Self-driving car Nanodegree - Term 1

In [1]:

    

import numpy as np
import cv2
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import pickle
import numpy as np
import glob
import os
from moviepy.editor import VideoFileClip
from IPython.display import HTML
%matplotlib inline


    

In [2]:

    

'''Read images directories'''
chessboard_images = glob.glob('../camera_cal/*.jpg')
test_images = glob.glob('../test_images/*.jpg')

#Prepare obj poinrts
objp = np.zeros((9 * 6, 3), np.float32)
objp[:,:2] = np.mgrid[0:9, 0:6].T.reshape(-1,2)
obj_points = [] #3d points in real world space
img_points = [] #2d points in image points

# termination criteria
criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 30, 0.001)

fig, axs = plt.subplots(5,4, figsize=(16, 11))
fig.subplots_adjust(hspace = .2, wspace=.001)
axs = axs.ravel()

for i, fname in enumerate(chessboard_images):
    img = cv2.imread(fname)
    image_name=os.path.split(fname)[1]
    gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
    
    ret, corners = cv2.findChessboardCorners(gray, (9, 6), None)
    if ret == True:
        obj_points.append(objp)
        
        # this step to refine image points was taken from:
        # http://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_calib3d/py_calibration/py_calibration.html
        corners2 = cv2.cornerSubPix(gray,corners,(11,11),(-1,-1),criteria)
        img_points.append(corners2)
        
        # Draw chessboard with corners
        img = cv2.drawChessboardCorners(img, (9,6), corners, ret)
        axs[i].axis('off')
        axs[i].imshow(img)


    

In [3]:

    

# Calcualte the undistortion matrix to calculate matrix and distance coefficient
img = cv2.imread(chessboard_images[0])
img_size = (img.shape[1], img.shape[0])
ret, mtx, dist, rvecs, tvecs = cv2.calibrateCamera(obj_points, img_points, img_size, None, None)


    

In [4]:

    

def undistort_image(img):           
    result = cv2.undistort(img, mtx, dist, None, mtx)
    return result


    

In [5]:

    

## using 1 chessboard image from calibration directory
chessboard_img = cv2.imread(chessboard_images[0])
undistort_chessboard_img = undistort_image(chessboard_img)

# using 1 image from test image directory to build and demonstrate each step of the pipeline
bgr_test_img = cv2.imread(test_images[0])
rgb_test_img = cv2.cvtColor(bgr_test_img, cv2.COLOR_BGR2RGB)
undistort_test_img = undistort_image(rgb_test_img )

# Visualize undistortion
f, (ax1, ax2) = plt.subplots(2, 2, figsize=(20,10))
f.subplots_adjust(hspace = .2, wspace=.05)

ax1[0].imshow(chessboard_img)
ax1[0].set_title('Original chessboard image', fontsize=30)
ax1[1].imshow(undistort_chessboard_img)
ax1[1].set_title('undistorted chessboard image', fontsize=30)

ax2[0].imshow(rgb_test_img)
ax2[0].set_title('Original sample test image', fontsize=30)
ax2[1].imshow(undistort_test_img)
ax2[1].set_title('Undistorted sample test image', fontsize=30)


    

    
Out[5]:





<matplotlib.text.Text at 0x2dacab8dac8>






    

In [6]:

    

# Visualize multiple color space channels
example_img_unwarp_R = undistort_test_img[:,:,0]
example_img_unwarp_G = undistort_test_img[:,:,1]
example_img_unwarp_B = undistort_test_img[:,:,2]

example_img_unwarp_HLS = cv2.cvtColor(undistort_test_img, cv2.COLOR_RGB2HLS)
example_img_unwarp_H = example_img_unwarp_HLS[:,:,0]
example_img_unwarp_L = example_img_unwarp_HLS[:,:,1]
example_img_unwarp_S = example_img_unwarp_HLS[:,:,2]

example_img_unwarp_HSV = cv2.cvtColor(undistort_test_img, cv2.COLOR_RGB2HSV)
example_img_unwarp_H = example_img_unwarp_HSV[:,:,0]
example_img_unwarp_S = example_img_unwarp_HSV[:,:,1]
example_img_unwarp_V = example_img_unwarp_HSV[:,:,2]

fig, axs = plt.subplots(3,3, figsize=(30, 20))
fig.subplots_adjust(hspace = .01, wspace=.01)
axs = axs.ravel()

axs[0].imshow(example_img_unwarp_R, cmap='gray')
axs[0].set_title('RGB R-channel', fontsize=30)
axs[1].imshow(example_img_unwarp_G, cmap='gray')
axs[1].set_title('RGB G-Channel', fontsize=30)
axs[2].imshow(example_img_unwarp_B, cmap='gray')
axs[2].set_title('RGB B-channel', fontsize=30)

axs[3].imshow(example_img_unwarp_H, cmap='gray')
axs[3].set_title('HLS H-channel', fontsize=30)
axs[4].imshow(example_img_unwarp_L, cmap='gray')
axs[4].set_title('HLS L-Channel', fontsize=30)
axs[5].imshow(example_img_unwarp_S, cmap='gray')
axs[5].set_title('HLS S-Channel', fontsize=30)

axs[6].imshow(example_img_unwarp_H, cmap='gray')
axs[6].set_title('HSV H-channel', fontsize=30)
axs[7].imshow(example_img_unwarp_S, cmap='gray')
axs[7].set_title('HSV S-Channel', fontsize=30)
axs[8].imshow(example_img_unwarp_V, cmap='gray')
axs[8].set_title('HSV V-Channel', fontsize=30)


    

    
Out[6]:





<matplotlib.text.Text at 0x2dacd4c0908>






    

In [7]:

    

rgb_r_channel = undistort_test_img[:,:,0]
rgb_r_thresh  = (200, 255)
rgb_r_binary = np.zeros_like(rgb_r_channel)
rgb_r_binary[(rgb_r_channel > rgb_r_thresh[0]) & (rgb_r_channel <= rgb_r_thresh[1])] = 1

hls = cv2.cvtColor(undistort_test_img, cv2.COLOR_RGB2HLS)
hls_s_channel = hls[:,:,2]
hls_s_thresh = (150, 255)
hls_s_binary = np.zeros_like(hls_s_channel)
hls_s_binary[(hls_s_channel > hls_s_thresh[0]) & (hls_s_channel <= hls_s_thresh[1])] = 1

hsv = cv2.cvtColor(undistort_test_img, cv2.COLOR_RGB2HSV)
hsv_v_channel = hsv[:,:,2]
hsv_v_thresh = (210, 255)
hsv_v_binary = np.zeros_like(hsv_v_channel)
hsv_v_binary[(hsv_v_channel > hsv_v_thresh[0]) & (hsv_v_channel <= hsv_v_thresh[1])] = 1
plt.imsave('../output_images/color_filter_binary.jpg', rgb_r_binary)

fig, axs = plt.subplots(2,2, figsize=(30, 20))
fig.subplots_adjust(hspace = .01, wspace=.01)
axs = axs.ravel()

axs[0].imshow(rgb_r_binary, cmap='gray')
axs[0].set_title('RGB r-binary', fontsize=30)
axs[1].imshow(hls_s_binary, cmap='gray')
axs[1].set_title('HLS s-binary', fontsize=30)
axs[2].imshow(hsv_v_binary, cmap='gray')
axs[2].set_title('HSV v-binary', fontsize=30)


    

    
Out[7]:





<matplotlib.text.Text at 0x2dacdb0d278>






    

In [8]:

    

def absolute_sobel_threshold(img, orient='x', thresh_min = 0, thresh_max = 255):
    if orient == 'x':
        abs_sobel = np.absolute(cv2.Sobel(img, cv2.CV_64F, 1, 0))
    if orient == 'y':
        abs_sobel = np.absolute(cv2.Sobel(img, cv2.CV_64F, 0, 1))
        
    scaled_sobel = np.uint8(255 * abs_sobel/np.max(abs_sobel))
    sobel_binary = np.zeros_like(scaled_sobel)
    sobel_binary[(scaled_sobel >= thresh_min) & (scaled_sobel <= thresh_max)] = 1
    return sobel_binary


    

In [9]:

    

gray_img =  cv2.cvtColor(undistort_test_img, cv2.COLOR_RGB2GRAY)
grad_x_binary = absolute_sobel_threshold(gray_img , orient='x', thresh_min=60, thresh_max=150)
grad_y_binary = absolute_sobel_threshold(gray_img , orient='y', thresh_min=90, thresh_max=255)

#Plot the result
fig, axs = plt.subplots(1,2, figsize=(24, 9))
fig.subplots_adjust(hspace = .01, wspace=.01)
axs = axs.ravel()
axs[0].imshow(grad_x_binary, cmap='gray')
axs[0].set_title('gradient x binary', fontsize=30)
axs[1].imshow(grad_y_binary, cmap='gray')
axs[1].set_title('gradient y binary', fontsize=30)


    

    
Out[9]:





<matplotlib.text.Text at 0x2dacdc560b8>






    

In [10]:

