fixing dataset procesosrs

1 files changed, 104 insertions, 92 deletions

diff --git a/megapixels/notebooks/_local_scratch.ipynb b/megapixels/notebooks/_local_scratch.ipynb
index 167b6ddd..cee17cba 100644
--- a/megapixels/notebooks/_local_scratch.ipynb
+++ b/megapixels/notebooks/_local_scratch.ipynb
@@ -1,161 +1,173 @@
 {
  "cells": [
   {
-   "cell_type": "code",
-   "execution_count": 1,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
    "source": [
-    "import pandas as pd\n",
-    "import cv2 as cv\n",
-    "import numpy as np\n",
-    "%matplotlib inline\n",
-    "import matplotlib.pyplot as plt"
+    "# Scratch pad"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
-    "import sys\n",
     "from glob import glob\n",
     "from os.path import join\n",
     "from pathlib import Path\n",
+    "import random\n",
+    "\n",
+    "import pandas as pd\n",
+    "import cv2 as cv\n",
+    "import numpy as np\n",
+    "%matplotlib inline\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "import sys\n",
     "sys.path.append('/work/megapixels_dev/megapixels')\n",
     "from app.models.bbox import BBox\n",
-    "#from app.utils import im_utils\n",
-    "import random"
+    "from app.utils import im_utils, file_utils"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
-    "dir_ims = '/data_store_ssd/apps/megapixels/datasets/umd_faces/faces/'"
+    "a= [1]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "0\n"
-     ]
+     "data": {
+      "text/plain": [
+       "1"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
-    "fp_ims = glob(join(dir_ims, '*.png'))\n",
-    "print(len(fp_ims))"
+    "a[-1]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Help on function choice in module random:\n",
-      "\n",
-      "choice(self, seq)\n",
-      "    Choose a random element from a non-empty sequence.\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "help(random.sample)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 33,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[1, 8, 0, 6, 3] True\n"
-     ]
-    }
-   ],
-   "source": [
-    "a = list(range(0,10))\n",
-    "b = random.sample(a, 5)\n",
-    "print(b, len(set(b))==5)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 32,
    "metadata": {},
    "outputs": [],
    "source": [
-    "from random import randint\n",
-    "imu"
+    "fp_filepath = '/data_store_ssd/datasets/people/lfw/metadata/filepath.csv'\n",
+    "df_filepath = pd.read_csv(fp_filepath)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 48,
    "metadata": {},
    "outputs": [],
    "source": [
-    "import face_alignment\n",
-    "from skimage import io\n",
-    "\n",
-    "fa = face_alignment.FaceAlignment(face_alignment.LandmarksType._3D, flip_input=False,  device='cuda')"
+    "image_index = 12467"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 55,
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "fp_im = np.random.choice(fp_ims)\n",
-    "im = io.imread(fp_im)\n",
-    "preds = fa.get_landmarks(im)\n",
-    "print(preds[0])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "12474\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "index                   12851\n",
+       "ext                       jpg\n",
+       "fn        Vladimir_Putin_0029\n",
+       "subdir         Vladimir_Putin\n",
+       "Name: 12474, dtype: object"
+      ]
+     },
+     "execution_count": 55,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "import json"
+    "image_index += 1\n",
+    "print(image_index)\n",
+    "df_filepath.iloc[image_index]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 56,
    "metadata": {},
    "outputs": [],
    "source": [
-    "print(len(preds[0]))\n"
+    "import imutils"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 57,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Help on function build_montages in module imutils.convenience:\n",
+      "\n",
+      "build_montages(image_list, image_shape, montage_shape)\n",
+      "    ---------------------------------------------------------------------------------------------\n",
+      "    author: Kyle Hounslow\n",
+      "    ---------------------------------------------------------------------------------------------\n",
+      "    Converts a list of single images into a list of 'montage' images of specified rows and columns.\n",
+      "    A new montage image is started once rows and columns of montage image is filled.\n",
+      "    Empty space of incomplete montage images are filled with black pixels\n",
+      "    ---------------------------------------------------------------------------------------------\n",
+      "    :param image_list: python list of input images\n",
+      "    :param image_shape: tuple, size each image will be resized to for display (width, height)\n",
+      "    :param montage_shape: tuple, shape of image montage (width, height)\n",
+      "    :return: list of montage images in numpy array format\n",
+      "    ---------------------------------------------------------------------------------------------\n",
+      "    \n",
+      "    example usage:\n",
+      "    \n",
+      "    # load single image\n",
+      "    img = cv2.imread('lena.jpg')\n",
+      "    # duplicate image 25 times\n",
+      "    num_imgs = 25\n",
+      "    img_list = []\n",
+      "    for i in xrange(num_imgs):\n",
+      "        img_list.append(img)\n",
+      "    # convert image list into a montage of 256x256 images tiled in a 5x5 montage\n",
+      "    montages = make_montages_of_images(img_list, (256, 256), (5, 5))\n",
+      "    # iterate through montages and display\n",
+      "    for montage in montages:\n",
+      "        cv2.imshow('montage image', montage)\n",
+      "        cv2.waitKey(0)\n",
+      "    \n",
+      "    ----------------------------------------------------------------------------------------------\n",
+      "\n"
+     ]
+    }
+   ],
    "source": [
-    "with open('test.json', 'w') as fp:\n",
-    "  json.dump(preds[0].tolist(), fp)"
+    "help(imutils.build_montages)"
    ]
   },
   {
@@ -182,7 +194,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.5"
+   "version": "3.6.6"
   }
  },
  "nbformat": 4,