_boxes = bbox_lm['a']\n",
+    "#         landmarks = bbox_lm['b']\n",
+    "        \n",
+    "#         for j in range(len(bounding_boxes)):\n",
+    "#             bbox_coordinates = bounding_boxes[j]\n",
+    "#             img_face = image.crop((bbox_coordinates[0], bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "# #             if (len(face_list) != 0 and face_list[-1].shape[0] == bbox_coordinates[2] - bbox_coordinates[0]):\n",
+    "# #                 img_face = image.crop((bbox_coordinates[0] -1, bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "#             img_face = np.array(img_face)\n",
+    "\n",
+    "#             if len(face_list) != 0:\n",
+    "#                 if img_face.shape[0] == face_list[-1].shape[0]:\n",
+    "#                     img_face = image.crop((bbox_coordinates[0] - 1, bbox_coordinates[1] - 1, bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "#                     img_face = np.array(img_face)\n",
+    "            \n",
+    "#             face_list.append(img_face)\n",
+    "#         face_list = np.asarray(face_list)\n",
+    "#         np.savez('../Dataset/SingleFaceFeatures/train/Positive/pos_' + str(pos_train_count + 1), a = face_list)\n",
+    "        \n",
+    "#         pos_train_count += 1\n",
+    "#     if i % 100 == 0:\n",
+    "#         print(i)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "IndentationError",
+     "evalue": "expected an indented block (<ipython-input-5-cfe01df4bb19>, line 47)",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;36m  File \u001b[1;32m\"<ipython-input-5-cfe01df4bb19>\"\u001b[1;36m, line \u001b[1;32m47\u001b[0m\n\u001b[1;33m    landmarks = bbox_lm['b']\u001b[0m\n\u001b[1;37m            ^\u001b[0m\n\u001b[1;31mIndentationError\u001b[0m\u001b[1;31m:\u001b[0m expected an indented block\n"
      ]
     }
    ],
    "source": [
-    "for i in range(len(image_datasets['train'])):\n",
-    "# for i in range(1):\n",
-    "    image, label = image_datasets['train'][i]\n",
+    "# for i in range(len(training_dataset)):\n",
+    "for i in range(10):\n",
+    "    image, label = training_dataset[i]\n",
     "#     bounding_boxes, landmarks = detect_faces(image)\n",
     "    face_list = []\n",
+    "    landmarks_new_coordinates = []\n",
     "    if label == 0:\n",
-    "        bbox_lm = np.load('../Dataset/FaceFeatures/train/Negative/neg_' + str(neg_train_count + 1) +'.npz')\n",
+    "        bbox_lm = np.load(face_coordinates_directory + 'train/Negative/' + train_filelist[i] +'.npz')\n",
     "        bounding_boxes = bbox_lm['a']\n",
+    "        if((bounding_boxes == 0)[0]):\n",
+    "            print(\"No bounding boxes for \" + train_filelist[i] + \". Adding empty file for the same\")\n",
+    "            np.savez(processed_dataset_path + 'train/Negative' + train_filelist[i], a = np.zeros(1), b = np.zeros(1))\n",
+    "            continue\n",
     "        landmarks = bbox_lm['b']\n",
     "        \n",
     "        for j in range(len(bounding_boxes)):\n",
     "            bbox_coordinates = bounding_boxes[j]\n",
+    "            landmark = landmarks[j]\n",
     "            img_face = image.crop((bbox_coordinates[0], bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
     "#             if(len(face_list) != 0 and face_list[-1].shape[0] == int(bbox_coordinates[2] - bbox_coordinates[0])):\n",
     "#                 img_face = image.crop((bbox_coordinates[0] -1, bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "            x = bbox_coordinates[0]\n",
+    "            y = bbox_coordinates[1]\n",
+    "            for k in range(5):\n",
+    "                landmark[k] -= x\n",
+    "                landmark[k+5] -= y\n",
     "            img_face = np.array(img_face)\n",
+    "            landmark = np.array(landmark)\n",
+    "            \n",