    

def magnitude_threshold(gray_img, sobel_kernel = 3, mag_thresh = (0, 255)): 
    sobelx = cv2.Sobel(gray_img, cv2.CV_64F, 1, 0, ksize = sobel_kernel)
    sobely = cv2.Sobel(gray_img, cv2.CV_64F, 0, 1, ksize = sobel_kernel)
    grad_mag = np.sqrt(sobelx**2 + sobely**2)
    scale_factor = np.max(grad_mag)/255 
    grad_mag = (grad_mag/scale_factor).astype(np.uint8) 
    mag_binary = np.zeros_like(grad_mag)
    mag_binary[(grad_mag >= mag_thresh[0]) & (grad_mag <= mag_thresh[1])] = 1
    return mag_binary


    

In [11]:

    

gray_img =  cv2.cvtColor(undistort_test_img, cv2.COLOR_RGB2GRAY)
mag_binary = magnitude_threshold(gray_img, sobel_kernel = 31, mag_thresh = (135, 255))
#Plot the result
fig, axs = plt.subplots(1,2, figsize=(24, 9))
fig.subplots_adjust(hspace = .01, wspace=.01)
axs = axs.ravel()
axs[0].imshow(undistort_test_img, cmap='gray')
axs[0].set_title('original image', fontsize=30)
axs[1].imshow(mag_binary , cmap='gray')
axs[1].set_title('thresholded gradient magnitude', fontsize=30)


    

    
Out[11]:





<matplotlib.text.Text at 0x2dac57a8240>






    

In [12]:

    

def direction_threshold(gray_img, sobel_kernel = 3, dir_thresh = (0, np.pi/2)):
    sobelx = cv2.Sobel(gray_img, cv2.CV_64F, 1, 0, ksize = sobel_kernel)
    sobely = cv2.Sobel(gray_img, cv2.CV_64F, 0, 1, ksize = sobel_kernel)
    abs_grad_dir = np.arctan2(np.absolute(sobely), np.absolute(sobelx))
    dir_binary =  np.zeros_like(abs_grad_dir)
    dir_binary[(abs_grad_dir >= dir_thresh[0]) & (abs_grad_dir <= dir_thresh[1])] = 1
    return dir_binary


    

In [13]:

    

gray_img =  cv2.cvtColor(undistort_test_img, cv2.COLOR_RGB2GRAY)

dir_binary = direction_threshold(gray_img, sobel_kernel = 23, dir_thresh = (0.7, 1.1))

#Plot the result
fig, axs = plt.subplots(1,2, figsize=(24, 9))
fig.subplots_adjust(hspace = .01, wspace=.01)
axs = axs.ravel()

axs[0].imshow(undistort_test_img, cmap='gray')
axs[0].set_title('original image', fontsize = 30)

axs[1].imshow(dir_binary  , cmap='gray')
axs[1].set_title('thresholded gradient direction', fontsize = 30)


    

    
Out[13]:





<matplotlib.text.Text at 0x2dac5679c88>






    

In [14]:

    

gray_img =  cv2.cvtColor(undistort_test_img, cv2.COLOR_RGB2GRAY)

grad_x_binary = absolute_sobel_threshold(gray_img, orient='x', thresh_min=60, thresh_max=150)
grad_y_binary = absolute_sobel_threshold(gray_img, orient='y', thresh_min=90, thresh_max=255)

mag_binary = magnitude_threshold(gray_img, sobel_kernel = 31, mag_thresh = (135, 255))
#dir_binary = direction_threshold(gray_img, sobel_kernel = 23, dir_thresh = (0.7, 1.1))

combined = np.zeros_like(gray_img)
combined[(grad_x_binary == 1) & (grad_y_binary == 1) & (mag_binary == 1) ] = 1

#Plot the result
fig, axs = plt.subplots(1,2, figsize=(24, 9))
fig.subplots_adjust(hspace = .01, wspace=.01)
axs = axs.ravel()

axs[0].imshow(undistort_test_img, cmap='gray')
axs[0].set_title('original image', fontsize=30)

axs[1].imshow(combined, cmap='gray')
axs[1].set_title('thresholded combine gradient', fontsize=30)


    

    
Out[14]:





<matplotlib.text.Text at 0x2dac5535c88>






    

In [15]:

    

gray_img =  cv2.cvtColor(undistort_test_img, cv2.COLOR_RGB2GRAY)

grad_x_binary = absolute_sobel_threshold(gray_img, orient='x', thresh_min=30, thresh_max=250)
grad_y_binary = absolute_sobel_threshold(gray_img, orient='y', thresh_min=20, thresh_max=100)
mag_binary = magnitude_threshold(gray_img, sobel_kernel = 9, mag_thresh = (120, 255))
dir_binary = direction_threshold(gray_img, sobel_kernel = 15, dir_thresh = (0.7, 1.1))

combined_threshold = np.zeros_like(dir_binary)
combined_threshold[((grad_x_binary == 1) & (grad_y_binary == 1)) | ((mag_binary == 1) & (dir_binary == 1))] = 1


hsv = cv2.cvtColor(undistort_test_img, cv2.COLOR_RGB2HSV)
hsv_v_channel = hsv[:,:,2]
hsv_v_thresh = (210, 255)
hsv_v_binary = np.zeros_like(hsv_v_channel)
hsv_v_binary[(hsv_v_channel > hsv_v_thresh[0]) & (hsv_v_channel <= hsv_v_thresh[1])] = 1

#rgb_r_channel = undistort_test_img[:,:,0]
#rgb_r_thresh  = (200, 255)
#rgb_r_binary = np.zeros_like(rgb_r_channel)
#rgb_r_binary[(rgb_r_channel > rgb_r_thresh[0]) & (rgb_r_channel <= rgb_r_thresh[1])] = 1

# Stack each channel to view their individual contributions in green and blue respectively
# This returns a stack of the two binary images, whose components you can see as different colors
color_binary = np.dstack((combined_threshold, combined_threshold, hsv_v_binary)) * 255

# Combine the two binary thresholds
combined_binary = np.zeros_like(hsv_v_channel)
combined_binary[(rgb_r_binary == 1) | (combined_threshold == 1)] = 1
plt.imsave('../output_images/combine_binary.jpg', combined_binary)

#Plot the result
fig, axs = plt.subplots(1,2, figsize=(24, 9))
fig.subplots_adjust(hspace = .01, wspace=.01)
axs = axs.ravel()

axs[0].imshow(undistort_test_img, cmap='gray')
axs[0].set_title('original image', fontsize = 30)

axs[1].imshow(combined_binary, cmap='gray')
axs[1].set_title('Thresholded combined gradient and color', fontsize = 30)


    

    
Out[15]:





<matplotlib.text.Text at 0x2dac53f46d8>






    

In [16]:

    

def warper(image, source, destination):
    h,w = img.shape[:2]
    transform_matrix = cv2.getPerspectiveTransform(source, destination)
    inverse_matrix = cv2.getPerspectiveTransform(destination, source)
    warped = cv2.warpPerspective(image, transform_matrix , (w,h))
    return warped, transform_matrix, inverse_matrix

def source(img_size):
    src = np.float32(
        [
             [(img_size[0] / 2) - 55, img_size[1] / 2 + 100],
             [(img_size[0] / 2 + 55), img_size[1] / 2 + 100],
             [((img_size[0] / 6) - 10), img_size[1]],
             [(img_size[0] * 5 / 6) + 60, img_size[1]]
            
        ])
    
    return src

def destination(img_size):
    dest = np.float32(
        [
             [(img_size[0] / 4), 0],
             [(img_size[0] * 3 / 4), 0],
             [(img_size[0] / 4), img_size[1]],
             [(img_size[0] * 3 / 4), img_size[1]]
        ])
    
    return dest


    

In [17]:

    

img_size = (undistort_test_img.shape[1], undistort_test_img.shape[0])
print(img_size)
src = source(img_size)
dest = destination(img_size)
warp_example_img, M, inverse_M = warper(undistort_test_img, src, dest) 
plt.imsave('../output_images/warp_example_img.jpg', warp_example_img)

# Visualize unwarp
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(20,10))
f.subplots_adjust(hspace = .2, wspace=.05)

ax1.imshow(undistort_test_img)
x = [src[0][0],src[2][0],src[3][0],src[1][0],src[0][0]]
y = [src[0][1],src[2][1],src[3][1],src[1][1],src[0][1]]
ax1.plot(x, y, color='#33cc99', alpha=0.4, linewidth=3, solid_capstyle='round', zorder=2)
ax1.set_title('Undistorted Image', fontsize=30)

ax2.imshow(warp_example_img)
ax2.set_title('Unwarped Image', fontsize=30)


    

    




(1280, 720)






    
Out[17]:





<matplotlib.text.Text at 0x2dac578c198>






    

In [18]:

