Doing pretty well now with resnet50 and adam with low learning rate. Also f...

natanielruiz

2017-08-10 54818d253649ff588ed0054d10dabb2a3a170309

 practice/smoothing_ypr.ipynb

@@ -2,7 +2,7 @@
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 156,
   "execution_count": 197,
   "metadata": {
    "collapsed": false
   },
@@ -17,7 +17,7 @@
  },
  {
   "cell_type": "code",
   "execution_count": 157,
   "execution_count": 198,
   "metadata": {
    "collapsed": false
   },
@@ -26,13 +26,13 @@
    "video_path = '../data/video/SGT036_2016_07_25_pivothead_AVI.avi'\n",
    "bbox_path = '../data/video/annotations/SGT036_childface.txt'\n",
    "\n",
    "annot_path = '../output/video/output-SGT036_resnet18_cr_epoch_1.txt'\n",
    "output_string = 'SGT036_resnet18_cr_epoch_1_flat_smoothed'"
    "annot_path = '../output/video/output-SGT036_resnet50_lowlr_epoch_20.txt'\n",
    "output_string = 'SGT036_resnet50_lowlr_epoch_20_smoothed'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 158,
   "execution_count": 199,
   "metadata": {
    "collapsed": false
   },
@@ -41,7 +41,7 @@
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[-6.069214 -0.831665  0.53318  ..., -3.836042 -3.868275 -2.377155]\n",
      "[ 4.170376  0.790443 -0.178368 ..., -3.437805  0.396835 -1.276176]\n",
      "(8508,)\n",
      "(53464,)\n"
     ]
@@ -93,7 +93,7 @@
  },
  {
   "cell_type": "code",
   "execution_count": 159,
   "execution_count": 200,
   "metadata": {
    "collapsed": false
   },
@@ -107,31 +107,39 @@
    }
   ],
   "source": [
    "window_len = 6\n",
    "window_len = 7\n",
    "pad = window_len / 2\n",
    "window = 'flat'\n",
    "window_2 = 'flat'\n",
    "window_len_2 = 7\n",
    "pad_2 = window_len_2 / 2\n",
    "\n",
    "s = np.r_[y[window_len-1:0:-1],y,y[-2:-window_len-1:-1]]\n",
    "t = np.r_[p[window_len-1:0:-1],p,p[-2:-window_len-1:-1]]\n",
    "u = np.r_[r[window_len-1:0:-1],r,r[-2:-window_len-1:-1]]\n",
    "\n",
    "xa = np.r_[x_min_arr[window_len-1:0:-1],x_min_arr,x_min_arr[-2:-window_len-1:-1]]\n",
    "xb = np.r_[x_max_arr[window_len-1:0:-1],x_max_arr,x_max_arr[-2:-window_len-1:-1]]\n",
    "ya = np.r_[y_min_arr[window_len-1:0:-1],y_min_arr,y_min_arr[-2:-window_len-1:-1]]\n",
    "yb = np.r_[y_max_arr[window_len-1:0:-1],y_max_arr,y_max_arr[-2:-window_len-1:-1]]\n",
    "xa = np.r_[x_min_arr[window_len_2-1:0:-1],x_min_arr,x_min_arr[-2:-window_len_2-1:-1]]\n",
    "xb = np.r_[x_max_arr[window_len_2-1:0:-1],x_max_arr,x_max_arr[-2:-window_len_2-1:-1]]\n",
    "ya = np.r_[y_min_arr[window_len_2-1:0:-1],y_min_arr,y_min_arr[-2:-window_len_2-1:-1]]\n",
    "yb = np.r_[y_max_arr[window_len_2-1:0:-1],y_max_arr,y_max_arr[-2:-window_len_2-1:-1]]\n",
    "\n",
    "if window == 'flat':\n",
    "    w=np.ones(window_len, 'd')\n",
    "else:\n",
    "    w=eval('np.' + window + '(window_len)')\n",
    "    \n",
    "if window_2 == 'flat':\n",
    "    w_2=np.ones(window_len_2, 'd')\n",
    "else:\n",
    "    w_2=eval('np.' + window_2 + '(window_len_2)')    \n",
    "\n",
    "y = np.convolve(w / w.sum(), s, mode='valid')[pad:-pad]\n",
    "p = np.convolve(w / w.sum(), t, mode='valid')[pad:-pad]\n",
    "r = np.convolve(w / w.sum(), u, mode='valid')[pad:-pad]\n",
    "x_min_arr = np.convolve(w / w.sum(), xa, mode='valid')[pad:-pad]\n",
    "x_max_arr = np.convolve(w / w.sum(), xb, mode='valid')[pad:-pad]\n",
    "y_min_arr = np.convolve(w / w.sum(), ya, mode='valid')[pad:-pad]\n",
    "y_max_arr = np.convolve(w / w.sum(), yb, mode='valid')[pad:-pad]\n",
    "x_min_arr = np.convolve(w_2 / w_2.sum(), xa, mode='valid')[pad_2:-pad_2]\n",
    "x_max_arr = np.convolve(w_2 / w_2.sum(), xb, mode='valid')[pad_2:-pad_2]\n",
    "y_min_arr = np.convolve(w_2 / w_2.sum(), ya, mode='valid')[pad_2:-pad_2]\n",
    "y_max_arr = np.convolve(w_2 / w_2.sum(), yb, mode='valid')[pad_2:-pad_2]\n",
    "\n",
    "pose_dict = {}\n",
    "bbox_dict = {}\n",
@@ -151,7 +159,7 @@
  },
  {
   "cell_type": "code",
   "execution_count": 160,
   "execution_count": 201,
   "metadata": {
    "collapsed": false
   },