     "            \n",
     "            if len(face_list) != 0:\n",
     "                if img_face.shape[0] == face_list[-1].shape[0]:\n",
     "                    img_face = image.crop((bbox_coordinates[0] - 1, bbox_coordinates[1] - 1, bbox_coordinates[2], bbox_coordinates[3]))\n",
     "                    img_face = np.array(img_face)\n",
+    "                    landmark -=1\n",
     "            \n",
     "            face_list.append(img_face)\n",
+    "            landmarks_new_coordinates.append(landmark)\n",
     "        face_list = np.asarray(face_list)\n",
-    "        np.savez('../Dataset/SingleFaceFeatures/train/Negative/neg_' + str(neg_train_count + 1), a = face_list)\n",
-    "        \n",
-    "        neg_train_count += 1\n",
-    "#         print('neg' + str(neg_train_count+1))\n",
+    "        landmarks_new_coordinates = np.asarray(landmarks_new_coordinates)\n",
+    "        np.savez(processed_dataset_path + 'train/Negative/' + train_filelist[i], a = face_list, b = landmarks_new_coordinates)\n",
     "        \n",
     "    elif label == 1:\n",
-    "        bbox_lm = np.load('../Dataset/FaceFeatures/train/Neutral/neu_' + str(neut_train_count + 1) +'.npz')\n",
+    "        bbox_lm = np.load(face_coordinates_directory + 'train/Neutral/' + train_filelist[i] +'.npz')\n",
     "        bounding_boxes = bbox_lm['a']\n",
+    "        if((bounding_boxes == 0)[0]):\n",
+    "            print(\"No bounding boxes for \" + train_filelist[i] + \". Adding empty file for the same\")\n",
+    "            np.savez(processed_dataset_path + 'train/Neutral' + train_filelist[i], a = np.zeros(1), b = np.zeros(1))\n",
+    "            continue\n",
     "        landmarks = bbox_lm['b']\n",
     "        \n",
     "        for j in range(len(bounding_boxes)):\n",
     "            bbox_coordinates = bounding_boxes[j]\n",
+    "            landmark = landmarks[j]\n",
     "            img_face = image.crop((bbox_coordinates[0], bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
     "#             if(len(face_list) != 0 and face_list[-1].shape[0] == int(bbox_coordinates[2] - bbox_coordinates[0])):\n",
     "#                 img_face = image.crop((bbox_coordinates[0] -1, bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "            x = bbox_coordinates[0]\n",
+    "            y = bbox_coordinates[1]\n",
+    "            for k in range(5):\n",
+    "                landmark[k] -= x\n",
+    "                landmark[k+5] -= y\n",
     "            img_face = np.array(img_face)\n",
+    "            landmark = np.array(landmark)\n",
     "            \n",
     "            if len(face_list) != 0:\n",
     "                if img_face.shape[0] == face_list[-1].shape[0]:\n",
     "                    img_face = image.crop((bbox_coordinates[0] - 1, bbox_coordinates[1] - 1, bbox_coordinates[2], bbox_coordinates[3]))\n",
     "                    img_face = np.array(img_face)\n",
+    "                    landmark -= 1\n",
     "            \n",
     "            face_list.append(img_face)\n",
+    "            landmarks_new_coordinates.append(landmark)\n",
     "        face_list = np.asarray(face_list)\n",
-    "        np.savez('../Dataset/SingleFaceFeatures/train/Neutral/neu_' + str(neut_train_count + 1), a = face_list)\n",
-    "        \n",
-    "        neut_train_count += 1\n",
-    "\n",
+    "        landmarks_new_coordinates = np.asarray(landmarks_new_coordinates)\n",
+    "        np.savez(processed_dataset_path + 'train/Neutral/' + train_filelist[i], a = face_list, b = landmarks_new_coordinates)\n",
     "        \n",
     "    else:\n",
-    "        bbox_lm = np.load('../Dataset/FaceFeatures/train/Positive/pos_' + str(pos_train_count + 1) +'.npz')\n",
+    "        bbox_lm = np.load(face_coordinates_directory + 'train/Positive/' + train_filelist[i] +'.npz')\n",