    

def pipeline(img):
    
    img_size = (img.shape[1], img.shape[0])
    src = source(img_size)
    dest = destination(img_size)
    warp_img, M, inverse_M = warper(img, src, dest) 

    gray_img =  cv2.cvtColor(warp_img, cv2.COLOR_RGB2GRAY)
    grad_x_binary = absolute_sobel_threshold(gray_img, orient='x', thresh_min=30, thresh_max=250)
    grad_y_binary = absolute_sobel_threshold(gray_img, orient='y', thresh_min=20, thresh_max=100)
    mag_binary = magnitude_threshold(gray_img, sobel_kernel = 9, mag_thresh = (120, 255))
    dir_binary = direction_threshold(gray_img, sobel_kernel = 15, dir_thresh = (0.7, 1.1))

    combined_threshold = np.zeros_like(dir_binary)
    combined_threshold[((grad_x_binary == 1) & (grad_y_binary == 1)) & (mag_binary == 1) ] = 1
    
    hsv = cv2.cvtColor(warp_img, cv2.COLOR_RGB2HSV)
    hsv_v_channel = hsv[:,:,2]
    hsv_v_thresh = (210, 255)
    hsv_v_binary = np.zeros_like(hsv_v_channel)
    hsv_v_binary[(hsv_v_channel > hsv_v_thresh[0]) & (hsv_v_channel <= hsv_v_thresh[1])] = 1

    # Stack each channel to view their individual contributions in green and blue respectively
    # This returns a stack of the two binary images, whose components you can see as different colors
    color_binary = np.dstack((combined_threshold, combined_threshold, hsv_v_binary)) * 255

    # Combine the two binary thresholds
    combined_binary = np.zeros_like(gray_img)
    combined_binary[(hsv_v_binary == 1) | (combined_threshold == 1)] = 1
    
    return combined_binary,  inverse_M


    

In [19]:

    

bgr_test_img_2 = cv2.imread(test_images[0])
rgb_test_img_2 = cv2.cvtColor(bgr_test_img_2, cv2.COLOR_BGR2RGB)
undistort_test_img = undistort_image(rgb_test_img)
binary_warped, inverse_M = pipeline(undistort_test_img)

fig, axs = plt.subplots(1,1, figsize=(24, 9))

axs.imshow(binary_warped, cmap='gray')
axs.set_title('combined binary', fontsize = 30)


    

    
Out[19]:





<matplotlib.text.Text at 0x2dac53b5e10>






    

In [20]:

    

# Take a histogram of the bottom half of the image
histogram = np.sum(binary_warped[binary_warped.shape[0]//2:,:], axis=0)

plt.title('Histogram')
plt.xlabel("Fixed Position")
plt.ylabel("Counts")
plt.plot(histogram)
plt.savefig('../output_images/histogram.jpg')


    

In [21]:

    

#def test_polyfit

out_img = np.dstack((binary_warped, binary_warped, binary_warped)) * 255

# Take a histogram of the bottom half of the image
histogram = np.sum(binary_warped[binary_warped.shape[0]//2:,:], axis=0)

midpoint = np.int(histogram.shape[0]/2)
leftx_base = np.argmax(histogram[:midpoint])
rightx_base = np.argmax(histogram[midpoint:]) + midpoint

# Choose the number of sliding windows
nwindows = 10
# Set height of windows
window_height = np.int(binary_warped.shape[0]/ nwindows)

# Identify the x and y positions of all nonzero pixels in the image
nonzero = binary_warped.nonzero()
nonzeroy = np.array(nonzero[0])
nonzerox = np.array(nonzero[1])

# Current positions to be updated for each window
leftx_current = leftx_base
rightx_current = rightx_base
# Set the width of the windows +/- margin
margin = 100
# Set minimum number of pixels found to recenter window
minpix = 50
# Create empty lists to receive left and right lane pixel indices
left_lane_inds = []
right_lane_inds = []

# Step through the windows one by one
for window in range(nwindows):
    # Identify window boundaries in x and y (and right and left)
    win_y_low = binary_warped.shape[0] - (window + 1) * window_height
    win_y_high = binary_warped.shape[0] - window * window_height
    win_xleft_low = leftx_current - margin
    win_xleft_high = leftx_current + margin
    win_xright_low = rightx_current - margin
    win_xright_high = rightx_current + margin
    # Draw the windows on the visualization image
    cv2.rectangle(out_img,(win_xleft_low,win_y_low),(win_xleft_high,win_y_high),(0,255,0), 2) 
    cv2.rectangle(out_img,(win_xright_low,win_y_low),(win_xright_high,win_y_high),(0,255,0), 2) 

    # Identify the nonzero pixels in x and y within the window
    good_left_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) & (nonzerox >= win_xleft_low) &  (nonzerox < win_xleft_high)).nonzero()[0]
    good_right_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) & (nonzerox >= win_xright_low) &  (nonzerox < win_xright_high)).nonzero()[0]

    # Append these indices to the lists
    left_lane_inds.append(good_left_inds)
    right_lane_inds.append(good_right_inds)
    # If you found > minpix pixels, recenter next window on their mean position
    if len(good_left_inds) > minpix:
        leftx_current = np.int(np.mean(nonzerox[good_left_inds]))
    if len(good_right_inds) > minpix:        
        rightx_current = np.int(np.mean(nonzerox[good_right_inds]))

# Concatenate the arrays of indices
left_lane_inds = np.concatenate(left_lane_inds)
right_lane_inds = np.concatenate(right_lane_inds)

# Extract left and right line pixel positions
leftx = nonzerox[left_lane_inds]
lefty = nonzeroy[left_lane_inds] 

rightx = nonzerox[right_lane_inds]
righty = nonzeroy[right_lane_inds] 

# Fit a second order polynomial to each
left_fit = np.polyfit(lefty, leftx, 2)
right_fit = np.polyfit(righty, rightx, 2)

# Generate x and y values for plotting
ploty = np.linspace(0, binary_warped.shape[0]-1, binary_warped.shape[0] )
left_fitx = left_fit[0]*ploty**2 + left_fit[1]*ploty + left_fit[2]
right_fitx = right_fit[0]*ploty**2 + right_fit[1]*ploty + right_fit[2]

out_img[nonzeroy[left_lane_inds], nonzerox[left_lane_inds]] = [255, 0, 0]
out_img[nonzeroy[right_lane_inds], nonzerox[right_lane_inds]] = [0, 0, 255]

#Plot the result
plt.imshow(out_img)
plt.plot(left_fitx, ploty, color='yellow')
plt.plot(right_fitx, ploty, color='yellow')
plt.xlim(0, 1280)
plt.ylim(720, 0)


    

    
Out[21]:





(720, 0)






    

In [22]:

    

# Assume you now have a new warped binary image 
# from the next frame of video (also called "binary_warped")
# It's now much easier to find line pixels!
nonzero = binary_warped.nonzero()
nonzeroy = np.array(nonzero[0])
nonzerox = np.array(nonzero[1])
margin = 100
left_lane_inds = ((nonzerox > (left_fit[0]*(nonzeroy**2) + left_fit[1]*nonzeroy + 
left_fit[2] - margin)) & (nonzerox < (left_fit[0]*(nonzeroy**2) + 
left_fit[1]*nonzeroy + left_fit[2] + margin))) 

right_lane_inds = ((nonzerox > (right_fit[0]*(nonzeroy**2) + right_fit[1]*nonzeroy + 
right_fit[2] - margin)) & (nonzerox < (right_fit[0]*(nonzeroy**2) + 
right_fit[1]*nonzeroy + right_fit[2] + margin)))  

# Again, extract left and right line pixel positions
leftx = nonzerox[left_lane_inds]
lefty = nonzeroy[left_lane_inds] 
rightx = nonzerox[right_lane_inds]
righty = nonzeroy[right_lane_inds]
# Fit a second order polynomial to each
left_fit_update = np.polyfit(lefty, leftx, 2)
right_fit_update = np.polyfit(righty, rightx, 2)

# Visualization
margin = 100
# Generate x and y values for plotting
ploty = np.linspace(0, binary_warped.shape[0]-1, binary_warped.shape[0] )

left_fitx = left_fit[0]*ploty**2 + left_fit[1]*ploty + left_fit[2]
right_fitx = right_fit[0]*ploty**2 + right_fit[1]*ploty + right_fit[2]

# Create an image to draw on and an image to show the selection window
out_img = np.dstack((binary_warped, binary_warped, binary_warped))*255
window_img = np.zeros_like(out_img)
# Color in left and right line pixels
out_img[nonzeroy[left_lane_inds], nonzerox[left_lane_inds]] = [255, 0, 0]
out_img[nonzeroy[right_lane_inds], nonzerox[right_lane_inds]] = [0, 0, 255]

# Generate a polygon to illustrate the search window area
# And recast the x and y points into usable format for cv2.fillPoly()
left_line_window1 = np.array([np.transpose(np.vstack([left_fitx-margin, ploty]))])
left_line_window2 = np.array([np.flipud(np.transpose(np.vstack([left_fitx+margin, ploty])))])
left_line_pts = np.hstack((left_line_window1, left_line_window2))
right_line_window1 = np.array([np.transpose(np.vstack([right_fitx-margin, ploty]))])
right_line_window2 = np.array([np.flipud(np.transpose(np.vstack([right_fitx+margin, ploty])))])
right_line_pts = np.hstack((right_line_window1, right_line_window2))

