VehicleDetection.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Vehicle Detection and Tracking "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1. Perform a Histogram of Oriented Gradients (HOG) feature extraction on a labeled training set of images and train a classifier Linear SVM classifier\n",
    "2. Optionally, you can also apply a color transform and append binned color features, as well as histograms of color, to your HOG feature vector.\n",
    "3. Note: for those first two steps don't forget to normalize your features and randomize a selection for training and testing.\n",
    "4. Implement a sliding-window technique and use your trained classifier to search for vehicles in images.\n",
    "5. Run your pipeline on a video stream (start with the test_video.mp4 and later implement on full project_video.mp4) and create a heat map of recurring detections frame by frame to reject outliers and follow detected vehicles.\n",
    "6. Estimate a bounding box for vehicles detected."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/bhavanabhasker/anaconda/lib/python3.5/site-packages/sklearn/cross_validation.py:44: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.\n",
      "  \"This module will be removed in 0.20.\", DeprecationWarning)\n"
     ]
    }
   ],
   "source": [
    "import matplotlib.image as mpimg\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import cv2\n",
    "import glob\n",
    "import time\n",
    "from sklearn.svm import LinearSVC\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from skimage.feature import hog\n",
    "from sklearn.cross_validation import train_test_split\n",
    "from scipy.ndimage.measurements import label\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "car_images = glob.iglob(\"vehicles/**/*.png\")\n",
    "noncar_images = glob.iglob(\"non-vehicles/**/*.png\")\n",
    "cars,noncars = [], []\n",
    "for image in car_images:\n",
    "    cars.append(image)\n",
    "for images in noncar_images:\n",
    "    noncars.append(images)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Color based Feature Extraction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Define a function to compute binned color features  \n",
    "def bin_spatial(img, size=(32, 32)):\n",
    "    # Use cv2.resize().ravel() to create the feature vector\n",
    "    features = cv2.resize(img, size).ravel() \n",
    "    # Return the feature vector\n",
    "    return features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Define a function to compute color histogram features  \n",
    "def color_hist(img, nbins=32, bins_range=(0, 256)):\n",
    "    # Compute the histogram of the color channels separately\n",
    "    channel1_hist = np.histogram(img[:,:,0], bins=nbins, range=bins_range)\n",
    "    channel2_hist = np.histogram(img[:,:,1], bins=nbins, range=bins_range)\n",
    "    channel3_hist = np.histogram(img[:,:,2], bins=nbins, range=bins_range)\n",
    "    # Concatenate the histograms into a single feature vector\n",
    "    hist_features = np.concatenate((channel1_hist[0], channel2_hist[0], channel3_hist[0]))\n",
    "    # Return the individual histograms, bin_centers and feature vector\n",
    "    return hist_features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Define a function to extract features from a list of images\n",
    "# Have this function call bin_spatial() and color_hist()\n",
    "def extract_features(imgs, cspace='RGB', spatial_size=(32, 32),\n",
    "                        hist_bins=32, hist_range=(0, 256)):\n",
    "    # Create a list to append feature vectors to\n",
    "    features = []\n",
    "    # Iterate through the list of images\n",
    "    for file in imgs:\n",
    "        # Read in each one by one\n",
    "        image = mpimg.imread(file)\n",
    "        # apply color conversion if other than 'RGB'\n",
    "        if cspace != 'RGB':\n",
    "            if cspace == 'HSV':\n",
    "                feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2HSV)\n",
    "            elif cspace == 'LUV':\n",
    "                feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2LUV)\n",
    "            elif cspace == 'HLS':\n",
    "                feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2HLS)\n",
    "            elif cspace == 'YUV':\n",
    "                feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2YUV)\n",
    "        else: feature_image = np.copy(image)      \n",
    "        # Apply bin_spatial() to get spatial color features\n",
    "        spatial_features = bin_spatial(feature_image, size=spatial_size)\n",
    "        # Apply color_hist() also with a color space option now\n",
    "        hist_features = color_hist(feature_image, nbins=hist_bins, bins_range=hist_range)\n",
    "        # Append the new feature vector to the features list\n",
    "        features.append(np.concatenate((spatial_features, hist_features)))\n",
    "    # Return list of feature vectors\n",
    "    return features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Using spatial binning of: 32 and 32 histogram bins\n",
      "Feature vector length: 3168\n",
      "37.06 Seconds to train SVC...\n",
      "Test Accuracy of SVC =  0.9079\n",
      "My SVC predicts:  [ 0.  1.  1.  1.  0.  1.  0.  0.  0.  1.]\n",
      "For these 10 labels:  [ 0.  1.  1.  1.  0.  1.  0.  0.  0.  1.]\n",
      "0.00101 Seconds to predict 10 labels with SVC\n"
     ]
    }
   ],
   "source": [
    "spatial = 32\n",
    "histbin = 32\n",
    "\n",
    "car_features = extract_features(cars, cspace='RGB', spatial_size=(spatial, spatial),\n",
    "                        hist_bins=histbin, hist_range=(0, 256))\n",
    "notcar_features = extract_features(noncars, cspace='RGB', spatial_size=(spatial, spatial),\n",
    "                        hist_bins=histbin, hist_range=(0, 256))\n",
    "\n",
    "# Create an array stack of feature vectors\n",
    "X = np.vstack((car_features, notcar_features)).astype(np.float64)                        \n",
    "# Fit a per-column scaler\n",
    "X_scaler = StandardScaler().fit(X)\n",
    "# Apply the scaler to X\n",
    "scaled_X = X_scaler.transform(X)\n",
    "\n",
    "# Define the labels vector\n",
    "y = np.hstack((np.ones(len(car_features)), np.zeros(len(notcar_features))))\n",
    "\n",
    "\n",
    "# Split up data into randomized training and test sets\n",
    "rand_state = np.random.randint(0, 100)\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    scaled_X, y, test_size=0.2, random_state=rand_state)\n",
    "\n",
    "print('Using spatial binning of:',spatial,\n",
    "    'and', histbin,'histogram bins')\n",
    "print('Feature vector length:', len(X_train[0]))\n",
    "# Use a linear SVC \n",
    "svc = LinearSVC(C=2.0)\n",
    "# Check the training time for the SVC\n",
    "t=time.time()\n",
    "svc.fit(X_train, y_train)\n",
    "t2 = time.time()\n",
    "print(round(t2-t, 2), 'Seconds to train SVC...')\n",
    "# Check the score of the SVC\n",
    "print('Test Accuracy of SVC = ', round(svc.score(X_test, y_test), 4))\n",
    "# Check the prediction time for a single sample\n",
    "t=time.time()\n",
    "n_predict = 10\n",
    "print('My SVC predicts: ', svc.predict(X_test[0:n_predict]))\n",
    "print('For these',n_predict, 'labels: ', y_test[0:n_predict])\n",
    "t2 = time.time()\n",
    "print(round(t2-t, 5), 'Seconds to predict', n_predict,'labels with SVC')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### HOG Based Feature Extraction "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Define a function to return HOG features and visualization\n",
    "def get_hog_features(img, orient, pix_per_cell, cell_per_block, \n",
    "                        vis=False, feature_vec=True):\n",
    "    # Call with two outputs if vis==True\n",
    "    if vis == True:\n",
    "        features, hog_image = hog(img, orientations=orient, pixels_per_cell=(pix_per_cell, pix_per_cell),\n",
    "                                  cells_per_block=(cell_per_block, cell_per_block), transform_sqrt=True, \n",
    "                                  visualise=vis, feature_vector=feature_vec)\n",
    "        return features, hog_image\n",
    "    # Otherwise call with one output\n",
    "    else:      \n",
    "        features = hog(img, orientations=orient, pixels_per_cell=(pix_per_cell, pix_per_cell),\n",
    "                       cells_per_block=(cell_per_block, cell_per_block), transform_sqrt=True, \n",
    "                       visualise=vis, feature_vector=feature_vec)\n",
    "        return features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Define a function to extract features from a list of images\n",
    "# Have this function call bin_spatial() and color_hist()\n",
    "def extract_features(imgs, cspace='RGB', orient=9, \n",
    "                        pix_per_cell=8, cell_per_block=2, hog_channel=0):\n",
    "    # Create a list to append feature vectors to\n",
    "    features = []\n",
    "    # Iterate through the list of images\n",
    "    for file in imgs:\n",
    "        # Read in each one by one\n",
    "        image = mpimg.imread(file)\n",
    "        # apply color conversion if other than 'RGB'\n",
    "        if cspace != 'RGB':\n",
    "            if cspace == 'HSV':\n",
    "                feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2HSV)\n",
    "            elif cspace == 'LUV':\n",
    "                feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2LUV)\n",
    "            elif cspace == 'HLS':\n",
    "                feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2HLS)\n",
    "            elif cspace == 'YUV':\n",
    "                feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2YUV)\n",
    "            elif cspace == 'YCrCb':\n",
    "                feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2YCrCb)\n",
    "        else: feature_image = np.copy(image)      \n",
    "\n",
    "        # Call get_hog_features() with vis=False, feature_vec=True\n",
    "        if hog_channel == 'ALL':\n",
    "            hog_features = []\n",
    "            for channel in range(feature_image.shape[2]):\n",
    "                hog_features.append(get_hog_features(feature_image[:,:,channel], \n",
    "                                    orient, pix_per_cell, cell_per_block, \n",
    "                                    vis=False, feature_vec=True))\n",
    "            hog_features = np.ravel(hog_features)        \n",
    "        else:\n",
    "            hog_features = get_hog_features(feature_image[:,:,hog_channel], orient, \n",
    "                        pix_per_cell, cell_per_block, vis=False, feature_vec=True)\n",
    "        # Append the new feature vector to the features list\n",
    "        features.append(hog_features)\n",
    "    # Return list of feature vectors\n",
    "    return features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "21.75 Seconds to extract HOG features...\n",
      "Using: 9 orientations 8 pixels per cell and 2 cells per block\n",
      "Feature vector length: 1764\n",
      "8.68 Seconds to train SVC...\n",
      "Test Accuracy of SVC =  0.9426\n",
      "My SVC predicts:  [ 0.  0.  0.  1.  0.  1.  1.  1.  0.  0.]\n",
      "For these 10 labels:  [ 0.  0.  0.  1.  0.  1.  1.  1.  0.  0.]\n",
      "0.00095 Seconds to predict 10 labels with SVC\n"
     ]
    }
   ],
   "source": [
    "colorspace = 'RGB' # Can be RGB, HSV, LUV, HLS, YUV, YCrCb\n",
    "orient = 9\n",
    "pix_per_cell = 8\n",
    "cell_per_block = 2\n",
    "hog_channel = 0 # Can be 0, 1, 2, or \"ALL\"\n",
    "\n",
    "t=time.time()\n",
    "car_features = extract_features(cars, cspace=colorspace, orient=orient, \n",
    "                        pix_per_cell=pix_per_cell, cell_per_block=cell_per_block, \n",
    "                        hog_channel=hog_channel)\n",
    "notcar_features = extract_features(noncars, cspace=colorspace, orient=orient, \n",
    "                        pix_per_cell=pix_per_cell, cell_per_block=cell_per_block, \n",
    "                        hog_channel=hog_channel)\n",
    "t2 = time.time()\n",
    "print(round(t2-t, 2), 'Seconds to extract HOG features...')\n",
    "# Create an array stack of feature vectors\n",
    "X = np.vstack((car_features, notcar_features)).astype(np.float64)                        \n",
    "# Fit a per-column scaler\n",
    "X_scaler = StandardScaler().fit(X)\n",
    "# Apply the scaler to X\n",
    "scaled_X = X_scaler.transform(X)\n",
    "\n",
    "# Define the labels vector\n",
    "y = np.hstack((np.ones(len(car_features)), np.zeros(len(notcar_features))))\n",
    "\n",
    "\n",
    "# Split up data into randomized training and test sets\n",
    "rand_state = np.random.randint(0, 100)\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    scaled_X, y, test_size=0.2, random_state=rand_state)\n",
    "\n",
    "print('Using:',orient,'orientations',pix_per_cell,\n",
    "    'pixels per cell and', cell_per_block,'cells per block')\n",
    "print('Feature vector length:', len(X_train[0]))\n",
    "# Use a linear SVC \n",
    "svc = LinearSVC(C=1)\n",
    "# Check the training time for the SVC\n",
    "t=time.time()\n",
    "svc.fit(X_train, y_train)\n",
    "t2 = time.time()\n",
    "print(round(t2-t, 2), 'Seconds to train SVC...')\n",
    "# Check the score of the SVC\n",
    "print('Test Accuracy of SVC = ', round(svc.score(X_test, y_test), 4))\n",
    "# Check the prediction time for a single sample\n",
    "t=time.time()\n",
    "n_predict = 10\n",
    "print('My SVC predicts: ', svc.predict(X_test[0:n_predict]))\n",
    "print('For these',n_predict, 'labels: ', y_test[0:n_predict])\n",
    "t2 = time.time()\n",
    "print(round(t2-t, 5), 'Seconds to predict', n_predict,'labels with SVC')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Combination of color based and HOG based feature extraction "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Define a function to compute binned color features  \n",
    "def bin_spatial(img, size=(32, 32)):\n",
    "    # Use cv2.resize().ravel() to create the feature vector\n",
    "    features = cv2.resize(img, size).ravel() \n",
    "    # Return the feature vector\n",
    "    return features\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Define a function to compute color histogram features  \n",
    "def color_hist(img, nbins=32, bins_range=(0, 256)):\n",
    "    # Compute the histogram of the color channels separately\n",
    "    channel1_hist = np.histogram(img[:,:,0], bins=nbins, range=bins_range)\n",
    "    channel2_hist = np.histogram(img[:,:,1], bins=nbins, range=bins_range)\n",
    "    channel3_hist = np.histogram(img[:,:,2], bins=nbins, range=bins_range)\n",
    "    # Concatenate the histograms into a single feature vector\n",
    "    hist_features = np.concatenate((channel1_hist[0], channel2_hist[0], channel3_hist[0]))\n",
    "    # Return the individual histograms, bin_centers and feature vector\n",
    "    return hist_features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Define a function to extract features from a list of images\n",
    "# Have this function call bin_spatial() and color_hist()\n",
    "def extract_features(imgs, cspace='RGB', spatial_size=(32, 32),\n",
    "                        hist_bins=32, hist_range=(0, 256),\n",
    "                        orient=9, pix_per_cell=8, cell_per_block=2, hog_channel='ALL'):\n",
    "    # Create a list to append feature vectors to\n",
    "    features = []\n",
    "    # Iterate through the list of images\n",
    "    for file in imgs:\n",
    "        # Read in each one by one\n",
    "        image = mpimg.imread(file)\n",
    "        # apply color conversion if other than 'RGB'\n",
    "        if cspace != 'RGB':\n",
    "            if cspace == 'HSV':\n",
    "                feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2HSV)\n",
    "            elif cspace == 'LUV':\n",
    "                feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2LUV)\n",
    "            elif cspace == 'HLS':\n",
    "                feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2HLS)\n",
    "            elif cspace == 'YUV':\n",
    "                feature_image = cv2.cvtColor(image, cv2.COLOR_RGB2YUV)\n",
    "        else: feature_image = convert_color(image, conv='RGB2YCrCb')    \n",
    "        # Apply bin_spatial() to get spatial color features\n",
    "        spatial_features = bin_spatial(feature_image, size=spatial_size)\n",
    "        # Apply color_hist() also with a color space option now\n",
    "        hist_features = color_hist(feature_image, nbins=hist_bins, bins_range=hist_range)\n",
    "        # Call get_hog_features() with vis=False, feature_vec=True\n",
    "        if hog_channel == 'ALL':\n",
    "            hog_features = []\n",
    "            for channel in range(feature_image.shape[2]):\n",
    "                hog_features.append(get_hog_features(feature_image[:,:,channel], \n",
    "                                    orient, pix_per_cell, cell_per_block, \n",
    "                                    vis=False, feature_vec=True))\n",
    "            hog_features = np.ravel(hog_features)        \n",
    "        else:\n",
    "            hog_features = get_hog_features(feature_image[:,:,hog_channel], orient, \n",
    "                        pix_per_cell, cell_per_block, vis=False, feature_vec=True)\n",
    "        # Append the new feature vector to the features list\n",
    "        features.append(np.concatenate((spatial_features, hist_features, hog_features)))\n",
    "    # Return list of feature vectors\n",
    "    return features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def convert_color(img, conv='RGB2YCrCb'):\n",
    "    if conv == 'RGB2YCrCb':\n",
    "        return cv2.cvtColor(img, cv2.COLOR_RGB2YCrCb)\n",
    "    if conv == 'BGR2YCrCb':\n",
    "        return cv2.cvtColor(img, cv2.COLOR_BGR2YCrCb)\n",
    "    if conv == 'RGB2LUV':\n",
    "        return cv2.cvtColor(img, cv2.COLOR_RGB2LUV)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Using spatial binning of: 32 and 32 histogram bins\n",
      "Feature vector length: 8460\n",
      "23.83 Seconds to train SVC...\n",
      "Test Accuracy of SVC =  0.9887\n",
      "My SVC predicts:  [ 0.  0.  0.  0.  1.  0.  0.  0.  1.  0.]\n",
      "For these 10 labels:  [ 0.  0.  0.  0.  1.  0.  0.  0.  1.  0.]\n",
      "0.00112 Seconds to predict 10 labels with SVC\n"
     ]
    }
   ],
   "source": [
    "# performs under different binning scenarios\n",
    "spatial = 32\n",
    "histbin = 32\n",
    "\n",
    "car_features = extract_features(cars, cspace='RGB', spatial_size=(spatial, spatial),\n",