     "        bounding_boxes = bbox_lm['a']\n",
+    "        if((bounding_boxes == 0)[0]):\n",
+    "            print(\"No bounding boxes for \" + train_filelist[i] + \". Adding empty file for the same\")\n",
+    "            np.savez(processed_dataset_path + 'train/Positive' + train_filelist[i], a = np.zeros(1), b = np.zeros(1))\n",
+    "            continue\n",
     "        landmarks = bbox_lm['b']\n",
     "        \n",
     "        for j in range(len(bounding_boxes)):\n",
     "            bbox_coordinates = bounding_boxes[j]\n",
+    "            landmark = landmarks[j]\n",
     "            img_face = image.crop((bbox_coordinates[0], bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
-    "#             if (len(face_list) != 0 and face_list[-1].shape[0] == bbox_coordinates[2] - bbox_coordinates[0]):\n",
+    "#             if(len(face_list) != 0 and face_list[-1].shape[0] == int(bbox_coordinates[2] - bbox_coordinates[0])):\n",
     "#                 img_face = image.crop((bbox_coordinates[0] -1, bbox_coordinates[1], bbox_coordinates[2], bbox_coordinates[3]))\n",
+    "            x = bbox_coordinates[0]\n",
+    "            y = bbox_coordinates[1]\n",
+    "            for k in range(5):\n",
+    "                landmark[k] -= x\n",
+    "                landmark[k+5] -= y\n",
     "            img_face = np.array(img_face)\n",
-    "\n",
+    "            landmark = np.array(landmark)\n",
+    "            \n",
     "            if len(face_list) != 0:\n",
     "                if img_face.shape[0] == face_list[-1].shape[0]:\n",
     "                    img_face = image.crop((bbox_coordinates[0] - 1, bbox_coordinates[1] - 1, bbox_coordinates[2], bbox_coordinates[3]))\n",
     "                    img_face = np.array(img_face)\n",
+    "                    landmark -= 1\n",
     "            \n",
     "            face_list.append(img_face)\n",
+    "            landmarks_new_coordinates.append(landmark)\n",
     "        face_list = np.asarray(face_list)\n",
-    "        np.savez('../Dataset/SingleFaceFeatures/train/Positive/pos_' + str(pos_train_count + 1), a = face_list)\n",
+    "        landmarks_new_coordinates = np.asarray(landmarks_new_coordinates)\n",
+    "        np.savez(processed_dataset_path + 'train/Positive/' + train_filelist[i], a = face_list, b = landmarks_new_coordinates)\n",
     "        \n",
-    "        pos_train_count += 1\n",
     "    if i % 100 == 0:\n",
     "        print(i)"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": []
-  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -382,7 +531,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "image = image_datasets['train'][155][0]\n",
@@ -392,7 +543,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "show_bboxes(image, bounding_boxes, landmarks)"
@@ -401,7 +554,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "print(len(bounding_boxes))\n",
@@ -411,7 +566,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "face_list = []\n",
@@ -432,7 +589,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "face_list.shape"
@@ -453,7 +612,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "img1"
@@ -517,7 +678,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "image"
@@ -547,7 +710,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "a"
@@ -567,7 +732,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "print(arr[0].shape)\n",
@@ -582,6 +749,122 @@
    },
    "outputs": [],