# Draw the lane onto the warped blank image
cv2.fillPoly(window_img, np.int_([left_line_pts]), (0,255, 0))
cv2.fillPoly(window_img, np.int_([right_line_pts]), (0,255, 0))
result = cv2.addWeighted(out_img, 1, window_img, 0.3, 0)
plt.imshow(result)
plt.plot(left_fitx, ploty, color='yellow')
plt.plot(right_fitx, ploty, color='yellow')
plt.xlim(0, 1280)
plt.ylim(720, 0)


    

    
Out[22]:





(720, 0)






    

In [46]:

    

# fit = [A,B,C] , radisu in pixel space
def calculate_curvature_pixel_space(fit, ploty):
    y_value = np.max(ploty)
    nominator =  (1 + (2 * fit[0] * y_value + fit[1])**2)**1.5
    denominator = np.absolute(2 * fit[0])
    return (nominator / denominator)

def calculate_curvature_world_space(fit,  ploty):
    # Define conversions in x and y from pixels space to meters
    y_in_m_per_pix = 30/720 # meters per pixel in y dimension
    x_in_m_per_pix = 3.7/700 # meters per pixel in x dimension
    # Fit new polynomials to x,y in world space
    fit_x = fit[0]*ploty**2 + fit[1] * ploty + fit[2]
    
    fit_word_space = np.polyfit(ploty * y_in_m_per_pix, fit_x* x_in_m_per_pix, 2)
    result = calculate_curvature_pixel_space(fit_word_space,  ploty)
    return result

# choose the maximum y-value, corresponding to the bottom of the image
left_curvature_pixel_space = calculate_curvature_pixel_space(left_fit,  ploty)
right_curvature_pixel_space = calculate_curvature_pixel_space(right_fit,  ploty)

left_curvature_world_space = calculate_curvature_world_space(left_fit,  ploty)
right_curvature_world_space = calculate_curvature_world_space(right_fit,  ploty)

print("Pixel space: left curvature: " + str(left_curvature_pixel_space) + ' , right curvature: ' + str(right_curvature_pixel_space))
print("World space: left curvature: " + str(left_curvature_world_space) + ' m , right curvature: ' + str(right_curvature_world_space) + ' m')

# compute the offset from the center\

xm_per_pix = 3.7/700 # meters per pixel in x dimension
ym_per_pix = 30/720

# Fit a second order polynomial to each
left_fit_m = np.polyfit(ploty*ym_per_pix, left_fitx*xm_per_pix, 2)
right_fit_m = np.polyfit(ploty*ym_per_pix, right_fitx*xm_per_pix, 2)

xMax = img.shape[1]*xm_per_pix
yMax = img.shape[0]*ym_per_pix
vehicleCenter = xMax / 2
lineLeft = left_fit_m[0]*yMax**2 + left_fit_m[1]*yMax + left_fit_m[2]
lineRight = right_fit_m[0]*yMax**2 + right_fit_m[1]*yMax + right_fit_m[2]
lineMiddle = lineLeft + (lineRight - lineLeft)/2
diffFromVehicle = lineMiddle - vehicleCenter
offset_string = "Center offset: %.2f m" % diffFromVehicle
print(offset_string)


    

    




Pixel space: left curvature: 13392.5440853 , right curvature: 49920.7740049
World space: left curvature: 4559.63632703 m , right curvature: 16337.8625965 m
Center offset: -0.03 m

In [53]:

    

def drawing(undistorted_img, binary_warped, left_fit, right_fit, inverse_M, img_size): 
    # Create an image to draw the lines on
    ploty = np.linspace(0, binary_warped.shape[0] - 1, binary_warped.shape[0] )
    left_fitx = left_fit[0]*ploty**2 + left_fit[1]*ploty + left_fit[2]
    right_fitx = right_fit[0]*ploty**2 + right_fit[1]*ploty + right_fit[2]
    
    warp_zero = np.zeros_like(binary_warped).astype(np.uint8)
    color_warp = np.dstack((warp_zero, warp_zero, warp_zero))

    # Recast the x and y points into usable format for cv2.fillPoly()
    pts_left = np.array([np.transpose(np.vstack([left_fitx, ploty]))])
    pts_right = np.array([np.flipud(np.transpose(np.vstack([right_fitx, ploty])))])
    pts = np.hstack((pts_left, pts_right))

    # Draw the lane onto the warped blank image
    cv2.fillPoly(color_warp, np.int_([pts]), (0,255, 0))

    # Warp the blank back to original image space using inverse perspective matrix (Minv)
    newwarp = cv2.warpPerspective(color_warp, inverse_M, img_size) 
    # Combine the result with the original image
    result = cv2.addWeighted(undistorted_img, 1, newwarp, 0.3, 0)

    left_curvature_world_space = calculate_curvature_world_space(left_fit,  ploty)
    right_curvature_world_space = calculate_curvature_world_space(right_fit,  ploty)
    
    curvature_string = "Left Radius of curvature: %.2f m" % left_curvature_world_space
    cv2.putText(result,curvature_string , (100, 90), cv2.FONT_HERSHEY_SIMPLEX, 1.5, (255,255,255), thickness=2)
    
    curvature_string = "Right Radius of curvature: %.2f m" % right_curvature_world_space
    cv2.putText(result,curvature_string , (100, 150), cv2.FONT_HERSHEY_SIMPLEX, 1.5, (255,255,255), thickness=2)

    
    # compute the offset from the center\

    xm_per_pix = 3.7/700 # meters per pixel in x dimension
    ym_per_pix = 30/720

    # Fit a second order polynomial to each
    left_fit_m = np.polyfit(ploty*ym_per_pix, left_fitx*xm_per_pix, 2)
    right_fit_m = np.polyfit(ploty*ym_per_pix, right_fitx*xm_per_pix, 2)

    xMax = img.shape[1]*xm_per_pix
    yMax = img.shape[0]*ym_per_pix
    vehicleCenter = xMax / 2
    lineLeft = left_fit_m[0]*yMax**2 + left_fit_m[1]*yMax + left_fit_m[2]
    lineRight = right_fit_m[0]*yMax**2 + right_fit_m[1]*yMax + right_fit_m[2]
    lineMiddle = lineLeft + (lineRight - lineLeft)/2
    diffFromVehicle = lineMiddle - vehicleCenter
    offset_string = "Center offset: %.2f m" % diffFromVehicle
    cv2.putText(result, offset_string, (100, 210), cv2.FONT_HERSHEY_SIMPLEX, 1.5, (255,255,255), thickness=2)
    
    return result

result = drawing(rgb_test_img, binary_warped, left_fit, right_fit, inverse_M, img_size)
plt.imsave("../output_images/test_img_1_output.jpg", result)


    

In [54]:

    

def sliding_window_polyfit(binary_warped):
    out_img = np.dstack((binary_warped, binary_warped, binary_warped)) * 255

    # Take a histogram of the bottom half of the image
    histogram = np.sum(binary_warped[binary_warped.shape[0]//2:,:], axis=0)
    
    ## fiding  left and right point
    midpoint = np.int(histogram.shape[0]/2)
    leftx_base = np.argmax(histogram[:midpoint])
    rightx_base = np.argmax(histogram[midpoint:]) + midpoint

    # Choose the number of sliding windows
    nwindows = 10
    # Set height of windows
    window_height = np.int(binary_warped.shape[0]/ nwindows)

    # Identify the x and y positions of all nonzero pixels in the image
    nonzero = binary_warped.nonzero()
    nonzeroy = np.array(nonzero[0])
    nonzerox = np.array(nonzero[1])

    # Set the width of the windows +/- margin
    margin = 100
    # Set minimum number of pixels found to recenter window
    minpix = 50
    # Create empty lists to receive left and right lane pixel indices
    left_lane_inds = []
    right_lane_inds = []

    # Step through the windows one by one
    for window in range(nwindows):
        # Identify window boundaries in x and y (and right and left)
        win_y_low = binary_warped.shape[0] - (window + 1) * window_height
        win_y_high = binary_warped.shape[0] - window * window_height
        
        win_xleft_low = leftx_base - margin
        win_xleft_high = leftx_base + margin
        
        win_xright_low = rightx_base - margin
        win_xright_high = rightx_base + margin
        
        # Draw the windows on the visualization image
        cv2.rectangle(out_img,(win_xleft_low,win_y_low),(win_xleft_high,win_y_high),(0,255,0), 2) 
        cv2.rectangle(out_img,(win_xright_low,win_y_low),(win_xright_high,win_y_high),(0,255,0), 2) 

        # Identify the nonzero pixels in x and y within the window
        good_left_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) & (nonzerox >= win_xleft_low) & 
                          (nonzerox < win_xleft_high)).nonzero()[0]
        good_right_inds = ((nonzeroy >= win_y_low) & (nonzeroy < win_y_high) & (nonzerox >= win_xright_low) & 
                           (nonzerox < win_xright_high)).nonzero()[0]