    "                        hist_bins=histbin, hist_range=(0, 256))\n",
    "notcar_features = extract_features(noncars, cspace='RGB', spatial_size=(spatial, spatial),\n",
    "                        hist_bins=histbin, hist_range=(0, 256))\n",
    "\n",
    "# Create an array stack of feature vectors\n",
    "X = np.vstack((car_features, notcar_features)).astype(np.float64)                        \n",
    "# Fit a per-column scaler\n",
    "X_scaler = StandardScaler().fit(X)\n",
    "# Apply the scaler to X\n",
    "scaled_X = X_scaler.transform(X)\n",
    "\n",
    "# Define the labels vector\n",
    "y = np.hstack((np.ones(len(car_features)), np.zeros(len(notcar_features))))\n",
    "\n",
    "\n",
    "# Split up data into randomized training and test sets\n",
    "rand_state = np.random.randint(0, 100)\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    scaled_X, y, test_size=0.2, random_state=rand_state)\n",
    "\n",
    "print('Using spatial binning of:',spatial,\n",
    "    'and', histbin,'histogram bins')\n",
    "print('Feature vector length:', len(X_train[0]))\n",
    "# Use a linear SVC \n",
    "svc = LinearSVC(C=0.5)\n",
    "# Check the training time for the SVC\n",
    "t=time.time()\n",
    "svc.fit(X_train, y_train)\n",
    "t2 = time.time()\n",
    "print(round(t2-t, 2), 'Seconds to train SVC...')\n",
    "# Check the score of the SVC\n",
    "print('Test Accuracy of SVC = ', round(svc.score(X_test, y_test), 4))\n",
    "# Check the prediction time for a single sample\n",
    "t=time.time()\n",
    "n_predict = 10\n",
    "print('My SVC predicts: ', svc.predict(X_test[0:n_predict]))\n",
    "print('For these',n_predict, 'labels: ', y_test[0:n_predict])\n",
    "t2 = time.time()\n",
    "print(round(t2-t, 5), 'Seconds to predict', n_predict,'labels with SVC')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Sliding windows Technique ; HOG subsampling "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def draw_boxes(img, bboxes, color=(0, 0, 255), thick=6):\n",
    "    # Make a copy of the image\n",
    "    imcopy = np.copy(img)\n",
    "    # Iterate through the bounding boxes\n",
    "    for bbox in bboxes:\n",
    "        # Draw a rectangle given bbox coordinates\n",
    "        cv2.rectangle(imcopy, bbox[0], bbox[1], color, thick)\n",
    "    # Return the image copy with boxes drawn\n",
    "    return imcopy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "spatial_size=(32, 32)\n",
    "hist_bins = 32\n",
    "\n",
    "# Define a single function that can extract features using hog sub-sampling and make predictions\n",
    "def find_cars(img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell, cell_per_block, spatial_size, hist_bins):\n",
    "    draw_img = np.copy(img)\n",
    "    img = img.astype(np.float32)/255\n",
    "    \n",
    "    img_tosearch = img[ystart:ystop,:,:]\n",
    "    ctrans_tosearch = convert_color(img_tosearch, conv='RGB2YCrCb')\n",
    "    if scale != 1:\n",
    "        imshape = ctrans_tosearch.shape\n",
    "        ctrans_tosearch = cv2.resize(ctrans_tosearch, (np.int(imshape[1]/scale), np.int(imshape[0]/scale)))\n",
    "        \n",
    "    ch1 = ctrans_tosearch[:,:,0]\n",
    "    ch2 = ctrans_tosearch[:,:,1]\n",
    "    ch3 = ctrans_tosearch[:,:,2]\n",
    "\n",
    "    # Define blocks and steps as above\n",
    "    nxblocks = (ch1.shape[1] // pix_per_cell)-1\n",
    "    nyblocks = (ch1.shape[0] // pix_per_cell)-1 \n",
    "    nfeat_per_block = orient*cell_per_block**2\n",
    "    # 64 was the orginal sampling rate, with 8 cells and 8 pix per cell\n",
    "    window = 64\n",
    "    nblocks_per_window = (window // pix_per_cell)-1 \n",
    "    cells_per_step = 2  # Instead of overlap, define how many cells to step\n",
    "    nxsteps = (nxblocks - nblocks_per_window) // cells_per_step\n",
    "    nysteps = (nyblocks - nblocks_per_window) // cells_per_step\n",
    "    \n",
    "    # Compute individual channel HOG features for the entire image\n",
    "    hog1 = get_hog_features(ch1, orient, pix_per_cell, cell_per_block, feature_vec=False)\n",
    "    hog2 = get_hog_features(ch2, orient, pix_per_cell, cell_per_block, feature_vec=False)\n",
    "    hog3 = get_hog_features(ch3, orient, pix_per_cell, cell_per_block, feature_vec=False)\n",
    "    \n",
    "    b_boxes = []\n",
    "\n",
    "    for xb in range(nxsteps):\n",
    "        for yb in range(nysteps):\n",
    "            ypos = yb*cells_per_step\n",
    "            xpos = xb*cells_per_step\n",
    "            # Extract HOG for this patch\n",
    "            hog_feat1 = hog1[ypos:ypos+nblocks_per_window, xpos:xpos+nblocks_per_window].ravel() \n",
    "            hog_feat2 = hog2[ypos:ypos+nblocks_per_window, xpos:xpos+nblocks_per_window].ravel() \n",
    "            hog_feat3 = hog3[ypos:ypos+nblocks_per_window, xpos:xpos+nblocks_per_window].ravel() \n",
    "            hog_features = np.hstack((hog_feat1, hog_feat2, hog_feat3))\n",
    "\n",
    "            xleft = xpos*pix_per_cell\n",
    "            ytop = ypos*pix_per_cell\n",
    "\n",
    "            # Extract the image patch\n",
    "            subimg = cv2.resize(ctrans_tosearch[ytop:ytop+window, xleft:xleft+window], (64,64))\n",
    "          \n",
    "            # Get color features\n",
    "            spatial_features = bin_spatial(subimg, size=spatial_size)\n",
    "            hist_features = color_hist(subimg, nbins=hist_bins)\n",
    "\n",
    "            # Scale features and make a prediction\n",
    "            test_features = X_scaler.transform(np.hstack((spatial_features, hist_features, hog_features)).reshape(1, -1))    \n",
    "            #test_features = X_scaler.transform(np.hstack((shape_feat, hist_feat)).reshape(1, -1))    \n",
    "            test_prediction = svc.predict(test_features)\n",
    "            \n",
    "            if test_prediction == 1:\n",
    "                xbox_left = np.int(xleft*scale)\n",
    "                ytop_draw = np.int(ytop*scale)\n",
    "                win_draw = np.int(window*scale)\n",
    "                b_boxes.append(((xbox_left, ytop_draw+ystart),(xbox_left+win_draw,ytop_draw+win_draw+ystart)))\n",
    "                \n",
    "    return b_boxes\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.image.AxesImage at 0x11d70c320>"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXQAAADdCAYAAACrB4nBAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x11866a5c0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "img = mpimg.imread('test_images/test6.jpg')\n",
    "ystart = 400\n",
    "ystop = 656\n",
    "scale = 1.5\n",
    "    \n",
    "b_boxes = find_cars(img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell, cell_per_block, spatial_size, hist_bins)\n",
    "\n",
    "out_img =  draw_boxes(img, b_boxes)\n",
    "\n",
    "plt.imshow(out_img)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Heatmaps to eliminate false positives"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def add_heat(heatmap, bbox_list):\n",
    "    # Iterate through list of bboxes\n",
    "    for box in bbox_list:\n",
    "        # Add += 1 for all pixels inside each bbox\n",
    "        # Assuming each \"box\" takes the form ((x1, y1), (x2, y2))\n",
    "        heatmap[box[0][1]:box[1][1], box[0][0]:box[1][0]] += 1\n",
    "\n",
    "    # Return updated heatmap\n",
    "    return heatmap"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def apply_threshold(heatmap, threshold):\n",
    "    # Zero out pixels below the threshold\n",
    "    heatmap[heatmap <= threshold] = 0\n",
    "    # Return thresholded map\n",
    "    return heatmap"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def draw_labeled_bboxes(img, labels):\n",
    "    # Iterate through all detected cars\n",
    "    for car_number in range(1, labels[1]+1):\n",
    "        # Find pixels with each car_number label value\n",
    "        nonzero = (labels[0] == car_number).nonzero()\n",
    "        # Identify x and y values of those pixels\n",
    "        nonzeroy = np.array(nonzero[0])\n",
    "        nonzerox = np.array(nonzero[1])\n",
    "        # Define a bounding box based on min/max x and y\n",
    "        bbox = ((np.min(nonzerox), np.min(nonzeroy)), (np.max(nonzerox), np.max(nonzeroy)))\n",
    "        # Draw the box on the image\n",
    "        cv2.rectangle(img, bbox[0], bbox[1], (0,0,255), 6)\n",
    "    # Return the image\n",
    "    return img"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAB2CAYAAAAz69PvAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n/xeVYqyB3CIMrQAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x11866a0b8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAB2CAYAAAAz69PvAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x106e43ef0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAB2CAYAAAAz69PvAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nFotlArGNu8VisUwgtnG3WCyWCeTf5glanbRd7aEAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x11d470c50>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAB2CAYAAAAz69PvAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nDh063IP4/0cdkxlR4EdBAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x11d7c08d0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAB2CAYAAAAz69PvAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x149599550>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAB2CAYAAAAz69PvAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nBkQf3Hv06NHjBkQf3Hv06NHjBsT/B1mSx/iK0zkrAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x14e1cd5c0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "test_images = glob.glob('test_images/*')\n",
    "\n",
    "for image in test_images:\n",
    "    img = mpimg.imread(image)\n",
    "    b_boxes = find_cars(img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell, cell_per_block, spatial_size, hist_bins)\n",
    "\n",
    "    heat = np.zeros_like(img[:,:,0]).astype(np.float)\n",
    "\n",
    "    add_heat(heat, b_boxes)\n",
    "\n",
    "    heat = apply_threshold(heat,1)\n",
    "\n",
    "    heatmap = np.clip(heat, 0, 255)\n",
    "\n",
    "    labels = label(heatmap)\n",
    "    draw_img = draw_labeled_bboxes(np.copy(img), labels)\n",
    "    \n",
    "    plt.figure()\n",
    "    plt.subplot(121)\n",
    "    plt.imshow(heat, cmap='hot')\n",
    "    plt.subplot(122)\n",
    "    plt.imshow(draw_img)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "\n",
    "from collections import deque\n",
    "b_boxes_deque = deque(maxlen=30)\n",
    "\n",
    "def add_heat_video(heatmap, b_boxes_deque):\n",
    "    # Iterate through list of bboxes\n",
    "    for bbox_list in b_boxes_deque:\n",
    "        for box in bbox_list:\n",
    "            # Add += 1 for all pixels inside each bbox\n",
    "            # Assuming each \"box\" takes the form ((x1, y1), (x2, y2))\n",
    "            heatmap[box[0][1]:box[1][1], box[0][0]:box[1][0]] += 1\n",
    "    # Return updated heatmap\n",
    "    return heatmap\n",
    "    \n",
    "def pipeline(img):\n",
    "    b_boxes = find_cars(img, ystart, ystop, scale, svc, X_scaler, orient, pix_per_cell, cell_per_block, spatial_size, hist_bins)\n",
    "    b_boxes_deque.append(b_boxes)\n",
    "    heat = np.zeros_like(img[:,:,0]).astype(np.float)\n",
    "    \n",
    "    add_heat_video(heat, b_boxes_deque)\n",
    "\n",
    "    heat = apply_threshold(heat,15)\n",
    "    \n",
    "    heatmap = np.clip(heat, 0, 255)\n",
    "    labels = label(heatmap)\n",
    "    draw_img = draw_labeled_bboxes(np.copy(img), labels)\n",
    "    return draw_img"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Vehicle detection for test video "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[MoviePy] >>>> Building video projectvideo_output.mp4\n",
      "[MoviePy] Writing video projectvideo_output.mp4\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\n",
      "  0%|          | 0/1261 [00:00<?, ?it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  0%|          | 1/1261 [00:00<05:53,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  0%|          | 2/1261 [00:00<05:47,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  0%|          | 3/1261 [00:00<05:46,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  0%|          | 4/1261 [00:01<05:43,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  0%|          | 5/1261 [00:01<05:40,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  0%|          | 6/1261 [00:01<05:34,  3.75it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  1%|          | 7/1261 [00:01<05:32,  3.77it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  1%|          | 8/1261 [00:02<05:31,  3.78it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  1%|          | 9/1261 [00:02<05:30,  3.79it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  1%|          | 10/1261 [00:02<05:30,  3.79it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  1%|          | 11/1261 [00:02<05:30,  3.78it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  1%|          | 12/1261 [00:03<05:28,  3.80it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  1%|          | 13/1261 [00:03<05:30,  3.77it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  1%|          | 14/1261 [00:03<05:27,  3.80it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  1%|          | 15/1261 [00:03<05:24,  3.83it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  1%|▏         | 16/1261 [00:04<05:25,  3.82it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  1%|▏         | 17/1261 [00:04<05:23,  3.85it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  1%|▏         | 18/1261 [00:04<05:21,  3.87it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  2%|▏         | 19/1261 [00:05<05:23,  3.84it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  2%|▏         | 20/1261 [00:05<05:22,  3.85it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  2%|▏         | 21/1261 [00:05<05:23,  3.84it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  2%|▏         | 22/1261 [00:05<05:21,  3.86it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  2%|▏         | 23/1261 [00:06<05:22,  3.84it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  2%|▏         | 24/1261 [00:06<05:22,  3.83it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  2%|▏         | 25/1261 [00:06<05:26,  3.79it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  2%|▏         | 26/1261 [00:06<05:27,  3.77it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  2%|▏         | 27/1261 [00:07<05:27,  3.76it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  2%|▏         | 28/1261 [00:07<05:30,  3.73it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  2%|▏         | 29/1261 [00:07<05:33,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  2%|▏         | 30/1261 [00:07<05:33,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  2%|▏         | 31/1261 [00:08<05:34,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  3%|▎         | 32/1261 [00:08<05:36,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  3%|▎         | 33/1261 [00:08<05:36,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  3%|▎         | 34/1261 [00:09<05:37,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  3%|▎         | 35/1261 [00:09<05:34,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  3%|▎         | 36/1261 [00:09<05:36,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  3%|▎         | 37/1261 [00:09<05:30,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  3%|▎         | 38/1261 [00:10<05:37,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  3%|▎         | 39/1261 [00:10<07:14,  2.81it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  3%|▎         | 40/1261 [00:11<09:14,  2.20it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  3%|▎         | 41/1261 [00:12<10:52,  1.87it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  3%|▎         | 42/1261 [00:12<09:21,  2.17it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  3%|▎         | 43/1261 [00:12<08:13,  2.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  3%|▎         | 44/1261 [00:12<07:25,  2.73it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  4%|▎         | 45/1261 [00:13<06:51,  2.95it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  4%|▎         | 46/1261 [00:13<06:28,  3.13it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  4%|▎         | 47/1261 [00:13<06:11,  3.27it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  4%|▍         | 48/1261 [00:14<05:59,  3.38it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  4%|▍         | 49/1261 [00:14<05:51,  3.44it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  4%|▍         | 50/1261 [00:14<05:45,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  4%|▍         | 51/1261 [00:14<05:40,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  4%|▍         | 52/1261 [00:15<05:37,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  4%|▍         | 53/1261 [00:15<05:36,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  4%|▍         | 54/1261 [00:15<05:40,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  4%|▍         | 55/1261 [00:15<05:48,  3.46it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  4%|▍         | 56/1261 [00:16<06:02,  3.32it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  5%|▍         | 57/1261 [00:16<05:56,  3.38it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  5%|▍         | 58/1261 [00:16<05:51,  3.43it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  5%|▍         | 59/1261 [00:17<05:44,  3.49it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  5%|▍         | 60/1261 [00:17<05:41,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  5%|▍         | 61/1261 [00:17<05:37,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  5%|▍         | 62/1261 [00:17<05:35,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  5%|▍         | 63/1261 [00:18<05:35,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  5%|▌         | 64/1261 [00:18<05:35,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  5%|▌         | 65/1261 [00:18<05:33,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  5%|▌         | 66/1261 [00:19<05:30,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  5%|▌         | 67/1261 [00:19<05:29,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  5%|▌         | 68/1261 [00:19<05:31,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  5%|▌         | 69/1261 [00:20<06:14,  3.19it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  6%|▌         | 70/1261 [00:20<06:01,  3.30it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  6%|▌         | 71/1261 [00:20<05:51,  3.39it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  6%|▌         | 72/1261 [00:20<05:49,  3.40it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  6%|▌         | 73/1261 [00:21<05:55,  3.34it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  6%|▌         | 74/1261 [00:21<05:49,  3.39it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  6%|▌         | 75/1261 [00:21<05:44,  3.44it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  6%|▌         | 76/1261 [00:22<06:08,  3.21it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  6%|▌         | 77/1261 [00:22<05:55,  3.33it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  6%|▌         | 78/1261 [00:22<05:49,  3.38it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  6%|▋         | 79/1261 [00:22<05:39,  3.49it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  6%|▋         | 80/1261 [00:23<05:29,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  6%|▋         | 81/1261 [00:23<05:24,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  7%|▋         | 82/1261 [00:23<05:29,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  7%|▋         | 83/1261 [00:24<05:28,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  7%|▋         | 84/1261 [00:24<05:33,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  7%|▋         | 85/1261 [00:24<05:41,  3.44it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  7%|▋         | 86/1261 [00:24<05:44,  3.41it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  7%|▋         | 87/1261 [00:25<06:07,  3.20it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  7%|▋         | 88/1261 [00:25<07:05,  2.76it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  7%|▋         | 89/1261 [00:26<07:27,  2.