    "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "arr = np.zeros(0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "arr.size"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "bbox_lm = np.load('../Dataset/FaceFeatures/val/Negative/neg_' + str(3) +'.npz')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "bb = bbox_lm['a']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([], shape=(0, 5), dtype=float64)"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "bb"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "testing = np.load('../Dataset/SingleFaceFeatures/train/Negative/neg_' + str(2) + '.npz')['a']\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([], dtype=float64)"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "detect_faces(image_datasets['train'][1])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAoAAAAFQCAIAAACgeVjGAAEAAElEQVR4nOz9y5blOK4mCH8AKe1t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\nQmCC\n",
+      "text/plain": [
+       "<PIL.Image.Image image mode=RGB size=640x336 at 0x1EC9C80EAC8>"
+      ]
+     },
+     "execution_count": 37,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "image_datasets['train'][1][0]"
+   ]
   }
  ],
  "metadata": {
diff --git a/MTCNN for face detection/Face Extraction .ipynb b/MTCNN for face detection/Face Extraction .ipynb
index 21d4a09..8fb8468 100644
--- a/MTCNN for face detection/Face Extraction .ipynb	
+++ b/MTCNN for face detection/Face Extraction .ipynb	
@@ -8,8 +8,8 @@
    },
    "outputs": [],
    "source": [
-    "%load_ext autoreload\n",
-    "%autoreload 2"
+    "# %load_ext autoreload\n",
+    "# %autoreload 2"
    ]
   },
   {
@@ -19,6 +19,29 @@
     "collapsed": true
    },
    "outputs": [],
+   "source": [
+    "#needs to be updated for exception handling from other pc"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
    "source": [
     "from src import detect_faces, show_bboxes\n",
     "from PIL import Image\n",
@@ -31,7 +54,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "dataset_path = '../Dataset/emotiw/'\n",
+    "\n",
+    "processed_dataset_path = '../Dataset/FaceCoordinates/'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
    "metadata": {
     "collapsed": true
    },
@@ -43,12 +79,11 @@
     "#     'val' : transforms.Compose([transforms.ToPILImage()])\n",
     "# }\n",
     "\n",
-    "data_dir = '../Dataset/emotiw/'\n",
     "\n",
-    "# image_datasets = {x : datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x])\n",
+    "# image_datasets = {x : datasets.ImageFolder(os.path.join(dataset_path, x), data_transforms[x])\n",
     "#                     for x in ['train', 'val']}\n",
     "\n",
-    "image_datasets = {x : datasets.ImageFolder(os.path.join(data_dir, x))\n",
+    "image_datasets = {x : datasets.ImageFolder(os.path.join(dataset_path, x))\n",
     "                    for x in ['train', 'val']}\n",
     "\n",
     "# dataloaders = { x : torch.utils.data.DataLoader(image_datasets[x], batch_size = 1, shuffle=True, num_workers= 4)\n",
@@ -63,7 +98,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -72,7 +107,7 @@
        "['Negative', 'Neutral', 'Positive']"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -83,18 +118,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "train_data = image_datasets['val']"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "metadata": {
     "collapsed": true
    },
@@ -120,7 +144,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "metadata": {
     "collapsed": true
    },
@@ -141,64 +165,476 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 10,
    "metadata": {
     "collapsed": true
    },
    "outputs": [],
    "source": [
-    "pos_train_count = 0\n",
-    "neg_train_count = 0\n",
-    "neut_train_count = 0"
+    "training_dataset = image_datasets['train']\n",
+    "validation_dataset = image_datasets['val']"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 11,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "neg_train = sorted(os.listdir(dataset_path + 'train/Negative/'))\n",
+    "neu_train = sorted(os.listdir(dataset_path + 'train/Neutral/'))\n",
+    "pos_train = sorted(os.listdir(dataset_path + 'train/Positive/'))\n",
+    "\n",