        # Append these indices to the lists
        left_lane_inds.append(good_left_inds)
        right_lane_inds.append(good_right_inds)
        # If you found > minpix pixels, recenter next window on their mean position
        if len(good_left_inds) > minpix:
            leftx_current = np.int(np.mean(nonzerox[good_left_inds]))
        if len(good_right_inds) > minpix:        
            rightx_current = np.int(np.mean(nonzerox[good_right_inds]))

    # Concatenate the arrays of indices
    left_lane_inds = np.concatenate(left_lane_inds)
    right_lane_inds = np.concatenate(right_lane_inds)


    # Extract left and right line pixel positions
    leftx = nonzerox[left_lane_inds]
    lefty = nonzeroy[left_lane_inds] 

    rightx = nonzerox[right_lane_inds]
    righty = nonzeroy[right_lane_inds] 

    # Fit a second order polynomial to each
    polyfit_left = np.polyfit(lefty, leftx, 2)
    polyfit_right = np.polyfit(righty, rightx, 2)
    
    return polyfit_left, polyfit_right


def polyfit_using_previous_fit(binary_warped, prev_left_fit, prev_right_fit):
    # Assume you now have a new warped binary image 
    # from the next frame of video (also called "binary_warped")
    # It's now much easier to find line pixels!
    nonzero = binary_warped.nonzero()
    nonzeroy = np.array(nonzero[0])
    nonzerox = np.array(nonzero[1])
    margin = 100
    
    left_lane_inds = ((nonzerox > (prev_left_fit[0]*(nonzeroy**2) + prev_left_fit[1]*nonzeroy + prev_left_fit[2] - margin))
                      & (nonzerox < (prev_left_fit[0]*(nonzeroy**2) + prev_left_fit[1]*nonzeroy + prev_left_fit[2] + margin))) 
    right_lane_inds = ((nonzerox > (prev_right_fit[0]*(nonzeroy**2) + prev_right_fit[1]*nonzeroy + prev_right_fit[2]- margin))
                       & (nonzerox < (prev_right_fit[0]*(nonzeroy**2) + prev_right_fit[1]*nonzeroy + prev_right_fit[2] + margin)))  

    # Again, extract left and right line pixel positions
    leftx = nonzerox[left_lane_inds]
    lefty = nonzeroy[left_lane_inds] 
    rightx = nonzerox[right_lane_inds]
    righty = nonzeroy[right_lane_inds]
    
    # Fit a second order polynomial to each
    if len(leftx) != 0:
        polyfit_left = np.polyfit(lefty, leftx, 2)
    if len(rightx) != 0:
        polyfit_right = np.polyfit(righty, rightx, 2)
    
    return polyfit_left, polyfit_right

def process_image(image):
    # global variables to store the polynomial coefficients of the line detected in the last frame
    global polyfit_left
    global polyfit_right
    
    img_size = (image.shape[1], image.shape[0])

    #1. Camera correction and distortion correction
    undistorted_img = undistort_image(image)
    
    #2. Applying perspective transformation, thresholded color and gradient filter
    binary_warped, inverse_M = pipeline(undistorted_img)
    
    #3. Detect lanes and return fit curves
    if (polyfit_left is not None) and (polyfit_right is not None):
        polyfit_left, polyfit_right =  polyfit_using_previous_fit(binary_warped, polyfit_left, polyfit_right)   
    else:
        polyfit_left, polyfit_right = sliding_window_polyfit(binary_warped)
    
    result = drawing(undistorted_img, binary_warped, polyfit_left, polyfit_right, inverse_M, img_size)
    return result


    

In [55]:

    

polyfit_left = None
polyfit_right = None

clip1 = VideoFileClip('../test_video/project_video.mp4')
video_clip = clip1.fl_image(process_image) #NOTE: this function expects color images!!

video_output = '../output_videos/project_video.mp4'
%time video_clip.write_videofile(video_output, audio=False)


    

    




[MoviePy] >>>> Building video ../output_videos/project_video.mp4
[MoviePy] Writing video ../output_videos/project_video.mp4






    