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  7%|▋         | 90/1261 [00:26<06:55,  2.82it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  7%|▋         | 91/1261 [00:26<06:31,  2.99it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  7%|▋         | 92/1261 [00:27<06:11,  3.14it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  7%|▋         | 93/1261 [00:27<05:58,  3.26it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  7%|▋         | 94/1261 [00:27<05:50,  3.33it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  8%|▊         | 95/1261 [00:27<05:57,  3.26it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  8%|▊         | 96/1261 [00:28<05:52,  3.30it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  8%|▊         | 97/1261 [00:28<06:00,  3.23it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  8%|▊         | 98/1261 [00:28<05:59,  3.23it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  8%|▊         | 99/1261 [00:29<05:51,  3.31it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  8%|▊         | 100/1261 [00:29<05:41,  3.40it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  8%|▊         | 101/1261 [00:29<05:28,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  8%|▊         | 102/1261 [00:29<05:22,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  8%|▊         | 103/1261 [00:30<05:24,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  8%|▊         | 104/1261 [00:30<05:29,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  8%|▊         | 105/1261 [00:30<05:23,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  8%|▊         | 106/1261 [00:31<05:18,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  8%|▊         | 107/1261 [00:31<05:17,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  9%|▊         | 108/1261 [00:31<05:17,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  9%|▊         | 109/1261 [00:32<05:47,  3.32it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  9%|▊         | 110/1261 [00:32<05:42,  3.36it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  9%|▉         | 111/1261 [00:32<05:31,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  9%|▉         | 112/1261 [00:32<05:30,  3.48it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  9%|▉         | 113/1261 [00:33<05:23,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  9%|▉         | 114/1261 [00:33<05:19,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  9%|▉         | 115/1261 [00:33<05:25,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  9%|▉         | 116/1261 [00:33<05:19,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  9%|▉         | 117/1261 [00:34<05:58,  3.19it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  9%|▉         | 118/1261 [00:34<05:41,  3.35it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "  9%|▉         | 119/1261 [00:34<05:29,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 10%|▉         | 120/1261 [00:35<05:21,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 10%|▉         | 121/1261 [00:35<05:21,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 10%|▉         | 122/1261 [00:35<05:14,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 10%|▉         | 123/1261 [00:35<05:15,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 10%|▉         | 124/1261 [00:36<05:11,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 10%|▉         | 125/1261 [00:36<05:04,  3.73it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 10%|▉         | 126/1261 [00:36<05:03,  3.73it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 10%|█         | 127/1261 [00:37<05:07,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 10%|█         | 128/1261 [00:37<05:09,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 10%|█         | 129/1261 [00:37<05:10,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 10%|█         | 130/1261 [00:37<05:14,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 10%|█         | 131/1261 [00:38<05:53,  3.20it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 10%|█         | 132/1261 [00:38<05:40,  3.31it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 11%|█         | 133/1261 [00:38<05:33,  3.38it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 11%|█         | 134/1261 [00:39<05:19,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 11%|█         | 135/1261 [00:39<05:15,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 11%|█         | 136/1261 [00:39<05:24,  3.46it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 11%|█         | 137/1261 [00:39<05:13,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 11%|█         | 138/1261 [00:40<05:08,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 11%|█         | 139/1261 [00:40<05:02,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 11%|█         | 140/1261 [00:40<04:59,  3.75it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 11%|█         | 141/1261 [00:40<04:56,  3.77it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 11%|█▏        | 142/1261 [00:41<04:55,  3.78it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 11%|█▏        | 143/1261 [00:41<05:01,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 11%|█▏        | 144/1261 [00:41<05:05,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 11%|█▏        | 145/1261 [00:42<05:04,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 12%|█▏        | 146/1261 [00:42<05:02,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 12%|█▏        | 147/1261 [00:42<05:03,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 12%|█▏        | 148/1261 [00:42<05:07,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 12%|█▏        | 149/1261 [00:43<05:05,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 12%|█▏        | 150/1261 [00:43<05:07,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 12%|█▏        | 151/1261 [00:43<05:01,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 12%|█▏        | 152/1261 [00:43<04:56,  3.74it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 12%|█▏        | 153/1261 [00:44<05:38,  3.28it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 12%|█▏        | 154/1261 [00:44<05:24,  3.41it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 12%|█▏        | 155/1261 [00:44<05:13,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 12%|█▏        | 156/1261 [00:45<05:18,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 12%|█▏        | 157/1261 [00:45<05:11,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 13%|█▎        | 158/1261 [00:45<05:06,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 13%|█▎        | 159/1261 [00:45<05:07,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 13%|█▎        | 160/1261 [00:46<05:03,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 13%|█▎        | 161/1261 [00:46<05:00,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 13%|█▎        | 162/1261 [00:46<04:59,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 13%|█▎        | 163/1261 [00:47<04:59,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 13%|█▎        | 164/1261 [00:47<04:56,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 13%|█▎        | 165/1261 [00:47<04:52,  3.75it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 13%|█▎        | 166/1261 [00:47<04:55,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 13%|█▎        | 167/1261 [00:48<04:57,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 13%|█▎        | 168/1261 [00:48<04:59,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 13%|█▎        | 169/1261 [00:48<05:00,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 13%|█▎        | 170/1261 [00:49<05:07,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 14%|█▎        | 171/1261 [00:49<05:10,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 14%|█▎        | 172/1261 [00:49<05:07,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 14%|█▎        | 173/1261 [00:49<05:05,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 14%|█▍        | 174/1261 [00:50<05:06,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 14%|█▍        | 175/1261 [00:50<05:05,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 14%|█▍        | 176/1261 [00:50<05:05,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 14%|█▍        | 177/1261 [00:50<05:03,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 14%|█▍        | 178/1261 [00:51<05:02,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 14%|█▍        | 179/1261 [00:51<05:02,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 14%|█▍        | 180/1261 [00:51<05:01,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 14%|█▍        | 181/1261 [00:52<05:02,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 14%|█▍        | 182/1261 [00:52<05:00,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 15%|█▍        | 183/1261 [00:52<05:01,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 15%|█▍        | 184/1261 [00:52<05:02,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 15%|█▍        | 185/1261 [00:53<05:00,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 15%|█▍        | 186/1261 [00:53<04:57,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 15%|█▍        | 187/1261 [00:53<05:02,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 15%|█▍        | 188/1261 [00:54<05:09,  3.46it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 15%|█▍        | 189/1261 [00:54<05:15,  3.40it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 15%|█▌        | 190/1261 [00:54<05:13,  3.42it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 15%|█▌        | 191/1261 [00:55<05:53,  3.03it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 15%|█▌        | 192/1261 [00:55<05:43,  3.11it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 15%|█▌        | 193/1261 [00:55<05:31,  3.23it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 15%|█▌        | 194/1261 [00:55<05:22,  3.31it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 15%|█▌        | 195/1261 [00:56<05:15,  3.38it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 16%|█▌        | 196/1261 [00:56<05:13,  3.39it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 16%|█▌        | 197/1261 [00:56<05:28,  3.24it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 16%|█▌        | 198/1261 [00:57<06:21,  2.79it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 16%|█▌        | 199/1261 [00:57<05:56,  2.97it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 16%|█▌        | 200/1261 [00:57<05:42,  3.10it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 16%|█▌        | 201/1261 [00:58<05:29,  3.22it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 16%|█▌        | 202/1261 [00:58<05:18,  3.32it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 16%|█▌        | 203/1261 [00:58<05:08,  3.43it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 16%|█▌        | 204/1261 [00:59<05:00,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 16%|█▋        | 205/1261 [00:59<04:57,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 16%|█▋        | 206/1261 [00:59<04:56,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 16%|█▋        | 207/1261 [00:59<04:53,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 16%|█▋        | 208/1261 [01:00<04:50,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 17%|█▋        | 209/1261 [01:00<04:49,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 17%|█▋        | 210/1261 [01:00<04:44,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 17%|█▋        | 211/1261 [01:00<04:45,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 17%|█▋        | 212/1261 [01:01<04:44,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 17%|█▋        | 213/1261 [01:01<04:42,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 17%|█▋        | 214/1261 [01:01<04:42,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 17%|█▋        | 215/1261 [01:02<04:46,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 17%|█▋        | 216/1261 [01:02<04:49,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 17%|█▋        | 217/1261 [01:02<04:56,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 17%|█▋        | 218/1261 [01:02<04:53,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 17%|█▋        | 219/1261 [01:03<04:59,  3.48it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 17%|█▋        | 220/1261 [01:03<05:01,  3.45it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 18%|█▊        | 221/1261 [01:03<04:59,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 18%|█▊        | 222/1261 [01:04<05:03,  3.43it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 18%|█▊        | 223/1261 [01:04<05:13,  3.31it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 18%|█▊        | 224/1261 [01:04<05:08,  3.36it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 18%|█▊        | 225/1261 [01:04<05:02,  3.42it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 18%|█▊        | 226/1261 [01:05<04:55,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 18%|█▊        | 227/1261 [01:05<04:50,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 18%|█▊        | 228/1261 [01:05<04:48,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 18%|█▊        | 229/1261 [01:06<04:42,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 18%|█▊        | 230/1261 [01:06<04:42,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 18%|█▊        | 231/1261 [01:06<04:43,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 18%|█▊        | 232/1261 [01:06<04:45,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 18%|█▊        | 233/1261 [01:07<04:47,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 19%|█▊        | 234/1261 [01:07<04:45,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 19%|█▊        | 235/1261 [01:07<04:47,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 19%|█▊        | 236/1261 [01:07<04:47,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 19%|█▉        | 237/1261 [01:08<04:42,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 19%|█▉        | 238/1261 [01:08<04:41,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 19%|█▉        | 239/1261 [01:08<04:41,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 19%|█▉        | 240/1261 [01:09<04:39,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 19%|█▉        | 241/1261 [01:09<04:40,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 19%|█▉        | 242/1261 [01:09<04:38,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 19%|█▉        | 243/1261 [01:09<04:36,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 19%|█▉        | 244/1261 [01:10<04:33,  3.72it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 19%|█▉        | 245/1261 [01:10<04:34,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 20%|█▉        | 246/1261 [01:10<04:35,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 20%|█▉        | 247/1261 [01:10<04:41,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 20%|█▉        | 248/1261 [01:11<04:42,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 20%|█▉        | 249/1261 [01:11<04:41,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 20%|█▉        | 250/1261 [01:11<04:38,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 20%|█▉        | 251/1261 [01:12<04:41,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 20%|█▉        | 252/1261 [01:12<04:42,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 20%|██        | 253/1261 [01:12<04:39,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 20%|██        | 254/1261 [01:12<04:36,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 20%|██        | 255/1261 [01:13<04:37,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 20%|██        | 256/1261 [01:13<04:35,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 20%|██        | 257/1261 [01:13<04:31,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 20%|██        | 258/1261 [01:14<04:31,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 21%|██        | 259/1261 [01:14<04:30,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 21%|██        | 260/1261 [01:14<04:58,  3.35it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 21%|██        | 261/1261 [01:14<05:09,  3.23it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 21%|██        | 262/1261 [01:15<05:03,  3.29it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 21%|██        | 263/1261 [01:15<04:55,  3.38it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 21%|██        | 264/1261 [01:15<04:47,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 21%|██        | 265/1261 [01:16<04:45,  3.48it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 21%|██        | 266/1261 [01:16<04:43,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 21%|██        | 267/1261 [01:16<04:43,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 21%|██▏       | 268/1261 [01:16<04:44,  3.49it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 21%|██▏       | 269/1261 [01:17<05:23,  3.07it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 