+    "neg_val = sorted(os.listdir(dataset_path + 'val/Negative/'))\n",
+    "neu_val = sorted(os.listdir(dataset_path + 'val/Neutral/'))\n",
+    "pos_val = sorted(os.listdir(dataset_path + 'val/Positive/'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "neg_train_filelist = [x.split('.')[0] for x in neg_train]\n",
+    "neu_train_filelist = [x.split('.')[0] for x in neu_train]\n",
+    "pos_train_filelist = [x.split('.')[0] for x in pos_train]\n",
+    "\n",
+    "neg_val_filelist = [x.split('.')[0] for x in neg_val]\n",
+    "neu_val_filelist = [x.split('.')[0] for x in neu_val]\n",
+    "pos_val_filelist = [x.split('.')[0] for x in pos_val]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
-     "name": "stderr",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
-      "C:\\Users\\Aarush\\Desktop\\EmotiW\\MTCNN for face detection\\src\\first_stage.py:32: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.\n",
-      "  img = Variable(torch.FloatTensor(_preprocess(img)), volatile=True)\n",
-      "C:\\Users\\Aarush\\Desktop\\EmotiW\\MTCNN for face detection\\src\\get_nets.py:70: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.\n",
-      "  a = F.softmax(a)\n",
-      "C:\\Users\\Aarush\\Desktop\\EmotiW\\MTCNN for face detection\\src\\detector.py:79: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.\n",
-      "  img_boxes = Variable(torch.FloatTensor(img_boxes), volatile=True)\n",
-      "C:\\Users\\Aarush\\Desktop\\EmotiW\\MTCNN for face detection\\src\\get_nets.py:115: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.\n",
-      "  a = F.softmax(a)\n",
-      "C:\\Users\\Aarush\\Desktop\\EmotiW\\MTCNN for face detection\\src\\detector.py:100: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead.\n",
-      "  img_boxes = Variable(torch.FloatTensor(img_boxes), volatile=True)\n",
-      "C:\\Users\\Aarush\\Desktop\\EmotiW\\MTCNN for face detection\\src\\get_nets.py:168: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.\n",
-      "  a = F.softmax(a)\n"
+      "['neg_1', 'neg_10', 'neg_100', 'neg_1000', 'neg_1001', 'neg_1002', 'neg_1003', 'neg_1004', 'neg_1005', 'neg_1006']\n",
+      "['neu_1', 'neu_10', 'neu_100', 'neu_1000', 'neu_1001', 'neu_1002', 'neu_1003', 'neu_1004', 'neu_1005', 'neu_1006']\n",
+      "['pos_1', 'pos_10', 'pos_100', 'pos_1000', 'pos_1001', 'pos_1002', 'pos_1003', 'pos_1004', 'pos_1005', 'pos_1006']\n",
+      "['neg_1', 'neg_10', 'neg_100', 'neg_1000', 'neg_1001', 'neg_1002', 'neg_1003', 'neg_1004', 'neg_1005', 'neg_1006']\n",
+      "['neu_1', 'neu_10', 'neu_100', 'neu_1000', 'neu_1001', 'neu_1002', 'neu_1003', 'neu_1004', 'neu_1005', 'neu_1006']\n",
+      "['pos_1', 'pos_10', 'pos_100', 'pos_1000', 'pos_1001', 'pos_1002', 'pos_1003', 'pos_1004', 'pos_1005', 'pos_1006']\n"
      ]
-    },
+    }
+   ],
+   "source": [
+    "print(neg_train_filelist[:10])\n",
+    "print(neu_train_filelist[:10])\n",
+    "print(pos_train_filelist[:10])\n",
+    "\n",
+    "print(neg_val_filelist[:10])\n",
+    "print(neu_val_filelist[:10])\n",
+    "print(pos_val_filelist[:10])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "train_filelist = neg_train_filelist + neu_train_filelist + pos_train_filelist\n",
+    "val_filelist = neg_val_filelist + neu_val_filelist + pos_val_filelist"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "# pos_train_count = 0\n",
+    "# neg_train_count = 0\n",
+    "# neut_train_count = 0"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "0\n"
+      "9815\n",
+      "4346\n"
      ]
     }
    ],
    "source": [
-    "for i in range(len(image_datasets['val'])):\n",
-    "# for i in range(1):\n",
-    "    image, label = image_datasets['val'][i]\n",
-    "    bounding_boxes, landmarks = detect_faces(image)\n",
-    "    if label == 0:\n",
-    "        np.savez('../Dataset/FaceFeatures/val/Negative/neg_' + str(neg_train_count + 1), a=bounding_boxes, b=landmarks)\n",