  0%|          | 0/1261 [00:00<?, ?it/s]
  0%|          | 1/1261 [00:00<05:41,  3.69it/s]
  0%|          | 2/1261 [00:00<05:49,  3.60it/s]
  0%|          | 3/1261 [00:00<05:52,  3.57it/s]
  0%|          | 4/1261 [00:01<05:53,  3.55it/s]
  0%|          | 5/1261 [00:01<05:53,  3.55it/s]
  0%|          | 6/1261 [00:01<05:57,  3.51it/s]
  1%|          | 7/1261 [00:01<05:54,  3.54it/s]
  1%|          | 8/1261 [00:02<05:53,  3.55it/s]
  1%|          | 9/1261 [00:02<05:56,  3.51it/s]
  1%|          | 10/1261 [00:02<05:55,  3.52it/s]
  1%|          | 11/1261 [00:03<05:58,  3.49it/s]
  1%|          | 12/1261 [00:03<06:02,  3.45it/s]
  1%|          | 13/1261 [00:03<05:57,  3.49it/s]
  1%|          | 14/1261 [00:04<06:03,  3.43it/s]
  1%|          | 15/1261 [00:04<06:01,  3.45it/s]
  1%|▏         | 16/1261 [00:04<05:56,  3.49it/s]
  1%|▏         | 17/1261 [00:04<05:57,  3.48it/s]
  1%|▏         | 18/1261 [00:05<05:57,  3.48it/s]
  2%|▏         | 19/1261 [00:05<05:59,  3.46it/s]
  2%|▏         | 20/1261 [00:05<05:54,  3.50it/s]
  2%|▏         | 21/1261 [00:06<05:53,  3.51it/s]
  2%|▏         | 22/1261 [00:06<05:55,  3.49it/s]
  2%|▏         | 23/1261 [00:06<05:53,  3.50it/s]
  2%|▏         | 24/1261 [00:06<05:52,  3.51it/s]
  2%|▏         | 25/1261 [00:07<05:51,  3.52it/s]
  2%|▏         | 26/1261 [00:07<05:51,  3.51it/s]
  2%|▏         | 27/1261 [00:07<05:49,  3.53it/s]
  2%|▏         | 28/1261 [00:08<05:50,  3.51it/s]
  2%|▏         | 29/1261 [00:08<05:49,  3.52it/s]
  2%|▏         | 30/1261 [00:08<05:48,  3.53it/s]
  2%|▏         | 31/1261 [00:08<05:44,  3.57it/s]
  3%|▎         | 32/1261 [00:09<05:49,  3.52it/s]
  3%|▎         | 33/1261 [00:09<05:49,  3.51it/s]
  3%|▎         | 34/1261 [00:09<05:48,  3.52it/s]
  3%|▎         | 35/1261 [00:09<05:47,  3.53it/s]
  3%|▎         | 36/1261 [00:10<05:47,  3.53it/s]
  3%|▎         | 37/1261 [00:10<05:53,  3.46it/s]
  3%|▎         | 38/1261 [00:10<05:54,  3.45it/s]
  3%|▎         | 39/1261 [00:11<05:54,  3.45it/s]
  3%|▎         | 40/1261 [00:11<05:51,  3.47it/s]
  3%|▎         | 41/1261 [00:11<05:50,  3.48it/s]
  3%|▎         | 42/1261 [00:12<05:48,  3.50it/s]
  3%|▎         | 43/1261 [00:12<06:09,  3.30it/s]
  3%|▎         | 44/1261 [00:12<06:04,  3.34it/s]
  4%|▎         | 45/1261 [00:12<06:02,  3.35it/s]
  4%|▎         | 46/1261 [00:13<05:55,  3.42it/s]
  4%|▎         | 47/1261 [00:13<06:05,  3.32it/s]
  4%|▍         | 48/1261 [00:13<06:02,  3.34it/s]
  4%|▍         | 49/1261 [00:14<06:05,  3.31it/s]
  4%|▍         | 50/1261 [00:14<06:04,  3.33it/s]
  4%|▍         | 51/1261 [00:14<06:03,  3.33it/s]
  4%|▍         | 52/1261 [00:15<06:02,  3.34it/s]
  4%|▍         | 53/1261 [00:15<05:58,  3.37it/s]
  4%|▍         | 54/1261 [00:15<05:57,  3.38it/s]
  4%|▍         | 55/1261 [00:15<05:53,  3.41it/s]
  4%|▍         | 56/1261 [00:16<06:00,  3.34it/s]
  5%|▍         | 57/1261 [00:16<05:48,  3.45it/s]
  5%|▍         | 58/1261 [00:16<05:52,  3.41it/s]
  5%|▍         | 59/1261 [00:17<05:49,  3.44it/s]
  5%|▍         | 60/1261 [00:17<05:52,  3.41it/s]
  5%|▍         | 61/1261 [00:17<05:48,  3.44it/s]
  5%|▍         | 62/1261 [00:17<05:49,  3.43it/s]
  5%|▍         | 63/1261 [00:18<05:53,  3.38it/s]
  5%|▌         | 64/1261 [00:18<05:55,  3.37it/s]
  5%|▌         | 65/1261 [00:18<05:55,  3.37it/s]
  5%|▌         | 66/1261 [00:19<05:50,  3.41it/s]
  5%|▌         | 67/1261 [00:19<05:52,  3.39it/s]
  5%|▌         | 68/1261 [00:19<06:00,  3.31it/s]
  5%|▌         | 69/1261 [00:20<05:53,  3.37it/s]
  6%|▌         | 70/1261 [00:20<05:59,  3.32it/s]
  6%|▌         | 71/1261 [00:20<05:52,  3.38it/s]
  6%|▌         | 72/1261 [00:20<05:53,  3.36it/s]
  6%|▌         | 73/1261 [00:21<05:54,  3.35it/s]
  6%|▌         | 74/1261 [00:21<05:48,  3.41it/s]
  6%|▌         | 75/1261 [00:21<05:51,  3.37it/s]
  6%|▌         | 76/1261 [00:22<05:56,  3.33it/s]
  6%|▌         | 77/1261 [00:22<05:56,  3.32it/s]
  6%|▌         | 78/1261 [00:22<05:56,  3.31it/s]
  6%|▋         | 79/1261 [00:23<05:48,  3.39it/s]
  6%|▋         | 80/1261 [00:23<05:52,  3.35it/s]
  6%|▋         | 81/1261 [00:23<05:57,  3.30it/s]
  7%|▋         | 82/1261 [00:23<05:49,  3.37it/s]
  7%|▋         | 83/1261 [00:24<05:47,  3.39it/s]
  7%|▋         | 84/1261 [00:24<05:52,  3.34it/s]
  7%|▋         | 85/1261 [00:24<05:46,  3.39it/s]
  7%|▋         | 86/1261 [00:25<05:54,  3.31it/s]
  7%|▋         | 87/1261 [00:25<06:02,  3.24it/s]
  7%|▋         | 88/1261 [00:25<05:54,  3.31it/s]
  7%|▋         | 89/1261 [00:26<05:54,  3.31it/s]
  7%|▋         | 90/1261 [00:26<06:09,  3.17it/s]
  7%|▋         | 91/1261 [00:26<06:04,  3.21it/s]
  7%|▋         | 92/1261 [00:26<06:00,  3.24it/s]
  7%|▋         | 93/1261 [00:27<05:57,  3.27it/s]
  7%|▋         | 94/1261 [00:27<05:53,  3.30it/s]
  8%|▊         | 95/1261 [00:27<05:46,  3.36it/s]
  8%|▊         | 96/1261 [00:28<05:48,  3.34it/s]
  8%|▊         | 97/1261 [00:28<05:46,  3.36it/s]
  8%|▊         | 98/1261 [00:28<05:49,  3.33it/s]
  8%|▊         | 99/1261 [00:29<05:47,  3.34it/s]
  8%|▊         | 100/1261 [00:29<05:48,  3.33it/s]
  8%|▊         | 101/1261 [00:29<05:42,  3.39it/s]
  8%|▊         | 102/1261 [00:29<05:52,  3.29it/s]
  8%|▊         | 103/1261 [00:30<06:16,  3.08it/s]
  8%|▊         | 104/1261 [00:30<06:15,  3.08it/s]
  8%|▊         | 105/1261 [00:30<06:05,  3.16it/s]
  8%|▊         | 106/1261 [00:31<06:13,  3.09it/s]
  8%|▊         | 107/1261 [00:31<06:24,  3.00it/s]
  9%|▊         | 108/1261 [00:32<06:27,  2.97it/s]
  9%|▊         | 109/1261 [00:32<06:31,  2.94it/s]
  9%|▊         | 110/1261 [00:32<06:08,  3.12it/s]
  9%|▉         | 111/1261 [00:32<06:03,  3.16it/s]
  9%|▉         | 112/1261 [00:33<06:00,  3.18it/s]
  9%|▉         | 113/1261 [00:33<05:55,  3.23it/s]
  9%|▉         | 114/1261 [00:33<05:52,  3.25it/s]
  9%|▉         | 115/1261 [00:34<05:49,  3.28it/s]
  9%|▉         | 116/1261 [00:34<05:47,  3.29it/s]
  9%|▉         | 117/1261 [00:34<05:45,  3.31it/s]
  9%|▉         | 118/1261 [00:35<05:38,  3.38it/s]
  9%|▉         | 119/1261 [00:35<05:45,  3.30it/s]
 10%|▉         | 120/1261 [00:35<05:39,  3.36it/s]
 10%|▉         | 121/1261 [00:35<05:44,  3.31it/s]
 10%|▉         | 122/1261 [00:36<05:44,  3.31it/s]
 10%|▉         | 123/1261 [00:36<05:37,  3.38it/s]
 10%|▉         | 124/1261 [00:36<05:39,  3.35it/s]
 10%|▉         | 125/1261 [00:37<05:38,  3.36it/s]
 10%|▉         | 126/1261 [00:37<05:38,  3.35it/s]
 10%|█         | 127/1261 [00:37<05:45,  3.29it/s]
 10%|█         | 128/1261 [00:38<05:43,  3.30it/s]
 10%|█         | 129/1261 [00:38<05:42,  3.31it/s]
 10%|█         | 130/1261 [00:38<05:40,  3.32it/s]
 10%|█         | 131/1261 [00:38<05:34,  3.38it/s]
 10%|█         | 132/1261 [00:39<05:40,  3.32it/s]
 11%|█         | 133/1261 [00:39<05:35,  3.36it/s]
 11%|█         | 134/1261 [00:39<05:35,  3.36it/s]
 11%|█         | 135/1261 [00:40<05:35,  3.36it/s]
 11%|█         | 136/1261 [00:40<05:36,  3.34it/s]