21%|██▏       | 270/1261 [01:17<05:16,  3.13it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 21%|██▏       | 271/1261 [01:18<05:17,  3.12it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 22%|██▏       | 272/1261 [01:18<05:09,  3.19it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 22%|██▏       | 273/1261 [01:18<05:07,  3.22it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 22%|██▏       | 274/1261 [01:18<05:09,  3.19it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 22%|██▏       | 275/1261 [01:19<05:41,  2.89it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 22%|██▏       | 276/1261 [01:19<05:21,  3.06it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 22%|██▏       | 277/1261 [01:19<05:07,  3.20it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 22%|██▏       | 278/1261 [01:20<04:59,  3.29it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 22%|██▏       | 279/1261 [01:20<04:51,  3.36it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 22%|██▏       | 280/1261 [01:20<04:46,  3.42it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 22%|██▏       | 281/1261 [01:21<04:45,  3.44it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 22%|██▏       | 282/1261 [01:21<04:39,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 22%|██▏       | 283/1261 [01:21<04:38,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 23%|██▎       | 284/1261 [01:21<04:35,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 23%|██▎       | 285/1261 [01:22<04:31,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 23%|██▎       | 286/1261 [01:22<04:32,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 23%|██▎       | 287/1261 [01:22<04:32,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 23%|██▎       | 288/1261 [01:22<04:32,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 23%|██▎       | 289/1261 [01:23<04:32,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 23%|██▎       | 290/1261 [01:23<04:33,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 23%|██▎       | 291/1261 [01:23<04:33,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 23%|██▎       | 292/1261 [01:24<04:32,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 23%|██▎       | 293/1261 [01:24<04:34,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 23%|██▎       | 294/1261 [01:24<04:32,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 23%|██▎       | 295/1261 [01:24<04:31,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 23%|██▎       | 296/1261 [01:25<04:30,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 24%|██▎       | 297/1261 [01:25<04:29,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 24%|██▎       | 298/1261 [01:25<04:32,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 24%|██▎       | 299/1261 [01:26<04:31,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 24%|██▍       | 300/1261 [01:26<04:30,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 24%|██▍       | 301/1261 [01:26<04:30,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 24%|██▍       | 302/1261 [01:26<04:29,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 24%|██▍       | 303/1261 [01:27<04:29,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 24%|██▍       | 304/1261 [01:27<04:27,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 24%|██▍       | 305/1261 [01:27<04:28,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 24%|██▍       | 306/1261 [01:28<05:07,  3.10it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 24%|██▍       | 307/1261 [01:28<04:58,  3.19it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 24%|██▍       | 308/1261 [01:28<04:55,  3.22it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 25%|██▍       | 309/1261 [01:29<04:50,  3.28it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 25%|██▍       | 310/1261 [01:29<04:47,  3.31it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 25%|██▍       | 311/1261 [01:29<04:48,  3.29it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 25%|██▍       | 312/1261 [01:29<04:42,  3.36it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 25%|██▍       | 313/1261 [01:30<04:38,  3.40it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 25%|██▍       | 314/1261 [01:30<04:36,  3.42it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 25%|██▍       | 315/1261 [01:30<04:33,  3.46it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 25%|██▌       | 316/1261 [01:31<04:29,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 25%|██▌       | 317/1261 [01:31<04:29,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 25%|██▌       | 318/1261 [01:31<04:27,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 25%|██▌       | 319/1261 [01:31<04:27,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 25%|██▌       | 320/1261 [01:32<04:29,  3.49it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 25%|██▌       | 321/1261 [01:32<04:25,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 26%|██▌       | 322/1261 [01:32<04:58,  3.15it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 26%|██▌       | 323/1261 [01:33<04:45,  3.28it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 26%|██▌       | 324/1261 [01:33<04:41,  3.33it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 26%|██▌       | 325/1261 [01:33<04:33,  3.42it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 26%|██▌       | 326/1261 [01:34<04:29,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 26%|██▌       | 327/1261 [01:34<04:26,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 26%|██▌       | 328/1261 [01:34<04:27,  3.49it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 26%|██▌       | 329/1261 [01:34<04:26,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 26%|██▌       | 330/1261 [01:35<04:24,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 26%|██▌       | 331/1261 [01:35<04:24,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 26%|██▋       | 332/1261 [01:35<04:23,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 26%|██▋       | 333/1261 [01:35<04:18,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 26%|██▋       | 334/1261 [01:36<04:17,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 27%|██▋       | 335/1261 [01:36<04:14,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 27%|██▋       | 336/1261 [01:36<04:15,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 27%|██▋       | 337/1261 [01:37<04:17,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 27%|██▋       | 338/1261 [01:37<04:16,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 27%|██▋       | 339/1261 [01:37<04:17,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 27%|██▋       | 340/1261 [01:37<04:17,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 27%|██▋       | 341/1261 [01:38<04:16,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 27%|██▋       | 342/1261 [01:38<04:16,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 27%|██▋       | 343/1261 [01:38<04:15,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 27%|██▋       | 344/1261 [01:39<04:16,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 27%|██▋       | 345/1261 [01:39<04:18,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 27%|██▋       | 346/1261 [01:39<04:18,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 28%|██▊       | 347/1261 [01:39<04:20,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 28%|██▊       | 348/1261 [01:40<04:20,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 28%|██▊       | 349/1261 [01:40<04:21,  3.48it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 28%|██▊       | 350/1261 [01:40<04:21,  3.48it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 28%|██▊       | 351/1261 [01:41<04:19,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 28%|██▊       | 352/1261 [01:41<04:18,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 28%|██▊       | 353/1261 [01:41<04:17,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 28%|██▊       | 354/1261 [01:42<04:52,  3.10it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 28%|██▊       | 355/1261 [01:42<04:39,  3.24it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 28%|██▊       | 356/1261 [01:42<04:34,  3.30it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 28%|██▊       | 357/1261 [01:42<04:28,  3.37it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 28%|██▊       | 358/1261 [01:43<04:25,  3.40it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 28%|██▊       | 359/1261 [01:43<04:23,  3.42it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 29%|██▊       | 360/1261 [01:43<04:22,  3.44it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 29%|██▊       | 361/1261 [01:44<04:19,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 29%|██▊       | 362/1261 [01:44<04:12,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 29%|██▉       | 363/1261 [01:44<04:11,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 29%|██▉       | 364/1261 [01:44<04:11,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 29%|██▉       | 365/1261 [01:45<04:10,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 29%|██▉       | 366/1261 [01:45<04:09,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 29%|██▉       | 367/1261 [01:45<04:11,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 29%|██▉       | 368/1261 [01:45<04:11,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 29%|██▉       | 369/1261 [01:46<04:11,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 29%|██▉       | 370/1261 [01:46<04:11,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 29%|██▉       | 371/1261 [01:46<04:07,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 30%|██▉       | 372/1261 [01:47<04:06,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 30%|██▉       | 373/1261 [01:47<04:07,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 30%|██▉       | 374/1261 [01:47<04:09,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 30%|██▉       | 375/1261 [01:47<04:08,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 30%|██▉       | 376/1261 [01:48<04:10,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 30%|██▉       | 377/1261 [01:48<04:09,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 30%|██▉       | 378/1261 [01:48<04:07,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 30%|███       | 379/1261 [01:49<04:07,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 30%|███       | 380/1261 [01:49<04:05,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 30%|███       | 381/1261 [01:49<04:04,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 30%|███       | 382/1261 [01:49<04:03,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 30%|███       | 383/1261 [01:50<04:03,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 30%|███       | 384/1261 [01:50<04:02,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 31%|███       | 385/1261 [01:50<04:04,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 31%|███       | 386/1261 [01:51<04:03,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 31%|███       | 387/1261 [01:51<04:01,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 31%|███       | 388/1261 [01:51<03:57,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 31%|███       | 389/1261 [01:51<03:56,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 31%|███       | 390/1261 [01:52<03:55,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 31%|███       | 391/1261 [01:52<03:56,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 31%|███       | 392/1261 [01:52<03:56,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 31%|███       | 393/1261 [01:52<03:56,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 31%|███       | 394/1261 [01:53<03:54,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 31%|███▏      | 395/1261 [01:53<03:57,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 31%|███▏      | 396/1261 [01:53<03:59,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 31%|███▏      | 397/1261 [01:54<03:58,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 32%|███▏      | 398/1261 [01:54<03:56,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 32%|███▏      | 399/1261 [01:54<03:57,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 32%|███▏      | 400/1261 [01:54<03:54,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 32%|███▏      | 401/1261 [01:55<03:55,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 32%|███▏      | 402/1261 [01:55<03:52,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 32%|███▏      | 403/1261 [01:55<03:52,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 32%|███▏      | 404/1261 [01:55<03:52,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 32%|███▏      | 405/1261 [01:56<03:51,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 32%|███▏      | 406/1261 [01:56<03:52,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 32%|███▏      | 407/1261 [01:56<03:50,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 32%|███▏      | 408/1261 [01:56<03:48,  3.73it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 32%|███▏      | 409/1261 [01:57<03:47,  3.75it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 33%|███▎      | 410/1261 [01:57<03:47,  3.75it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 33%|███▎      | 411/1261 [01:57<03:47,  3.74it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 33%|███▎      | 412/1261 [01:58<03:45,  3.77it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 33%|███▎      | 413/1261 [01:58<03:44,  3.78it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 33%|███▎      | 414/1261 [01:58<03:43,  3.79it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 33%|███▎      | 415/1261 [01:58<03:43,  3.79it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 33%|███▎      | 416/1261 [01:59<03:47,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 33%|███▎      | 417/1261 [01:59<03:49,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 33%|███▎      | 418/1261 [01:59<03:51,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 33%|███▎      | 419/1261 [01:59<03:54,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 33%|███▎      | 420/1261 [02:00<03:53,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 33%|███▎      | 421/1261 [02:00<03:53,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 33%|███▎      | 422/1261 [02:00<03:53,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 34%|███▎      | 423/1261 [02:01<03:52,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 34%|███▎      | 424/1261 [02:01<03:52,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 34%|███▎      | 425/1261 [02:01<03:51,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 34%|███▍      | 426/1261 [02:01<03:50,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 34%|███▍      | 427/1261 [02:02<03:49,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 34%|███▍      | 428/1261 [02:02<03:50,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 34%|███▍      | 429/1261 [02:02<03:52,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 34%|███▍      | 430/1261 [02:03<03:54,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 34%|███▍      | 431/1261 [02:03<04:34,  3.02it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 34%|███▍      | 432/1261 [02:03<04:28,  3.09it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 34%|███▍      | 433/1261 [02:04<04:16,  3.22it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 34%|███▍      | 434/1261 [02:04<04:08,  3.33it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 34%|███▍      | 435/1261 [02:04<04:02,  3.40it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 35%|███▍      | 436/1261 [02:04<04:00,  3.44it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 35%|███▍      | 437/1261 [02:05<03:57,  3.48it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 35%|███▍      | 438/1261 [02:05<03:54,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 35%|███▍      | 439/1261 [02:05<03:53,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 35%|███▍      | 440/1261 [02:05<03:49,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 35%|███▍      | 441/1261 [02:06<03:48,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 35%|███▌      | 442/1261 [02:06<03:45,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 35%|███▌      | 443/1261 [02:06<03:47,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 35%|███▌      | 444/1261 [02:07<03:46,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 35%|███▌      | 445/1261 [02:07<03:45,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 35%|███▌      | 446/1261 [02:07<03:45,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 35%|███▌      | 447/1261 [02:07<03:49,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 36%|███▌      | 448/1261 [02:08<03:47,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 36%|███▌      | 449/1261 [02:08<03:47,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 36%|███▌      | 450/1261 [02:08<03:46,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 36%|███▌      | 451/1261 [02:09<03:47,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 36%|███▌      | 452/1261 [02:09<03:46,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 36%|███▌      | 453/1261 [02:09<04:13,  3.19it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 36%|███▌      | 454/1261 [02:10<04:04,  3.30it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 36%|███▌      | 455/1261 [02:10<03:57,  3.39it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 36%|███▌      | 456/1261 [02:10<03:52,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 36%|███▌      | 457/1261 [02:10<03:47,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 36%|███▋      | 458/1261 [02:11<03:46,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 36%|███▋      | 459/1261 [02:11<03:43,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 36%|███▋      | 460/1261 [02:11<03:42,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 37%|███▋      | 461/1261 [02:11<03:39,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 37%|███▋      | 462/1261 [02:12<03:39,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 37%|███▋      | 463/1261 [02:12<03:38,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 37%|███▋      | 464/1261 [02:12<03:37,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 37%|███▋      | 465/1261 [02:13<03:36,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 37%|███▋      | 466/1261 [02:13<03:44,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 37%|███▋      | 467/1261 [02:13<03:43,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 37%|███▋      | 468/1261 [02:13<03:42,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 37%|███▋      | 469/1261 [02:14<03:40,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 