-    "        neg_train_count = neg_train_count + 1\n",
-    "    elif label == 1:\n",
-    "        np.savez('../Dataset/FaceFeatures/val/Neutral/neu_' + str(neut_train_count + 1), a=bounding_boxes, b=landmarks)\n",
-    "        neut_train_count += 1\n",
-    "    else:\n",
-    "        np.savez('../Dataset/FaceFeatures/val/Positive/pos_' + str(pos_train_count + 1), a=bounding_boxes, b=landmarks)\n",
-    "        pos_train_count += 1\n",
-    "    if i % 100 == 0:\n",
-    "        print(i)"
+    "print(len(training_dataset))\n",
+    "print(len(validation_dataset))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "#No faces detected for pos_928. Empty file stored"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "for i in range(len(training_dataset)):\n",
+    "# for i in range(5):\n",
+    "    image, label = training_dataset[i]\n",
+    "    print(train_filelist[i])\n",
+    "    try:\n",
+    "        bounding_boxes, landmarks = detect_faces(image)\n",
+    "        if bounding_boxes.size == 0:\n",
+    "            print('MTCNN model handling empty face condition at ' + train_filelist[i])\n",
+    "        if label == 0:\n",
+    "            np.savez(processed_dataset_path + 'train/Negative/' + train_filelist[i] , a=bounding_boxes, b=landmarks)\n",
+    "#             neg_train_count = neg_train_count + 1\n",
+    "        elif label == 1:\n",
+    "            np.savez(processed_dataset_path + 'train/Neutral/' + train_filelist[i] , a=bounding_boxes, b=landmarks)\n",
+    "#             neut_train_count += 1\n",
+    "        else:\n",
+    "            np.savez(processed_dataset_path + 'train/Positive/' + train_filelist[i] , a=bounding_boxes, b=landmarks)\n",
+    "#             pos_train_count += 1\n",
+    "#         if i % 100 == 0:\n",
+    "#             print(i)\n",
+    "            \n",
+    "            \n",
+    "    except ValueError:\n",
+    "        print('No faces detected for ' + train_filelist[i] + \". Also MTCNN failed.\")\n",
+    "        if label == 0:\n",
+    "#             print('File ' + train_filelist[i] + \" empty\")\n",
+    "            np.savez(processed_dataset_path + 'train/Negative/' + train_filelist[i] , a=np.zeros(1), b=np.zeros(1))\n",
+    "#             neg_train_count += 1\n",
+    "        elif label == 1:\n",
+    "#             print('File ' + train_filelist[i] + \" empty\")\n",
+    "            np.savez(processed_dataset_path + 'train/Neutral/' + train_filelist[i] , a=np.zeros(1), b=np.zeros(1))\n",
+    "#             neut_train_count += 1\n",
+    "        else:\n",
+    "#             print('File ' + train_filelist[i] + \" empty\")\n",
+    "            np.savez(processed_dataset_path + 'train/Positive/' + train_filelist[i] , a=np.zeros(1), b=np.zeros(1))\n",
+    "#             pos_train_count += 1\n",
+    "        continue"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "neg_1\n",
+      "neg_10\n",
+      "neg_100\n",
+      "MTCNN model handling empty face condition at neg_100\n",
+      "neg_1000\n",
+      "neg_1001\n",
+      "neg_1002\n",
+      "neg_1003\n",
+      "neg_1004\n",
+      "neg_1005\n",
+      "neg_1006\n",
+      "neg_1007\n",
+      "neg_1008\n",
+      "neg_1009\n",
+      "MTCNN model handling empty face condition at neg_1009\n",
+      "neg_101\n",
+      "neg_1010\n",
+      "neg_1011\n",
+      "neg_1012\n",
+      "neg_1013\n",
+      "neg_1014\n",
+      "MTCNN model handling empty face condition at neg_1014\n",
+      "neg_1015\n",
+      "neg_1016\n",
+      "neg_1017\n",
+      "neg_1018\n",
+      "neg_1019\n",
+      "neg_102\n",
+      "neg_1020\n",
+      "neg_1021\n",
+      "neg_1022\n",
+      "neg_1023\n",
+      "neg_1024\n",
+      "neg_1025\n",
+      "neg_1026\n",
+      "neg_1027\n",
+      "neg_1028\n",
+      "neg_1029\n",