 11%|█         | 137/1261 [00:40<05:39,  3.31it/s]
 11%|█         | 138/1261 [00:41<05:35,  3.35it/s]
 11%|█         | 139/1261 [00:41<05:36,  3.34it/s]
 11%|█         | 140/1261 [00:41<05:29,  3.40it/s]
 11%|█         | 141/1261 [00:41<05:35,  3.34it/s]
 11%|█▏        | 142/1261 [00:42<05:33,  3.35it/s]
 11%|█▏        | 143/1261 [00:42<05:31,  3.38it/s]
 11%|█▏        | 144/1261 [00:42<05:32,  3.36it/s]
 11%|█▏        | 145/1261 [00:43<05:27,  3.41it/s]
 12%|█▏        | 146/1261 [00:43<05:39,  3.29it/s]
 12%|█▏        | 147/1261 [00:43<05:48,  3.19it/s]
 12%|█▏        | 148/1261 [00:44<05:45,  3.23it/s]
 12%|█▏        | 149/1261 [00:44<05:49,  3.18it/s]
 12%|█▏        | 150/1261 [00:44<05:42,  3.25it/s]
 12%|█▏        | 151/1261 [00:44<05:36,  3.30it/s]
 12%|█▏        | 152/1261 [00:45<05:31,  3.34it/s]
 12%|█▏        | 153/1261 [00:45<05:38,  3.28it/s]
 12%|█▏        | 154/1261 [00:45<05:30,  3.35it/s]
 12%|█▏        | 155/1261 [00:46<05:30,  3.35it/s]
 12%|█▏        | 156/1261 [00:46<05:30,  3.34it/s]
 12%|█▏        | 157/1261 [00:46<05:24,  3.40it/s]
 13%|█▎        | 158/1261 [00:47<05:27,  3.37it/s]
 13%|█▎        | 159/1261 [00:47<05:26,  3.38it/s]
 13%|█▎        | 160/1261 [00:47<05:23,  3.41it/s]
 13%|█▎        | 161/1261 [00:47<05:24,  3.39it/s]
 13%|█▎        | 162/1261 [00:48<05:26,  3.36it/s]
 13%|█▎        | 163/1261 [00:48<05:29,  3.33it/s]
 13%|█▎        | 164/1261 [00:48<05:36,  3.26it/s]
 13%|█▎        | 165/1261 [00:49<05:30,  3.32it/s]
 13%|█▎        | 166/1261 [00:49<05:34,  3.27it/s]
 13%|█▎        | 167/1261 [00:49<05:36,  3.25it/s]
 13%|█▎        | 168/1261 [00:50<05:31,  3.30it/s]
 13%|█▎        | 169/1261 [00:50<05:33,  3.28it/s]
 13%|█▎        | 170/1261 [00:50<05:24,  3.36it/s]
 14%|█▎        | 171/1261 [00:50<05:25,  3.35it/s]
 14%|█▎        | 172/1261 [00:51<05:19,  3.41it/s]
 14%|█▎        | 173/1261 [00:51<05:21,  3.38it/s]
 14%|█▍        | 174/1261 [00:51<05:23,  3.36it/s]
 14%|█▍        | 175/1261 [00:52<05:28,  3.30it/s]
 14%|█▍        | 176/1261 [00:52<05:22,  3.37it/s]
 14%|█▍        | 177/1261 [00:52<05:28,  3.30it/s]
 14%|█▍        | 178/1261 [00:53<05:27,  3.31it/s]
 14%|█▍        | 179/1261 [00:53<05:24,  3.33it/s]
 14%|█▍        | 180/1261 [00:53<05:20,  3.37it/s]
 14%|█▍        | 181/1261 [00:53<05:21,  3.36it/s]
 14%|█▍        | 182/1261 [00:54<05:21,  3.35it/s]
 15%|█▍        | 183/1261 [00:54<05:22,  3.34it/s]
 15%|█▍        | 184/1261 [00:54<05:12,  3.45it/s]
 15%|█▍        | 185/1261 [00:55<05:13,  3.43it/s]
 15%|█▍        | 186/1261 [00:55<05:11,  3.45it/s]
 15%|█▍        | 187/1261 [00:55<05:21,  3.34it/s]
 15%|█▍        | 188/1261 [00:56<05:14,  3.41it/s]
 15%|█▍        | 189/1261 [00:56<05:16,  3.38it/s]
 15%|█▌        | 190/1261 [00:56<05:17,  3.37it/s]
 15%|█▌        | 191/1261 [00:56<05:17,  3.37it/s]
 15%|█▌        | 192/1261 [00:57<05:18,  3.35it/s]
 15%|█▌        | 193/1261 [00:57<05:18,  3.35it/s]
 15%|█▌        | 194/1261 [00:57<05:20,  3.33it/s]
 15%|█▌        | 195/1261 [00:58<05:17,  3.36it/s]
 16%|█▌        | 196/1261 [00:58<05:14,  3.39it/s]
 16%|█▌        | 197/1261 [00:58<05:16,  3.37it/s]
 16%|█▌        | 198/1261 [00:59<05:21,  3.30it/s]
 16%|█▌        | 199/1261 [00:59<05:14,  3.37it/s]
 16%|█▌        | 200/1261 [00:59<05:15,  3.36it/s]
 16%|█▌        | 201/1261 [00:59<05:11,  3.41it/s]
 16%|█▌        | 202/1261 [01:00<05:10,  3.41it/s]
 16%|█▌        | 203/1261 [01:00<05:15,  3.35it/s]
 16%|█▌        | 204/1261 [01:00<05:15,  3.35it/s]
 16%|█▋        | 205/1261 [01:01<05:15,  3.35it/s]
 16%|█▋        | 206/1261 [01:01<05:12,  3.37it/s]
 16%|█▋        | 207/1261 [01:01<05:12,  3.38it/s]
 16%|█▋        | 208/1261 [01:01<05:15,  3.34it/s]
 17%|█▋        | 209/1261 [01:02<05:13,  3.35it/s]
 17%|█▋        | 210/1261 [01:02<05:16,  3.32it/s]
 17%|█▋        | 211/1261 [01:02<05:11,  3.37it/s]
 17%|█▋        | 212/1261 [01:03<05:10,  3.38it/s]
 17%|█▋        | 213/1261 [01:03<05:13,  3.35it/s]
 17%|█▋        | 214/1261 [01:03<05:09,  3.38it/s]
 17%|█▋        | 215/1261 [01:04<05:13,  3.34it/s]
 17%|█▋        | 216/1261 [01:04<05:19,  3.27it/s]
 17%|█▋        | 217/1261 [01:04<05:17,  3.29it/s]
 17%|█▋        | 218/1261 [01:04<05:10,  3.36it/s]
 17%|█▋        | 219/1261 [01:05<05:10,  3.35it/s]
 17%|█▋        | 220/1261 [01:05<05:10,  3.35it/s]
 18%|█▊        | 221/1261 [01:05<05:11,  3.34it/s]
 18%|█▊        | 222/1261 [01:06<05:06,  3.39it/s]
 18%|█▊        | 223/1261 [01:06<05:12,  3.32it/s]
 18%|█▊        | 224/1261 [01:06<05:06,  3.39it/s]
 18%|█▊        | 225/1261 [01:07<05:08,  3.36it/s]
 18%|█▊        | 226/1261 [01:07<05:03,  3.41it/s]
 18%|█▊        | 227/1261 [01:07<05:09,  3.34it/s]
 18%|█▊        | 228/1261 [01:07<05:04,  3.39it/s]
 18%|█▊        | 229/1261 [01:08<05:04,  3.39it/s]
 18%|█▊        | 230/1261 [01:08<05:02,  3.41it/s]
 18%|█▊        | 231/1261 [01:08<05:03,  3.39it/s]
 18%|█▊        | 232/1261 [01:09<04:59,  3.43it/s]
 18%|█▊        | 233/1261 [01:09<05:03,  3.38it/s]
 19%|█▊        | 234/1261 [01:09<05:04,  3.38it/s]
 19%|█▊        | 235/1261 [01:10<05:09,  3.31it/s]
 19%|█▊        | 236/1261 [01:10<05:03,  3.38it/s]
 19%|█▉        | 237/1261 [01:10<05:05,  3.36it/s]
 19%|█▉        | 238/1261 [01:10<05:00,  3.40it/s]
 19%|█▉        | 239/1261 [01:11<05:09,  3.30it/s]
 19%|█▉        | 240/1261 [01:11<05:06,  3.33it/s]
 19%|█▉        | 241/1261 [01:11<05:23,  3.16it/s]
 19%|█▉        | 242/1261 [01:12<05:33,  3.06it/s]
 19%|█▉        | 243/1261 [01:12<05:48,  2.92it/s]
 19%|█▉        | 244/1261 [01:12<05:50,  2.90it/s]
 19%|█▉        | 245/1261 [01:13<05:46,  2.93it/s]
 20%|█▉        | 246/1261 [01:13<05:43,  2.95it/s]
 20%|█▉        | 247/1261 [01:13<05:45,  2.93it/s]
 20%|█▉        | 248/1261 [01:14<05:30,  3.06it/s]
 20%|█▉        | 249/1261 [01:14<05:26,  3.10it/s]
 20%|█▉        | 250/1261 [01:14<05:15,  3.21it/s]
 20%|█▉        | 251/1261 [01:15<05:11,  3.24it/s]
 20%|█▉        | 252/1261 [01:15<05:18,  3.16it/s]
 20%|██        | 253/1261 [01:15<05:28,  3.07it/s]
 20%|██        | 254/1261 [01:16<05:39,  2.96it/s]
 20%|██        | 255/1261 [01:16<05:43,  2.93it/s]
 20%|██        | 256/1261 [01:16<05:41,  2.94it/s]
 20%|██        | 257/1261 [01:17<05:48,  2.88it/s]
 20%|██        | 258/1261 [01:17<05:31,  3.03it/s]
 21%|██        | 259/1261 [01:17<05:15,  3.18it/s]
 21%|██        | 260/1261 [01:18<05:08,  3.24it/s]
 21%|██        | 261/1261 [01:18<05:04,  3.29it/s]
 21%|██        | 262/1261 [01:18<04:57,  3.36it/s]
 21%|██        | 263/1261 [01:18<04:57,  3.36it/s]
 21%|██        | 264/1261 [01:19<04:59,  3.33it/s]
 21%|██        | 265/1261 [01:19<05:01,  3.31it/s]
 21%|██        | 266/1261 [01:19<05:01,  3.30it/s]
 21%|██        | 267/1261 [01:20<05:00,  3.31it/s]
 21%|██▏       | 268/1261 [01:20<04:55,  3.36it/s]
 21%|██▏       | 269/1261 [01:20<04:54,  3.37it/s]
 21%|██▏       | 270/1261 [01:21<04:56,  3.34it/s]