37%|███▋      | 470/1261 [02:14<03:37,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 37%|███▋      | 471/1261 [02:14<03:37,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 37%|███▋      | 472/1261 [02:14<03:38,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 38%|███▊      | 473/1261 [02:15<03:38,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 38%|███▊      | 474/1261 [02:15<03:40,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 38%|███▊      | 475/1261 [02:15<03:40,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 38%|███▊      | 476/1261 [02:16<03:39,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 38%|███▊      | 477/1261 [02:16<03:39,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 38%|███▊      | 478/1261 [02:16<03:38,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 38%|███▊      | 479/1261 [02:16<03:37,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 38%|███▊      | 480/1261 [02:17<03:35,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 38%|███▊      | 481/1261 [02:17<03:37,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 38%|███▊      | 482/1261 [02:17<03:37,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 38%|███▊      | 483/1261 [02:18<03:36,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 38%|███▊      | 484/1261 [02:18<03:35,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 38%|███▊      | 485/1261 [02:18<03:36,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 39%|███▊      | 486/1261 [02:18<03:36,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 39%|███▊      | 487/1261 [02:19<03:36,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 39%|███▊      | 488/1261 [02:19<03:35,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 39%|███▉      | 489/1261 [02:19<03:34,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 39%|███▉      | 490/1261 [02:19<03:33,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 39%|███▉      | 491/1261 [02:20<03:33,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 39%|███▉      | 492/1261 [02:20<03:34,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 39%|███▉      | 493/1261 [02:20<03:33,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 39%|███▉      | 494/1261 [02:21<03:33,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 39%|███▉      | 495/1261 [02:21<03:33,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 39%|███▉      | 496/1261 [02:21<03:33,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 39%|███▉      | 497/1261 [02:21<03:33,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 39%|███▉      | 498/1261 [02:22<03:32,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 40%|███▉      | 499/1261 [02:22<03:33,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 40%|███▉      | 500/1261 [02:22<03:32,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 40%|███▉      | 501/1261 [02:23<03:34,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 40%|███▉      | 502/1261 [02:23<03:33,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 40%|███▉      | 503/1261 [02:23<03:32,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 40%|███▉      | 504/1261 [02:23<03:32,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 40%|████      | 505/1261 [02:24<03:29,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 40%|████      | 506/1261 [02:24<03:26,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 40%|████      | 507/1261 [02:24<03:25,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 40%|████      | 508/1261 [02:24<03:25,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 40%|████      | 509/1261 [02:25<03:24,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 40%|████      | 510/1261 [02:25<03:23,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 41%|████      | 511/1261 [02:25<03:23,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 41%|████      | 512/1261 [02:26<03:23,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 41%|████      | 513/1261 [02:26<03:22,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 41%|████      | 514/1261 [02:26<03:22,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 41%|████      | 515/1261 [02:26<03:22,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 41%|████      | 516/1261 [02:27<03:22,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 41%|████      | 517/1261 [02:27<03:24,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 41%|████      | 518/1261 [02:27<03:24,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 41%|████      | 519/1261 [02:28<03:25,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 41%|████      | 520/1261 [02:28<03:24,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 41%|████▏     | 521/1261 [02:28<03:23,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 41%|████▏     | 522/1261 [02:28<03:22,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 41%|████▏     | 523/1261 [02:29<03:21,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 42%|████▏     | 524/1261 [02:29<03:20,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 42%|████▏     | 525/1261 [02:29<03:20,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 42%|████▏     | 526/1261 [02:29<03:19,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 42%|████▏     | 527/1261 [02:30<03:19,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 42%|████▏     | 528/1261 [02:30<03:18,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 42%|████▏     | 529/1261 [02:30<03:18,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 42%|████▏     | 530/1261 [02:30<03:20,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 42%|████▏     | 531/1261 [02:31<03:19,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 42%|████▏     | 532/1261 [02:31<03:18,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 42%|████▏     | 533/1261 [02:31<03:18,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 42%|████▏     | 534/1261 [02:32<03:19,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 42%|████▏     | 535/1261 [02:32<03:19,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 43%|████▎     | 536/1261 [02:32<03:18,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 43%|████▎     | 537/1261 [02:32<03:18,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 43%|████▎     | 538/1261 [02:33<03:18,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 43%|████▎     | 539/1261 [02:33<03:22,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 43%|████▎     | 540/1261 [02:33<03:33,  3.38it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 43%|████▎     | 541/1261 [02:34<03:45,  3.20it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 43%|████▎     | 542/1261 [02:34<03:35,  3.33it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 43%|████▎     | 543/1261 [02:34<03:30,  3.41it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 43%|████▎     | 544/1261 [02:34<03:26,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 43%|████▎     | 545/1261 [02:35<03:24,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 43%|████▎     | 546/1261 [02:35<03:21,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 43%|████▎     | 547/1261 [02:35<03:19,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 43%|████▎     | 548/1261 [02:36<03:18,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 44%|████▎     | 549/1261 [02:36<03:17,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 44%|████▎     | 550/1261 [02:36<03:15,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 44%|████▎     | 551/1261 [02:36<03:15,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 44%|████▍     | 552/1261 [02:37<03:15,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 44%|████▍     | 553/1261 [02:37<03:16,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 44%|████▍     | 554/1261 [02:37<03:18,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 44%|████▍     | 555/1261 [02:38<03:18,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 44%|████▍     | 556/1261 [02:38<03:17,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 44%|████▍     | 557/1261 [02:38<03:16,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 44%|████▍     | 558/1261 [02:38<03:15,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 44%|████▍     | 559/1261 [02:39<03:12,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 44%|████▍     | 560/1261 [02:39<03:11,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 44%|████▍     | 561/1261 [02:39<03:12,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 45%|████▍     | 562/1261 [02:39<03:11,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 45%|████▍     | 563/1261 [02:40<03:11,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 45%|████▍     | 564/1261 [02:40<03:10,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 45%|████▍     | 565/1261 [02:40<03:09,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 45%|████▍     | 566/1261 [02:41<03:09,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 45%|████▍     | 567/1261 [02:41<03:10,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 45%|████▌     | 568/1261 [02:41<03:11,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 45%|████▌     | 569/1261 [02:41<03:10,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 45%|████▌     | 570/1261 [02:42<03:09,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 45%|████▌     | 571/1261 [02:42<03:09,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 45%|████▌     | 572/1261 [02:42<03:10,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 45%|████▌     | 573/1261 [02:42<03:08,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 46%|████▌     | 574/1261 [02:43<03:07,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 46%|████▌     | 575/1261 [02:43<03:07,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 46%|████▌     | 576/1261 [02:43<03:06,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 46%|████▌     | 577/1261 [02:44<03:05,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 46%|████▌     | 578/1261 [02:44<03:07,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 46%|████▌     | 579/1261 [02:44<03:08,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 46%|████▌     | 580/1261 [02:44<03:10,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 46%|████▌     | 581/1261 [02:45<03:08,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 46%|████▌     | 582/1261 [02:45<03:08,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 46%|████▌     | 583/1261 [02:45<03:07,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 46%|████▋     | 584/1261 [02:46<03:08,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 46%|████▋     | 585/1261 [02:46<03:06,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 46%|████▋     | 586/1261 [02:46<03:05,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 47%|████▋     | 587/1261 [02:46<03:05,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 47%|████▋     | 588/1261 [02:47<03:03,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 47%|████▋     | 589/1261 [02:47<03:03,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 47%|████▋     | 590/1261 [02:47<03:03,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 47%|████▋     | 591/1261 [02:47<03:02,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 47%|████▋     | 592/1261 [02:48<03:04,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 47%|████▋     | 593/1261 [02:48<03:03,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 47%|████▋     | 594/1261 [02:48<03:03,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 47%|████▋     | 595/1261 [02:49<03:02,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 47%|████▋     | 596/1261 [02:49<03:01,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 47%|████▋     | 597/1261 [02:49<03:00,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 47%|████▋     | 598/1261 [02:49<03:01,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 48%|████▊     | 599/1261 [02:50<03:01,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 48%|████▊     | 600/1261 [02:50<03:01,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 48%|████▊     | 601/1261 [02:50<03:00,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 48%|████▊     | 602/1261 [02:50<02:59,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 48%|████▊     | 603/1261 [02:51<02:59,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 48%|████▊     | 604/1261 [02:51<02:59,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 48%|████▊     | 605/1261 [02:51<03:00,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 48%|████▊     | 606/1261 [02:52<02:58,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 48%|████▊     | 607/1261 [02:52<02:58,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 48%|████▊     | 608/1261 [02:52<02:57,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 48%|████▊     | 609/1261 [02:52<02:58,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 48%|████▊     | 610/1261 [02:53<02:59,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 48%|████▊     | 611/1261 [02:53<03:00,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 49%|████▊     | 612/1261 [02:53<02:59,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 49%|████▊     | 613/1261 [02:53<02:59,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 49%|████▊     | 614/1261 [02:54<02:58,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 49%|████▉     | 615/1261 [02:54<02:56,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 49%|████▉     | 616/1261 [02:54<02:56,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 49%|████▉     | 617/1261 [02:55<02:57,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 49%|████▉     | 618/1261 [02:55<02:55,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 49%|████▉     | 619/1261 [02:55<02:54,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 49%|████▉     | 620/1261 [02:55<02:54,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 49%|████▉     | 621/1261 [02:56<02:56,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 49%|████▉     | 622/1261 [02:56<02:54,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 49%|████▉     | 623/1261 [02:56<02:53,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 49%|████▉     | 624/1261 [02:56<03:01,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 50%|████▉     | 625/1261 [02:57<02:57,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 50%|████▉     | 626/1261 [02:57<02:55,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 50%|████▉     | 627/1261 [02:57<02:54,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 50%|████▉     | 628/1261 [02:58<02:52,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 50%|████▉     | 629/1261 [02:58<02:50,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 50%|████▉     | 630/1261 [02:58<02:50,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 50%|█████     | 631/1261 [02:58<02:50,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 50%|█████     | 632/1261 [02:59<02:48,  3.72it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 50%|█████     | 633/1261 [02:59<02:49,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 50%|█████     | 634/1261 [02:59<02:49,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 50%|█████     | 635/1261 [02:59<02:48,  3.72it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 50%|█████     | 636/1261 [03:00<02:48,  3.72it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 51%|█████     | 637/1261 [03:00<02:47,  3.73it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 51%|█████     | 638/1261 [03:00<02:46,  3.74it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 51%|█████     | 639/1261 [03:01<02:46,  3.74it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 51%|█████     | 640/1261 [03:01<02:46,  3.74it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 51%|█████     | 641/1261 [03:01<02:47,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 51%|█████     | 642/1261 [03:01<02:46,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 51%|█████     | 643/1261 [03:02<02:45,  3.72it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 51%|█████     | 644/1261 [03:02<02:44,  3.75it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 51%|█████     | 645/1261 [03:02<02:44,  3.75it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 51%|█████     | 646/1261 [03:02<02:46,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 51%|█████▏    | 647/1261 [03:03<02:48,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 51%|█████▏    | 648/1261 [03:03<02:49,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 51%|█████▏    | 649/1261 [03:03<02:49,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 52%|█████▏    | 650/1261 [03:04<02:49,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 52%|█████▏    | 651/1261 [03:04<02:49,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 52%|█████▏    | 652/1261 [03:04<02:48,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 52%|█████▏    | 653/1261 [03:04<02:48,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 52%|█████▏    | 654/1261 [03:05<02:48,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 52%|█████▏    | 655/1261 [03:05<02:47,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 52%|█████▏    | 656/1261 [03:05<02:47,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 52%|█████▏    | 657/1261 [03:05<02:49,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 52%|█████▏    | 658/1261 [03:06<02:48,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 52%|█████▏    | 659/1261 [03:06<02:47,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 52%|█████▏    | 660/1261 [03:06<02:46,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 52%|█████▏    | 661/1261 [03:07<02:45,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 52%|█████▏    | 662/1261 [03:07<02:46,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 53%|█████▎    | 663/1261 [03:07<02:45,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 53%|█████▎    | 664/1261 [03:07<02:46,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 53%|█████▎    | 665/1261 [03:08<02:45,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 53%|█████▎    | 666/1261 [03:08<02:45,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 53%|█████▎    | 667/1261 [03:08<02:44,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 53%|█████▎    | 668/1261 [03:09<02:43,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 53%|█████▎    | 669/1261 [03:09<02:43,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 53%|█████▎    | 670/1261 [03:09<02:42,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 53%|█████▎    | 671/1261 [03:09<02:41,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 53%|█████▎    | 672/1261 [03:10<02:40,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 53%|█████▎    | 