+      "neg_103\n",
+      "neg_1030\n",
+      "neg_1031\n",
+      "neg_1032\n",
+      "neg_1033\n",
+      "neg_1034\n",
+      "neg_1035\n",
+      "neg_1036\n",
+      "neg_1037\n",
+      "neg_1038\n",
+      "neg_1039\n",
+      "neg_104\n",
+      "neg_1040\n",
+      "neg_1041\n",
+      "neg_1042\n",
+      "neg_1043\n",
+      "neg_1044\n",
+      "neg_1045\n",
+      "neg_1046\n",
+      "neg_1047\n",
+      "neg_1048\n",
+      "neg_1049\n",
+      "neg_105\n",
+      "neg_1050\n",
+      "neg_1051\n",
+      "neg_1052\n",
+      "neg_1053\n",
+      "neg_1054\n",
+      "neg_1055\n",
+      "neg_1056\n",
+      "neg_1057\n",
+      "neg_1058\n",
+      "neg_1059\n",
+      "neg_106\n",
+      "neg_1060\n",
+      "neg_1061\n",
+      "neg_1062\n",
+      "neg_1063\n",
+      "neg_1064\n",
+      "neg_1065\n",
+      "neg_1066\n",
+      "neg_1067\n",
+      "neg_1068\n",
+      "neg_1069\n",
+      "neg_107\n",
+      "neg_1070\n",
+      "neg_1071\n",
+      "neg_1072\n",
+      "neg_1073\n",
+      "neg_1074\n",
+      "neg_1075\n",
+      "neg_1076\n",
+      "neg_1077\n",
+      "neg_1078\n",
+      "neg_1079\n",
+      "neg_108\n",
+      "neg_1080\n",
+      "neg_1081\n",
+      "neg_1082\n",
+      "neg_1083\n",
+      "neg_1084\n",
+      "neg_1085\n",
+      "neg_1086\n",
+      "neg_1087\n",
+      "neg_1088\n",
+      "neg_1089\n",
+      "neg_109\n",
+      "neg_1090\n",
+      "neg_1091\n",
+      "neg_1092\n",
+      "neg_1093\n",
+      "neg_1094\n",
+      "neg_1095\n",
+      "neg_1096\n",
+      "neg_1097\n",
+      "neg_1098\n",
+      "neg_1099\n",
+      "neg_11\n",
+      "neg_110\n",
+      "neg_1100\n",
+      "neg_1101\n",
+      "neg_1102\n",
+      "neg_1103\n",
+      "neg_1104\n",
+      "neg_1105\n",
+      "neg_1106\n",
+      "neg_1107\n",
+      "neg_1108\n",
+      "neg_1109\n",
+      "neg_111\n",
+      "neg_1110\n",
+      "neg_1111\n",
+      "neg_1112\n",
+      "neg_1113\n",
+      "neg_1114\n",
+      "neg_1115\n",
+      "neg_1116\n",
+      "neg_1117\n",
+      "neg_1118\n",
+      "neg_1119\n",
+      "neg_112\n",
+      "neg_1120\n",
+      "neg_1121\n",
+      "neg_1122\n",
+      "neg_1123\n",
+      "neg_1124\n",
+      "neg_1125\n",
+      "neg_1126\n",
+      "neg_1127\n",
+      "neg_1128\n",
+      "neg_1129\n",
+      "neg_113\n",
+      "neg_1130\n",
+      "neg_1131\n",
+      "neg_1132\n",
+      "neg_1133\n",
+      "neg_1134\n",
+      "neg_1135\n",
+      "neg_1136\n",
+      "neg_1137\n",
+      "neg_1138\n",
+      "neg_1139\n",
+      "neg_114\n",
+      "neg_1140\n",
+      "neg_1141\n",
+      "neg_1142\n",
+      "neg_1143\n",
+      "neg_1144\n",
+      "neg_1145\n",
+      "neg_1146\n",
+      "neg_1147\n",
+      "neg_1148\n",
+      "neg_1149\n",
+      "neg_115\n",
+      "neg_1150\n",
+      "neg_1151\n",
+      "neg_1152\n",
+      "neg_1153\n",
+      "neg_1154\n",
+      "neg_1155\n",
+      "neg_1156\n",
+      "neg_1157\n",
+      "neg_1158\n",
+      "neg_1159\n",
+      "neg_116\n",
+      "neg_1160\n",
+      "neg_1161\n",
+      "neg_1162\n",
+      "neg_1163\n",
+      "neg_1164\n",
+      "neg_1165\n",
+      "neg_1166\n",
+      "neg_1167\n",
+      "neg_1168\n",
+      "neg_1169\n",
+      "neg_117\n",
+      "neg_1170\n",
+      "neg_1171\n",
+      "neg_1172\n",
+      "neg_1173\n",
+      "neg_1174\n",
+      "neg_1175\n",
+      "neg_1176\n",
+      "neg_1177\n",
+      "neg_1178\n",
+      "neg_1179\n",
+      "neg_118\n",
+      "neg_1180\n",
+      "neg_1181\n",
+      "neg_1182\n",
+      "neg_1183\n",
+      "neg_1184\n",
+      "neg_1185\n",
+      "neg_1186\n",
+      "neg_1187\n",
+      "neg_1188\n",
+      "neg_1189\n",
+      "neg_119\n",
+      "neg_1190\n",
+      "neg_1191\n",
+      "neg_1192\n",
+      "neg_1193\n",
+      "neg_1194\n",
+      "neg_1195\n",