673/1261 [03:10<02:40,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 53%|█████▎    | 674/1261 [03:10<02:40,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 54%|█████▎    | 675/1261 [03:10<02:40,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 54%|█████▎    | 676/1261 [03:11<02:41,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 54%|█████▎    | 677/1261 [03:11<03:03,  3.18it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 54%|█████▍    | 678/1261 [03:11<02:56,  3.30it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 54%|█████▍    | 679/1261 [03:12<02:50,  3.41it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 54%|█████▍    | 680/1261 [03:12<02:46,  3.49it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 54%|█████▍    | 681/1261 [03:12<02:43,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 54%|█████▍    | 682/1261 [03:13<02:44,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 54%|█████▍    | 683/1261 [03:13<02:44,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 54%|█████▍    | 684/1261 [03:13<03:04,  3.12it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 54%|█████▍    | 685/1261 [03:13<02:57,  3.24it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 54%|█████▍    | 686/1261 [03:14<02:55,  3.28it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 54%|█████▍    | 687/1261 [03:14<02:51,  3.35it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 55%|█████▍    | 688/1261 [03:14<02:48,  3.40it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 55%|█████▍    | 689/1261 [03:15<02:49,  3.38it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 55%|█████▍    | 690/1261 [03:15<02:45,  3.44it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 55%|█████▍    | 691/1261 [03:15<02:43,  3.48it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 55%|█████▍    | 692/1261 [03:16<02:46,  3.42it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 55%|█████▍    | 693/1261 [03:16<02:47,  3.39it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 55%|█████▌    | 694/1261 [03:16<02:49,  3.35it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 55%|█████▌    | 695/1261 [03:16<02:46,  3.41it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 55%|█████▌    | 696/1261 [03:17<02:46,  3.39it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 55%|█████▌    | 697/1261 [03:17<02:46,  3.38it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 55%|█████▌    | 698/1261 [03:17<02:49,  3.31it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 55%|█████▌    | 699/1261 [03:18<02:48,  3.34it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 56%|█████▌    | 700/1261 [03:18<02:46,  3.37it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 56%|█████▌    | 701/1261 [03:18<02:43,  3.42it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 56%|█████▌    | 702/1261 [03:18<02:43,  3.43it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 56%|█████▌    | 703/1261 [03:19<02:42,  3.44it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 56%|█████▌    | 704/1261 [03:19<03:02,  3.06it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 56%|█████▌    | 705/1261 [03:19<02:55,  3.17it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 56%|█████▌    | 706/1261 [03:20<02:51,  3.25it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 56%|█████▌    | 707/1261 [03:20<02:47,  3.31it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 56%|█████▌    | 708/1261 [03:20<02:45,  3.35it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 56%|█████▌    | 709/1261 [03:21<02:43,  3.37it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 56%|█████▋    | 710/1261 [03:21<02:43,  3.36it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 56%|█████▋    | 711/1261 [03:21<02:41,  3.41it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 56%|█████▋    | 712/1261 [03:21<02:40,  3.42it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 57%|█████▋    | 713/1261 [03:22<02:39,  3.44it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 57%|█████▋    | 714/1261 [03:22<02:39,  3.42it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 57%|█████▋    | 715/1261 [03:22<02:38,  3.45it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 57%|█████▋    | 716/1261 [03:23<02:36,  3.49it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 57%|█████▋    | 717/1261 [03:23<02:34,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 57%|█████▋    | 718/1261 [03:23<02:31,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 57%|█████▋    | 719/1261 [03:23<02:30,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 57%|█████▋    | 720/1261 [03:24<02:29,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 57%|█████▋    | 721/1261 [03:24<02:29,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 57%|█████▋    | 722/1261 [03:24<02:29,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 57%|█████▋    | 723/1261 [03:25<02:28,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 57%|█████▋    | 724/1261 [03:25<02:29,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 57%|█████▋    | 725/1261 [03:25<02:27,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 58%|█████▊    | 726/1261 [03:25<02:27,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 58%|█████▊    | 727/1261 [03:26<02:27,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 58%|█████▊    | 728/1261 [03:26<02:27,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 58%|█████▊    | 729/1261 [03:26<02:27,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 58%|█████▊    | 730/1261 [03:26<02:27,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 58%|█████▊    | 731/1261 [03:27<02:26,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 58%|█████▊    | 732/1261 [03:27<02:26,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 58%|█████▊    | 733/1261 [03:27<02:25,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 58%|█████▊    | 734/1261 [03:28<02:27,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 58%|█████▊    | 735/1261 [03:28<02:32,  3.45it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 58%|█████▊    | 736/1261 [03:28<02:31,  3.46it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 58%|█████▊    | 737/1261 [03:28<02:30,  3.48it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 59%|█████▊    | 738/1261 [03:29<02:29,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 59%|█████▊    | 739/1261 [03:29<02:28,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 59%|█████▊    | 740/1261 [03:29<02:26,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 59%|█████▉    | 741/1261 [03:30<02:26,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 59%|█████▉    | 742/1261 [03:30<02:27,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 59%|█████▉    | 743/1261 [03:30<02:26,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 59%|█████▉    | 744/1261 [03:30<02:25,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 59%|█████▉    | 745/1261 [03:31<02:25,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 59%|█████▉    | 746/1261 [03:31<02:30,  3.41it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 59%|█████▉    | 747/1261 [03:31<02:41,  3.19it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 59%|█████▉    | 748/1261 [03:32<02:36,  3.28it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 59%|█████▉    | 749/1261 [03:32<02:31,  3.38it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 59%|█████▉    | 750/1261 [03:32<02:32,  3.35it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 60%|█████▉    | 751/1261 [03:33<02:45,  3.09it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 60%|█████▉    | 752/1261 [03:33<02:40,  3.17it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 60%|█████▉    | 753/1261 [03:33<02:35,  3.27it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 60%|█████▉    | 754/1261 [03:34<02:30,  3.37it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 60%|█████▉    | 755/1261 [03:34<02:28,  3.42it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 60%|█████▉    | 756/1261 [03:34<02:26,  3.45it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 60%|██████    | 757/1261 [03:34<02:24,  3.49it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 60%|██████    | 758/1261 [03:35<02:23,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 60%|██████    | 759/1261 [03:35<02:22,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 60%|██████    | 760/1261 [03:35<02:21,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 60%|██████    | 761/1261 [03:35<02:20,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 60%|██████    | 762/1261 [03:36<02:20,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 61%|██████    | 763/1261 [03:36<02:20,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 61%|██████    | 764/1261 [03:36<02:19,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 61%|██████    | 765/1261 [03:37<02:19,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 61%|██████    | 766/1261 [03:37<02:19,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 61%|██████    | 767/1261 [03:37<02:20,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 61%|██████    | 768/1261 [03:37<02:19,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 61%|██████    | 769/1261 [03:38<02:18,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 61%|██████    | 770/1261 [03:38<02:19,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 61%|██████    | 771/1261 [03:38<02:17,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 61%|██████    | 772/1261 [03:39<02:18,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 61%|██████▏   | 773/1261 [03:39<02:18,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 61%|██████▏   | 774/1261 [03:39<02:24,  3.37it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 61%|██████▏   | 775/1261 [03:40<02:33,  3.16it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 62%|██████▏   | 776/1261 [03:40<02:28,  3.26it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 62%|██████▏   | 777/1261 [03:40<02:23,  3.37it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 62%|██████▏   | 778/1261 [03:40<02:21,  3.40it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 62%|██████▏   | 779/1261 [03:41<02:20,  3.44it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 62%|██████▏   | 780/1261 [03:41<02:23,  3.35it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 62%|██████▏   | 781/1261 [03:41<02:33,  3.13it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 62%|██████▏   | 782/1261 [03:42<02:26,  3.27it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 62%|██████▏   | 783/1261 [03:42<02:21,  3.38it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 62%|██████▏   | 784/1261 [03:42<02:17,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 62%|██████▏   | 785/1261 [03:42<02:16,  3.49it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 62%|██████▏   | 786/1261 [03:43<02:14,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 62%|██████▏   | 787/1261 [03:43<02:13,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 62%|██████▏   | 788/1261 [03:43<02:13,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 63%|██████▎   | 789/1261 [03:44<02:12,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 63%|██████▎   | 790/1261 [03:44<02:11,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 63%|██████▎   | 791/1261 [03:44<02:11,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 63%|██████▎   | 792/1261 [03:44<02:10,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 63%|██████▎   | 793/1261 [03:45<02:10,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 63%|██████▎   | 794/1261 [03:45<02:09,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 63%|██████▎   | 795/1261 [03:45<02:10,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 63%|██████▎   | 796/1261 [03:46<02:10,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 63%|██████▎   | 797/1261 [03:46<02:09,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 63%|██████▎   | 798/1261 [03:46<02:08,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 63%|██████▎   | 799/1261 [03:46<02:07,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 63%|██████▎   | 800/1261 [03:47<02:07,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 64%|██████▎   | 801/1261 [03:47<02:07,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 64%|██████▎   | 802/1261 [03:47<02:07,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 64%|██████▎   | 803/1261 [03:47<02:07,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 64%|██████▍   | 804/1261 [03:48<02:06,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 64%|██████▍   | 805/1261 [03:48<02:06,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 64%|██████▍   | 806/1261 [03:48<02:05,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 64%|██████▍   | 807/1261 [03:49<02:05,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 64%|██████▍   | 808/1261 [03:49<02:05,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 64%|██████▍   | 809/1261 [03:49<02:04,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 64%|██████▍   | 810/1261 [03:49<02:04,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 64%|██████▍   | 811/1261 [03:50<02:04,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 64%|██████▍   | 812/1261 [03:50<02:04,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 64%|██████▍   | 813/1261 [03:50<02:03,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 65%|██████▍   | 814/1261 [03:51<02:03,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 65%|██████▍   | 815/1261 [03:51<02:02,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 65%|██████▍   | 816/1261 [03:51<02:02,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 65%|██████▍   | 817/1261 [03:51<02:02,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 65%|██████▍   | 818/1261 [03:52<02:01,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 65%|██████▍   | 819/1261 [03:52<02:01,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 65%|██████▌   | 820/1261 [03:52<02:02,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 65%|██████▌   | 821/1261 [03:52<02:00,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 65%|██████▌   | 822/1261 [03:53<02:00,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 65%|██████▌   | 823/1261 [03:53<02:01,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 65%|██████▌   | 824/1261 [03:53<02:00,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 65%|██████▌   | 825/1261 [03:54<02:01,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 66%|██████▌   | 826/1261 [03:54<02:01,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 66%|██████▌   | 827/1261 [03:54<02:00,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 66%|██████▌   | 828/1261 [03:54<02:00,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 66%|██████▌   | 829/1261 [03:55<02:00,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 66%|██████▌   | 830/1261 [03:55<01:59,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 66%|██████▌   | 831/1261 [03:55<01:58,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 66%|██████▌   | 832/1261 [03:55<01:58,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 66%|██████▌   | 833/1261 [03:56<01:58,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 66%|██████▌   | 834/1261 [03:56<01:57,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 66%|██████▌   | 835/1261 [03:56<01:57,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 66%|██████▋   | 836/1261 [03:57<01:56,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 66%|██████▋   | 837/1261 [03:57<01:57,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 66%|██████▋   | 838/1261 [03:57<01:57,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 67%|██████▋   | 839/1261 [03:57<01:56,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 67%|██████▋   | 840/1261 [03:58<01:56,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 67%|██████▋   | 841/1261 [03:58<01:55,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 67%|██████▋   | 842/1261 [03:58<01:54,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 67%|██████▋   | 843/1261 [03:59<01:54,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 67%|██████▋   | 844/1261 [03:59<01:54,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 67%|██████▋   | 845/1261 [03:59<01:55,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 67%|██████▋   | 846/1261 [03:59<01:55,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 67%|██████▋   | 847/1261 [04:00<01:55,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 67%|██████▋   | 848/1261 [04:00<01:55,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 67%|██████▋   | 849/1261 [04:00<01:54,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 67%|██████▋   | 850/1261 [04:00<01:55,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 67%|██████▋   | 851/1261 [04:01<01:55,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 68%|██████▊   | 852/1261 [04:01<01:55,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 68%|██████▊   | 853/1261 [04:01<01:56,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 68%|██████▊   | 854/1261 [04:02<01:55,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 68%|██████▊   | 855/1261 [04:02<01:55,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 68%|██████▊   | 856/1261 [04:02<01:55,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 68%|██████▊   | 857/1261 [04:02<01:55,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 68%|██████▊   | 858/1261 [04:03<01:53,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 68%|██████▊   | 859/1261 [04:03<01:53,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 68%|██████▊   | 860/1261 [04:03<01:52,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 68%|██████▊   | 861/1261 [04:04<01:51,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 68%|██████▊   | 862/1261 [04:04<01:51,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 68%|██████▊   | 863/1261 [04:04<01:50,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 69%|██████▊   | 864/1261 [04:04<01:49,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 69%|██████▊   | 865/1261 [04:05<01:49,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 69%|██████▊   | 866/1261 [04:05<01:49,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 69%|██████▉   | 867/1261 [04:05<01:48,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 69%|██████▉   | 868/1261 [04:06<01:48,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 69%|██████▉   | 869/1261 [04:06<01:47,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 69%|██████▉   | 870/1261 [04:06<01:48,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 69%|██████▉   | 871/1261 [04:06<01:47,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 69%|██████▉   | 872/1261 [04:07<01:51,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 69%|██████▉   | 873/1261 [04:07<02:01,  3.19it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 69%|██████▉   | 874/1261 [04:07<02:08,  3.00it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 69%|██████▉   | 875/1261 [04:08<02:02,  3.15it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 69%|██████▉   | 876/1261 [04:08<01:59,  3.23it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 70%|██████▉   | 877/1261 [04:08<01:56,  3.31it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 70%|██████▉   | 878/1261 [04:09<01:54,  3.35it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 70%|██████▉   | 879/1261 [04:09<01:52,  3.39it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 70%|██████▉   | 880/1261 [04:09<01:49,  3.48it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 70%|██████▉   | 881/1261 [04:09<01:48,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 70%|██████▉   | 882/1261 [04:10<01:46,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 70%|███████   | 883/1261 [04:10<01:45,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 70%|███████   | 884/1261 [04:10<01:44,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 70%|███████   | 885/1261 [04:10<01:43,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 70%|███████   | 886/1261 [04:11<01:42,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 70%|███████   | 887/1261 [04:11<01:43,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 70%|███████   | 888/1261 [04:11<01:42,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 70%|███████   | 889/1261 [04:12<01:42,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 71%|███████   | 890/1261 [04:12<01:42,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 71%|███████   | 891/1261 [04:12<01:41,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 71%|███████   | 892/1261 [04:12<01:40,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 71%|███████   | 893/1261 [04:13<01:40,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 71%|███████   | 894/1261 [04:13<01:40,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 71%|███████   | 895/1261 [04:13<01:39,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 71%|███████   | 896/1261 [04:13<01:39,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 71%|███████   | 897/1261 [04:14<01:39,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 71%|███████   | 898/1261 [04:14<01:39,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 71%|███████▏  | 899/1261 [04:14<01:39,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 71%|███████▏  | 900/1261 [04:15<01:39,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 71%|███████▏  | 901/1261 [04:15<01:38,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 72%|███████▏  | 902/1261 [04:15<01:38,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 72%|███████▏  | 903/1261 [04:15<01:38,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 72%|███████▏  | 904/1261 [04:16<01:38,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 72%|███████▏  | 905/1261 [04:16<01:38,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 72%|███████▏  | 906/1261 [04:16<01:37,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 72%|███████▏  | 907/1261 [04:17<01:37,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 72%|███████▏  | 908/1261 [04:17<01:36,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 72%|███████▏  | 909/1261 [04:17<01:36,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 72%|███████▏  | 910/1261 [04:17<01:36,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 72%|███████▏  | 911/1261 [04:18<01:36,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 72%|███████▏  | 912/1261 [04:18<01:36,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 72%|███████▏  | 913/1261 [04:18<01:36,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 72%|███████▏  | 914/1261 [04:18<01:35,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 73%|███████▎  | 915/1261 [04:19<01:34,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 73%|███████▎  | 916/1261 [04:19<01:34,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 73%|███████▎  | 917/1261 [04:19<01:34,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 73%|███████▎  | 918/1261 [04:20<01:34,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 73%|███████▎  | 919/1261 [04:20<01:33,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 73%|███████▎  | 920/1261 [04:20<01:33,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 73%|███████▎  | 921/1261 [04:20<01:33,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 73%|███████▎  | 922/1261 [04:21<01:32,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 73%|███████▎  | 923/1261 [04:21<01:31,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 73%|███████▎  | 924/1261 [04:21<01:31,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 73%|███████▎  | 925/1261 [04:21<01:31,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 73%|███████▎  | 926/1261 [04:22<01:31,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 74%|███████▎  | 927/1261 [04:22<01:31,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 74%|███████▎  | 928/1261 [04:22<01:44,  3.20it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 74%|███████▎  | 929/1261 [04:23<01:39,  3.33it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 74%|███████▍  | 930/1261 [04:23<01:36,  3.41it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 74%|███████▍  | 931/1261 [04:23<01:35,  3.45it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 74%|███████▍  | 932/1261 [04:24<01:33,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 74%|███████▍  | 933/1261 [04:24<01:31,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 74%|███████▍  | 934/1261 [04:24<01:31,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 74%|███████▍  | 935/1261 [04:24<01:30,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 74%|███████▍  | 936/1261 [04:25<01:30,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 74%|███████▍  | 937/1261 [04:25<01:29,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 74%|███████▍  | 938/1261 [04:25<01:29,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 74%|███████▍  | 939/1261 [04:25<01:29,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 75%|███████▍  | 940/1261 [04:26<01:28,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 75%|███████▍  | 941/1261 [04:26<01:27,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 75%|███████▍  | 942/1261 [04:26<01:27,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 75%|███████▍  | 943/1261 [04:27<01:27,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 75%|███████▍  | 944/1261 [04:27<01:27,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 75%|███████▍  | 945/1261 [04:27<01:27,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 75%|███████▌  | 946/1261 [04:27<01:27,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 75%|███████▌  | 947/1261 [04:28<01:27,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 75%|███████▌  | 948/1261 [04:28<01:26,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 75%|███████▌  | 949/1261 [04:28<01:26,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 75%|███████▌  | 950/1261 [04:28<01:26,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 75%|███████▌  | 951/1261 [04:29<01:25,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 75%|███████▌  | 952/1261 [04:29<01:25,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 76%|███████▌  | 953/1261 [04:29<01:25,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 76%|███████▌  | 954/1261 [04:30<01:24,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 76%|███████▌  | 955/1261 [04:30<01:24,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 76%|███████▌  | 956/1261 [04:30<01:24,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 76%|███████▌  | 957/1261 [04:30<01:24,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 76%|███████▌  | 958/1261 [04:31<01:23,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 76%|███████▌  | 959/1261 [04:31<01:23,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 76%|███████▌  | 960/1261 [04:31<01:23,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 76%|███████▌  | 961/1261 [04:32<01:23,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 76%|███████▋  | 962/1261 [04:32<01:23,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 76%|███████▋  | 963/1261 [04:32<01:24,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 76%|███████▋  | 964/1261 [04:32<01:24,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 77%|███████▋  | 965/1261 [04:33<01:24,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 77%|███████▋  | 966/1261 [04:33<01:24,  3.49it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 77%|███████▋  | 967/1261 [04:33<01:23,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 77%|███████▋  | 968/1261 [04:34<01:24,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 77%|███████▋  | 969/1261 [04:34<01:24,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 77%|███████▋  | 970/1261 [04:34<01:24,  3.46it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 77%|███████▋  | 971/1261 [04:34<01:23,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 77%|███████▋  | 972/1261 [04:35<01:23,  3.46it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 77%|███████▋  | 973/1261 [04:35<01:23,  3.45it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 77%|███████▋  | 974/1261 [04:35<01:22,  3.48it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 77%|███████▋  | 975/1261 [04:36<01:22,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 77%|███████▋  | 976/1261 [04:36<01:22,  3.48it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 77%|███████▋  | 977/1261 [04:36<01:21,  3.49it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 78%|███████▊  | 978/1261 [04:36<01:21,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 78%|███████▊  | 979/1261 [04:37<01:20,  3.49it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 78%|███████▊  | 980/1261 [04:37<01:20,  3.49it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 78%|███████▊  | 981/1261 [04:37<01:19,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 78%|███████▊  | 982/1261 [04:38<01:19,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 78%|███████▊  | 983/1261 [04:38<01:19,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 78%|███████▊  | 984/1261 [04:38<01:19,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 78%|███████▊  | 985/1261 [04:38<01:18,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 78%|███████▊  | 986/1261 [04:39<01:18,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 78%|███████▊  | 987/1261 [04:39<01:17,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 78%|███████▊  | 988/1261 [04:39<01:16,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 78%|███████▊  | 989/1261 [04:40<01:16,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 79%|███████▊  | 990/1261 [04:40<01:15,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 79%|███████▊  | 991/1261 [04:40<01:15,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 79%|███████▊  | 992/1261 [04:40<01:15,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 79%|███████▊  | 993/1261 [04:41<01:15,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 79%|███████▉  | 994/1261 [04:41<01:15,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 79%|███████▉  | 995/1261 [04:41<01:15,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 79%|███████▉  | 996/1261 [04:42<01:15,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 79%|███████▉  | 997/1261 [04:42<01:15,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 79%|███████▉  | 998/1261 [04:42<01:15,  3.48it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 79%|███████▉  | 999/1261 [04:42<01:15,  3.49it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 79%|███████▉  | 1000/1261 [04:43<01:15,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 79%|███████▉  | 1001/1261 [04:43<01:15,  3.46it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 79%|███████▉  | 1002/1261 [04:43<01:14,  3.49it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 80%|███████▉  | 1003/1261 [04:44<01:13,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 80%|███████▉  | 1004/1261 [04:44<01:15,  3.42it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 80%|███████▉  | 1005/1261 [04:44<01:13,  3.46it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 80%|███████▉  | 1006/1261 [04:44<01:13,  3.48it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 80%|███████▉  | 1007/1261 [04:45<01:13,  3.48it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 80%|███████▉  | 1008/1261 [04:45<01:12,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 80%|████████  | 1009/1261 [04:45<01:11,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 80%|████████  | 1010/1261 [04:46<01:11,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 80%|████████  | 1011/1261 [04:46<01:10,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 80%|████████  | 1012/1261 [04:46<01:10,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 80%|████████  | 1013/1261 [04:46<01:10,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 80%|████████  | 1014/1261 [04:47<01:09,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 80%|████████  | 1015/1261 [04:47<01:09,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 81%|████████  | 1016/1261 [04:47<01:08,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 81%|████████  | 1017/1261 [04:47<01:07,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 81%|████████  | 1018/1261 [04:48<01:07,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 81%|████████  | 1019/1261 [04:48<01:07,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 81%|████████  | 1020/1261 [04:48<01:06,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 81%|████████  | 1021/1261 [04:49<01:06,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 81%|████████  | 1022/1261 [04:49<01:05,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 81%|████████  | 1023/1261 [04:49<01:05,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 81%|████████  | 1024/1261 [04:49<01:05,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 81%|████████▏ | 1025/1261 [04:50<01:05,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 81%|████████▏ | 1026/1261 [04:50<01:05,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 81%|████████▏ | 1027/1261 [04:50<01:04,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 82%|████████▏ | 1028/1261 [04:51<01:03,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 82%|████████▏ | 1029/1261 [04:51<01:03,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 82%|████████▏ | 1030/1261 [04:51<01:03,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 82%|████████▏ | 1031/1261 [04:51<01:03,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 82%|████████▏ | 1032/1261 [04:52<01:03,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 82%|████████▏ | 1033/1261 [04:52<01:02,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 82%|████████▏ | 1034/1261 [04:52<01:02,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 82%|████████▏ | 1035/1261 [04:52<01:02,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 82%|████████▏ | 1036/1261 [04:53<01:01,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 82%|████████▏ | 1037/1261 [04:53<01:01,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 82%|████████▏ | 1038/1261 [04:53<01:01,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 82%|████████▏ | 1039/1261 [04:54<01:01,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 82%|████████▏ | 1040/1261 [04:54<01:02,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 83%|████████▎ | 1041/1261 [04:54<01:02,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 83%|████████▎ | 1042/1261 [04:54<01:01,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 83%|████████▎ | 1043/1261 [04:55<01:00,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 83%|████████▎ | 1044/1261 [04:55<01:00,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 83%|████████▎ | 1045/1261 [04:55<01:00,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 83%|████████▎ | 1046/1261 [04:55<00:59,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 83%|████████▎ | 1047/1261 [04:56<00:59,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 83%|████████▎ | 1048/1261 [04:56<00:59,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 83%|████████▎ | 1049/1261 [04:56<01:00,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 83%|████████▎ | 1050/1261 [04:57<00:59,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 83%|████████▎ | 1051/1261 [04:57<00:59,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 83%|████████▎ | 1052/1261 [04:57<00:59,  3.49it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 84%|████████▎ | 1053/1261 [04:57<00:59,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 84%|████████▎ | 1054/1261 [04:58<00:58,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 84%|████████▎ | 1055/1261 [04:58<00:58,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 84%|████████▎ | 1056/1261 [04:58<00:57,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 84%|████████▍ | 1057/1261 [04:59<00:57,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 84%|████████▍ | 1058/1261 [04:59<00:57,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 84%|████████▍ | 1059/1261 [04:59<00:56,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 84%|████████▍ | 1060/1261 [04:59<00:56,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 84%|████████▍ | 1061/1261 [05:00<00:56,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 84%|████████▍ | 1062/1261 [05:00<00:56,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 84%|████████▍ | 1063/1261 [05:00<00:56,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 84%|████████▍ | 1064/1261 [05:01<00:56,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 84%|████████▍ | 1065/1261 [05:01<00:55,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 85%|████████▍ | 1066/1261 [05:01<00:55,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 85%|████████▍ | 1067/1261 [05:01<00:55,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 85%|████████▍ | 1068/1261 [05:02<00:55,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 85%|████████▍ | 1069/1261 [05:02<00:55,  3.48it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 85%|████████▍ | 1070/1261 [05:02<00:54,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 85%|████████▍ | 1071/1261 [05:03<00:54,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 85%|████████▌ | 1072/1261 [05:03<00:54,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 85%|████████▌ | 1073/1261 [05:03<00:56,  