+      "neg_1196\n",
+      "neg_1197\n",
+      "neg_1198\n",
+      "neg_1199\n",
+      "neg_12\n",
+      "neg_120\n",
+      "neg_1200\n",
+      "neg_1201\n",
+      "neg_1202\n",
+      "neg_1203\n",
+      "neg_1204\n",
+      "neg_1205\n",
+      "neg_1206\n",
+      "neg_1207\n",
+      "neg_1208\n",
+      "neg_1209\n",
+      "neg_121\n",
+      "neg_1210\n",
+      "neg_1211\n",
+      "neg_1212\n",
+      "neg_1213\n",
+      "neg_1214\n",
+      "neg_1215\n",
+      "neg_1216\n",
+      "neg_1217\n",
+      "neg_1218\n"
+     ]
+    }
+   ],
+   "source": [
+    "for i in range(len(validation_dataset)):\n",
+    "# for i in range(5):\n",
+    "    image, label = validation_dataset[i]\n",
+    "    print(val_filelist[i])\n",
+    "    try:\n",
+    "        bounding_boxes, landmarks = detect_faces(image)\n",
+    "        if bounding_boxes.size == 0:\n",
+    "            print('MTCNN model handling empty face condition at ' + val_filelist[i])\n",
+    "        if label == 0:\n",
+    "            np.savez(processed_dataset_path + 'val/Negative/' + val_filelist[i] , a=bounding_boxes, b=landmarks)\n",
+    "#             neg_val_count = neg_val_count + 1\n",
+    "        elif label == 1:\n",
+    "            np.savez(processed_dataset_path + 'val/Neutral/' + val_filelist[i] , a=bounding_boxes, b=landmarks)\n",
+    "#             neut_val_count += 1\n",
+    "        else:\n",
+    "            np.savez(processed_dataset_path + 'val/Positive/' + val_filelist[i] , a=bounding_boxes, b=landmarks)\n",
+    "#             pos_val_count += 1\n",
+    "#         if i % 100 == 0:\n",
+    "#             print(i)\n",
+    "            \n",
+    "            \n",
+    "    except ValueError:\n",
+    "        print('No faces detected for ' + val_filelist[i] + \". Also MTCNN failed.\")\n",
+    "        if label == 0:\n",
+    "#             print('File ' + val_filelist[i] + \" empty\")\n",
+    "            np.savez(processed_dataset_path + 'val/Negative/' + val_filelist[i] , a=np.zeros(1), b=np.zeros(1))\n",
+    "#             neg_val_count += 1\n",
+    "        elif label == 1:\n",
+    "#             print('File ' + val_filelist[i] + \" empty\")\n",
+    "            np.savez(processed_dataset_path + 'val/Neutral/' + val_filelist[i] , a=np.zeros(1), b=np.zeros(1))\n",
+    "#             neut_val_count += 1\n",
+    "        else:\n",
+    "#             print('File ' + val_filelist[i] + \" empty\")\n",
+    "            np.savez(processed_dataset_path + 'val/Positive/' + val_filelist[i] , a=np.zeros(1), b=np.zeros(1))\n",
+    "#             pos_val_count += 1\n",
+    "        continue"
    ]
   },
   {
@@ -236,6 +672,111 @@
     "bounding_boxes, landmarks = detect_faces(image_datasets['train'][7][0])"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "for i in range(1000):\n",
+    "        bbox_ld = np.load('../Dataset/FaceFeatures/train/Negative/neg_' + str(i + 1) + '.npz')\n",
+    "        bbox = bbox_ld['a']\n",
+    "#         landmarks = bbox_ld['b']\n",
+    "        if bbox.size == 0:\n",
+    "            print(bbox.shape, i + 1)\n",
+    "#             print(landmarks.shape)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "bboxes, landmarks = detect_faces(image_datasets['train'][457][0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "image_datasets['train'][1][0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "show_bboxes(image_datasets['train'][457][0], bboxes, landmarks)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "dataloaders['train'][0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "sorted(os.listdir('../Dataset/emotiw/train/Negative/'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "a = np.zeros(1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "(a == 0)[0]"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,