3.35it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 85%|████████▌ | 1074/1261 [05:03<00:54,  3.44it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 85%|████████▌ | 1075/1261 [05:04<00:53,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 85%|████████▌ | 1076/1261 [05:04<00:52,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 85%|████████▌ | 1077/1261 [05:04<00:52,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 85%|████████▌ | 1078/1261 [05:05<00:52,  3.48it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 86%|████████▌ | 1079/1261 [05:05<00:52,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 86%|████████▌ | 1080/1261 [05:05<00:51,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 86%|████████▌ | 1081/1261 [05:05<00:51,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 86%|████████▌ | 1082/1261 [05:06<00:50,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 86%|████████▌ | 1083/1261 [05:06<00:50,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 86%|████████▌ | 1084/1261 [05:06<00:49,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 86%|████████▌ | 1085/1261 [05:07<00:49,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 86%|████████▌ | 1086/1261 [05:07<00:48,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 86%|████████▌ | 1087/1261 [05:07<00:48,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 86%|████████▋ | 1088/1261 [05:07<00:48,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 86%|████████▋ | 1089/1261 [05:08<00:48,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 86%|████████▋ | 1090/1261 [05:08<00:47,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 87%|████████▋ | 1091/1261 [05:08<00:47,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 87%|████████▋ | 1092/1261 [05:09<00:47,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 87%|████████▋ | 1093/1261 [05:09<00:46,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 87%|████████▋ | 1094/1261 [05:09<00:46,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 87%|████████▋ | 1095/1261 [05:09<00:46,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 87%|████████▋ | 1096/1261 [05:10<00:45,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 87%|████████▋ | 1097/1261 [05:10<00:45,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 87%|████████▋ | 1098/1261 [05:10<00:46,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 87%|████████▋ | 1099/1261 [05:11<00:46,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 87%|████████▋ | 1100/1261 [05:11<00:45,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 87%|████████▋ | 1101/1261 [05:11<00:45,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 87%|████████▋ | 1102/1261 [05:11<00:44,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 87%|████████▋ | 1103/1261 [05:12<00:43,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 88%|████████▊ | 1104/1261 [05:12<00:43,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 88%|████████▊ | 1105/1261 [05:12<00:43,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 88%|████████▊ | 1106/1261 [05:12<00:42,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 88%|████████▊ | 1107/1261 [05:13<00:42,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 88%|████████▊ | 1108/1261 [05:13<00:43,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 88%|████████▊ | 1109/1261 [05:14<00:57,  2.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 88%|████████▊ | 1110/1261 [05:14<01:14,  2.03it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 88%|████████▊ | 1111/1261 [05:15<01:22,  1.82it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 88%|████████▊ | 1112/1261 [05:15<01:10,  2.13it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 88%|████████▊ | 1113/1261 [05:16<01:00,  2.43it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 88%|████████▊ | 1114/1261 [05:16<00:54,  2.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 88%|████████▊ | 1115/1261 [05:16<00:49,  2.92it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 89%|████████▊ | 1116/1261 [05:16<00:46,  3.13it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 89%|████████▊ | 1117/1261 [05:17<00:43,  3.29it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 89%|████████▊ | 1118/1261 [05:17<00:42,  3.40it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 89%|████████▊ | 1119/1261 [05:17<00:41,  3.43it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 89%|████████▉ | 1120/1261 [05:18<00:40,  3.49it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 89%|████████▉ | 1121/1261 [05:18<00:40,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 89%|████████▉ | 1122/1261 [05:18<00:39,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 89%|████████▉ | 1123/1261 [05:18<00:40,  3.43it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 89%|████████▉ | 1124/1261 [05:19<00:39,  3.50it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 89%|████████▉ | 1125/1261 [05:19<00:38,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 89%|████████▉ | 1126/1261 [05:19<00:38,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 89%|████████▉ | 1127/1261 [05:20<00:37,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 89%|████████▉ | 1128/1261 [05:20<00:37,  3.54it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 90%|████████▉ | 1129/1261 [05:20<00:37,  3.52it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 90%|████████▉ | 1130/1261 [05:20<00:36,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 90%|████████▉ | 1131/1261 [05:21<00:36,  3.55it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 90%|████████▉ | 1132/1261 [05:21<00:35,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 90%|████████▉ | 1133/1261 [05:21<00:35,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 90%|████████▉ | 1134/1261 [05:22<00:35,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 90%|█████████ | 1135/1261 [05:22<00:35,  3.56it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 90%|█████████ | 1136/1261 [05:22<00:34,  3.57it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 90%|█████████ | 1137/1261 [05:22<00:34,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 90%|█████████ | 1138/1261 [05:23<00:33,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 90%|█████████ | 1139/1261 [05:23<00:33,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 90%|█████████ | 1140/1261 [05:23<00:33,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 90%|█████████ | 1141/1261 [05:23<00:32,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 91%|█████████ | 1142/1261 [05:24<00:32,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 91%|█████████ | 1143/1261 [05:24<00:32,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 91%|█████████ | 1144/1261 [05:24<00:31,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 91%|█████████ | 1145/1261 [05:25<00:31,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 91%|█████████ | 1146/1261 [05:25<00:31,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 91%|█████████ | 1147/1261 [05:25<00:31,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 91%|█████████ | 1148/1261 [05:25<00:31,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 91%|█████████ | 1149/1261 [05:26<00:30,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 91%|█████████ | 1150/1261 [05:26<00:30,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 91%|█████████▏| 1151/1261 [05:26<00:30,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 91%|█████████▏| 1152/1261 [05:26<00:30,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 91%|█████████▏| 1153/1261 [05:27<00:30,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 92%|█████████▏| 1154/1261 [05:27<00:29,  3.58it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 92%|█████████▏| 1155/1261 [05:27<00:29,  3.59it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 92%|█████████▏| 1156/1261 [05:28<00:29,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 92%|█████████▏| 1157/1261 [05:28<00:28,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 92%|█████████▏| 1158/1261 [05:28<00:28,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 92%|█████████▏| 1159/1261 [05:28<00:27,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 92%|█████████▏| 1160/1261 [05:29<00:27,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 92%|█████████▏| 1161/1261 [05:29<00:26,  3.75it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 92%|█████████▏| 1162/1261 [05:29<00:26,  3.76it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 92%|█████████▏| 1163/1261 [05:29<00:26,  3.76it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 92%|█████████▏| 1164/1261 [05:30<00:25,  3.79it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 92%|█████████▏| 1165/1261 [05:30<00:26,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 92%|█████████▏| 1166/1261 [05:30<00:26,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 93%|█████████▎| 1167/1261 [05:31<00:25,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 93%|█████████▎| 1168/1261 [05:31<00:25,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 93%|█████████▎| 1169/1261 [05:31<00:25,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 93%|█████████▎| 1170/1261 [05:31<00:25,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 93%|█████████▎| 1171/1261 [05:32<00:24,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 93%|█████████▎| 1172/1261 [05:32<00:24,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 93%|█████████▎| 1173/1261 [05:32<00:24,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 93%|█████████▎| 1174/1261 [05:32<00:23,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 93%|█████████▎| 1175/1261 [05:33<00:23,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 93%|█████████▎| 1176/1261 [05:33<00:23,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 93%|█████████▎| 1177/1261 [05:33<00:23,  3.53it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 93%|█████████▎| 1178/1261 [05:34<00:23,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 93%|█████████▎| 1179/1261 [05:34<00:22,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 94%|█████████▎| 1180/1261 [05:34<00:22,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 94%|█████████▎| 1181/1261 [05:34<00:22,  3.61it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 94%|█████████▎| 1182/1261 [05:35<00:21,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 94%|█████████▍| 1183/1261 [05:35<00:21,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 94%|█████████▍| 1184/1261 [05:35<00:20,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 94%|█████████▍| 1185/1261 [05:35<00:20,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 94%|█████████▍| 1186/1261 [05:36<00:20,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 94%|█████████▍| 1187/1261 [05:36<00:19,  3.72it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 94%|█████████▍| 1188/1261 [05:36<00:19,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 94%|█████████▍| 1189/1261 [05:37<00:19,  3.74it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 94%|█████████▍| 1190/1261 [05:37<00:19,  3.73it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 94%|█████████▍| 1191/1261 [05:37<00:18,  3.73it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 95%|█████████▍| 1192/1261 [05:37<00:18,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 95%|█████████▍| 1193/1261 [05:38<00:18,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 95%|█████████▍| 1194/1261 [05:38<00:18,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 95%|█████████▍| 1195/1261 [05:38<00:17,  3.72it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 95%|█████████▍| 1196/1261 [05:38<00:17,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 95%|█████████▍| 1197/1261 [05:39<00:17,  3.72it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 95%|█████████▌| 1198/1261 [05:39<00:16,  3.74it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 95%|█████████▌| 1199/1261 [05:39<00:16,  3.74it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 95%|█████████▌| 1200/1261 [05:40<00:16,  3.72it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 95%|█████████▌| 1201/1261 [05:40<00:16,  3.73it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 95%|█████████▌| 1202/1261 [05:40<00:15,  3.72it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 95%|█████████▌| 1203/1261 [05:40<00:15,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 95%|█████████▌| 1204/1261 [05:41<00:15,  3.68it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 96%|█████████▌| 1205/1261 [05:41<00:15,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 96%|█████████▌| 1206/1261 [05:41<00:14,  3.72it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 96%|█████████▌| 1207/1261 [05:41<00:14,  3.73it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 96%|█████████▌| 1208/1261 [05:42<00:14,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 96%|█████████▌| 1209/1261 [05:42<00:14,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 96%|█████████▌| 1210/1261 [05:42<00:13,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 96%|█████████▌| 1211/1261 [05:42<00:13,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 96%|█████████▌| 1212/1261 [05:43<00:13,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 96%|█████████▌| 1213/1261 [05:43<00:13,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 96%|█████████▋| 1214/1261 [05:43<00:12,  3.66it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 96%|█████████▋| 1215/1261 [05:44<00:12,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 96%|█████████▋| 1216/1261 [05:44<00:12,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 97%|█████████▋| 1217/1261 [05:44<00:11,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 97%|█████████▋| 1218/1261 [05:44<00:11,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 97%|█████████▋| 1219/1261 [05:45<00:11,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 97%|█████████▋| 1220/1261 [05:45<00:11,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 97%|█████████▋| 1221/1261 [05:45<00:10,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 97%|█████████▋| 1222/1261 [05:45<00:10,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 97%|█████████▋| 1223/1261 [05:46<00:10,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 97%|█████████▋| 1224/1261 [05:46<00:10,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 97%|█████████▋| 1225/1261 [05:46<00:09,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 97%|█████████▋| 1226/1261 [05:47<00:09,  3.70it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 97%|█████████▋| 1227/1261 [05:47<00:09,  3.71it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 97%|█████████▋| 1228/1261 [05:47<00:08,  3.72it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 97%|█████████▋| 1229/1261 [05:47<00:08,  3.69it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 98%|█████████▊| 1230/1261 [05:48<00:08,  3.67it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 98%|█████████▊| 1231/1261 [05:48<00:08,  3.65it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 98%|█████████▊| 1232/1261 [05:48<00:07,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 98%|█████████▊| 1233/1261 [05:48<00:07,  3.64it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 98%|█████████▊| 1234/1261 [05:49<00:07,  3.63it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 98%|█████████▊| 1235/1261 [05:49<00:07,  3.62it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 98%|█████████▊| 1236/1261 [05:49<00:06,  3.60it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 98%|█████████▊| 1237/1261 [05:50<00:06,  3.51it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 98%|█████████▊| 1238/1261 [05:50<00:06,  3.47it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 98%|█████████▊| 1239/1261 [05:50<00:06,  3.43it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 98%|█████████▊| 1240/1261 [05:51<00:06,  3.30it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 98%|█████████▊| 1241/1261 [05:51<00:06,  3.26it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 98%|█████████▊| 1242/1261 [05:51<00:05,  3.25it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 99%|█████████▊| 1243/1261 [05:51<00:05,  3.27it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 99%|█████████▊| 1244/1261 [05:52<00:05,  3.32it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 99%|█████████▊| 1245/1261 [05:52<00:04,  3.40it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 99%|█████████▉| 1246/1261 [05:52<00:04,  3.13it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 99%|█████████▉| 1247/1261 [05:53<00:04,  3.03it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 99%|█████████▉| 1248/1261 [05:53<00:04,  3.09it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 99%|█████████▉| 1249/1261 [05:53<00:03,  3.20it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 99%|█████████▉| 1250/1261 [05:54<00:03,  3.30it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 99%|█████████▉| 1251/1261 [05:54<00:03,  3.33it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 99%|█████████▉| 1252/1261 [05:54<00:02,  3.38it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 99%|█████████▉| 1253/1261 [05:55<00:02,  3.40it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      " 99%|█████████▉| 1254/1261 [05:55<00:02,  3.37it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "100%|█████████▉| 1255/1261 [05:55<00:01,  3.40it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "100%|█████████▉| 1256/1261 [05:55<00:01,  3.41it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "100%|█████████▉| 1257/1261 [05:56<00:01,  3.41it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "100%|█████████▉| 1258/1261 [05:56<00:00,  3.46it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "100%|█████████▉| 1259/1261 [05:56<00:00,  3.38it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "100%|█████████▉| 1260/1261 [05:57<00:00,  3.43it/s]\u001b[A\u001b[A\u001b[A\n",
      "\n",
      "\n",
      "\u001b[A\u001b[A\u001b[A"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[MoviePy] Done.\n",
      "[MoviePy] >>>> Video ready: projectvideo_output.mp4 \n",
      "\n",
      "CPU times: user 5min 47s, sys: 17.4 s, total: 6min 4s\n",
      "Wall time: 5min 58s\n"
     ]
    }
   ],
   "source": [
    "from moviepy.editor import *\n",
    "output_video = \"projectvideo_output.mp4\"\n",
    "clip1 = VideoFileClip(\"project_video.mp4\")\n",
    "output_clip = clip1.fl_image(pipeline)\n",
    "%time output_clip.write_videofile(output_video, audio=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python [Root]",
   "language": "python",
   "name": "Python [Root]"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}