 21%|██▏       | 271/1261 [01:21<04:50,  3.40it/s]
 22%|██▏       | 272/1261 [01:21<05:10,  3.18it/s]
 22%|██▏       | 273/1261 [01:22<05:07,  3.21it/s]
 22%|██▏       | 274/1261 [01:22<05:44,  2.87it/s]
 22%|██▏       | 275/1261 [01:22<05:42,  2.88it/s]
 22%|██▏       | 276/1261 [01:23<05:37,  2.92it/s]
 22%|██▏       | 277/1261 [01:23<05:21,  3.06it/s]
 22%|██▏       | 278/1261 [01:23<05:12,  3.15it/s]
 22%|██▏       | 279/1261 [01:24<05:13,  3.13it/s]
 22%|██▏       | 280/1261 [01:24<05:03,  3.23it/s]
 22%|██▏       | 281/1261 [01:24<05:03,  3.23it/s]
 22%|██▏       | 282/1261 [01:25<05:22,  3.04it/s]
 22%|██▏       | 283/1261 [01:25<05:17,  3.08it/s]
 23%|██▎       | 284/1261 [01:25<05:18,  3.07it/s]
 23%|██▎       | 285/1261 [01:25<05:14,  3.10it/s]
 23%|██▎       | 286/1261 [01:26<05:08,  3.16it/s]
 23%|██▎       | 287/1261 [01:26<05:20,  3.04it/s]
 23%|██▎       | 288/1261 [01:26<05:13,  3.10it/s]
 23%|██▎       | 289/1261 [01:27<05:06,  3.17it/s]
 23%|██▎       | 290/1261 [01:27<05:02,  3.21it/s]
 23%|██▎       | 291/1261 [01:27<04:57,  3.26it/s]
 23%|██▎       | 292/1261 [01:28<04:51,  3.33it/s]
 23%|██▎       | 293/1261 [01:28<04:59,  3.23it/s]
 23%|██▎       | 294/1261 [01:28<04:52,  3.30it/s]
 23%|██▎       | 295/1261 [01:29<05:07,  3.14it/s]
 23%|██▎       | 296/1261 [01:29<05:06,  3.15it/s]
 24%|██▎       | 297/1261 [01:29<04:55,  3.27it/s]
 24%|██▎       | 298/1261 [01:29<04:48,  3.34it/s]
 24%|██▎       | 299/1261 [01:30<04:44,  3.38it/s]
 24%|██▍       | 300/1261 [01:30<04:38,  3.45it/s]
 24%|██▍       | 301/1261 [01:30<04:46,  3.35it/s]
 24%|██▍       | 302/1261 [01:31<04:47,  3.34it/s]
 24%|██▍       | 303/1261 [01:31<05:05,  3.14it/s]
 24%|██▍       | 304/1261 [01:31<04:56,  3.23it/s]
 24%|██▍       | 305/1261 [01:32<04:53,  3.26it/s]
 24%|██▍       | 306/1261 [01:32<04:50,  3.29it/s]
 24%|██▍       | 307/1261 [01:32<05:03,  3.15it/s]
 24%|██▍       | 308/1261 [01:33<04:57,  3.20it/s]
 25%|██▍       | 309/1261 [01:33<04:48,  3.30it/s]
 25%|██▍       | 310/1261 [01:33<05:04,  3.13it/s]
 25%|██▍       | 311/1261 [01:33<04:55,  3.21it/s]
 25%|██▍       | 312/1261 [01:34<04:52,  3.25it/s]
 25%|██▍       | 313/1261 [01:34<04:56,  3.20it/s]
 25%|██▍       | 314/1261 [01:34<04:54,  3.21it/s]
 25%|██▍       | 315/1261 [01:35<04:46,  3.30it/s]
 25%|██▌       | 316/1261 [01:35<04:44,  3.32it/s]
 25%|██▌       | 317/1261 [01:35<04:44,  3.32it/s]
 25%|██▌       | 318/1261 [01:36<04:41,  3.35it/s]
 25%|██▌       | 319/1261 [01:36<04:40,  3.36it/s]
 25%|██▌       | 320/1261 [01:36<04:44,  3.30it/s]
 25%|██▌       | 321/1261 [01:36<04:42,  3.33it/s]
 26%|██▌       | 322/1261 [01:37<04:48,  3.25it/s]
 26%|██▌       | 323/1261 [01:37<04:51,  3.22it/s]
 26%|██▌       | 324/1261 [01:37<04:46,  3.27it/s]
 26%|██▌       | 325/1261 [01:38<04:40,  3.34it/s]
 26%|██▌       | 326/1261 [01:38<04:40,  3.33it/s]
 26%|██▌       | 327/1261 [01:38<04:37,  3.37it/s]
 26%|██▌       | 328/1261 [01:39<04:39,  3.34it/s]
 26%|██▌       | 329/1261 [01:39<04:35,  3.38it/s]
 26%|██▌       | 330/1261 [01:39<04:41,  3.31it/s]
 26%|██▌       | 331/1261 [01:40<04:40,  3.31it/s]
 26%|██▋       | 332/1261 [01:40<04:39,  3.32it/s]
 26%|██▋       | 333/1261 [01:40<04:36,  3.35it/s]
 26%|██▋       | 334/1261 [01:40<04:33,  3.39it/s]
 27%|██▋       | 335/1261 [01:41<04:31,  3.41it/s]
 27%|██▋       | 336/1261 [01:41<04:31,  3.41it/s]
 27%|██▋       | 337/1261 [01:41<04:29,  3.43it/s]
 27%|██▋       | 338/1261 [01:42<04:30,  3.41it/s]
 27%|██▋       | 339/1261 [01:42<04:28,  3.43it/s]
 27%|██▋       | 340/1261 [01:42<04:29,  3.42it/s]
 27%|██▋       | 341/1261 [01:42<04:27,  3.44it/s]
 27%|██▋       | 342/1261 [01:43<04:29,  3.40it/s]
 27%|██▋       | 343/1261 [01:43<04:30,  3.39it/s]
 27%|██▋       | 344/1261 [01:43<04:32,  3.37it/s]
 27%|██▋       | 345/1261 [01:44<04:27,  3.42it/s]
 27%|██▋       | 346/1261 [01:44<04:29,  3.39it/s]
 28%|██▊       | 347/1261 [01:44<04:26,  3.43it/s]
 28%|██▊       | 348/1261 [01:45<04:33,  3.34it/s]
 28%|██▊       | 349/1261 [01:45<04:27,  3.41it/s]
 28%|██▊       | 350/1261 [01:45<04:25,  3.43it/s]
 28%|██▊       | 351/1261 [01:45<04:25,  3.43it/s]
 28%|██▊       | 352/1261 [01:46<04:28,  3.38it/s]
 28%|██▊       | 353/1261 [01:46<04:29,  3.37it/s]
 28%|██▊       | 354/1261 [01:46<04:30,  3.35it/s]
 28%|██▊       | 355/1261 [01:47<04:26,  3.39it/s]
 28%|██▊       | 356/1261 [01:47<04:26,  3.39it/s]
 28%|██▊       | 357/1261 [01:47<04:29,  3.36it/s]
 28%|██▊       | 358/1261 [01:47<04:28,  3.37it/s]
 28%|██▊       | 359/1261 [01:48<04:25,  3.40it/s]
 29%|██▊       | 360/1261 [01:48<04:30,  3.33it/s]
 29%|██▊       | 361/1261 [01:48<04:25,  3.39it/s]
 29%|██▊       | 362/1261 [01:49<04:26,  3.37it/s]
 29%|██▉       | 363/1261 [01:49<04:22,  3.42it/s]
 29%|██▉       | 364/1261 [01:49<04:25,  3.38it/s]
 29%|██▉       | 365/1261 [01:50<04:37,  3.23it/s]
 29%|██▉       | 366/1261 [01:50<04:49,  3.10it/s]
 29%|██▉       | 367/1261 [01:50<04:44,  3.14it/s]
 29%|██▉       | 368/1261 [01:51<04:40,  3.18it/s]
 29%|██▉       | 369/1261 [01:51<04:37,  3.21it/s]
 29%|██▉       | 370/1261 [01:51<04:43,  3.14it/s]
 29%|██▉       | 371/1261 [01:52<04:43,  3.14it/s]
 30%|██▉       | 372/1261 [01:52<04:53,  3.03it/s]
 30%|██▉       | 373/1261 [01:52<04:50,  3.06it/s]
 30%|██▉       | 374/1261 [01:52<04:47,  3.08it/s]
 30%|██▉       | 375/1261 [01:53<04:59,  2.96it/s]
 30%|██▉       | 376/1261 [01:53<04:56,  2.99it/s]
 30%|██▉       | 377/1261 [01:54<04:59,  2.95it/s]
 30%|██▉       | 378/1261 [01:54<04:51,  3.02it/s]
 30%|███       | 379/1261 [01:54<04:54,  3.00it/s]
 30%|███       | 380/1261 [01:54<04:42,  3.11it/s]
 30%|███       | 381/1261 [01:55<04:48,  3.05it/s]
 30%|███       | 382/1261 [01:55<04:43,  3.10it/s]
 30%|███       | 383/1261 [01:55<04:35,  3.19it/s]
 30%|███       | 384/1261 [01:56<04:34,  3.20it/s]
 31%|███       | 385/1261 [01:56<04:26,  3.28it/s]
 31%|███       | 386/1261 [01:56<04:26,  3.29it/s]
 31%|███       | 387/1261 [01:57<04:27,  3.27it/s]
 31%|███       | 388/1261 [01:57<04:23,  3.32it/s]
 31%|███       | 389/1261 [01:57<04:34,  3.18it/s]
 31%|███       | 390/1261 [01:58<04:58,  2.92it/s]
 31%|███       | 391/1261 [01:58<04:58,  2.91it/s]
 31%|███       | 392/1261 [01:58<04:47,  3.03it/s]
 31%|███       | 393/1261 [01:59<04:48,  3.01it/s]
 31%|███       | 394/1261 [01:59<05:04,  2.85it/s]
 31%|███▏      | 395/1261 [01:59<04:46,  3.02it/s]
 31%|███▏      | 396/1261 [02:00<04:42,  3.06it/s]
 31%|███▏      | 397/1261 [02:00<04:54,  2.93it/s]
 32%|███▏      | 398/1261 [02:00<04:46,  3.01it/s]
 32%|███▏      | 399/1261 [02:01<04:53,  2.93it/s]
 32%|███▏      | 400/1261 [02:01<04:54,  2.92it/s]
 32%|███▏      | 401/1261 [02:01<04:47,  2.99it/s]
 32%|███▏      | 402/1261 [02:02<04:51,  2.95it/s]
 32%|███▏      | 403/1261 [02:02<04:39,  3.07it/s]
 32%|███▏      | 404/1261 [02:02<04:32,  3.15it/s]
 32%|███▏      | 405/1261 [02:03<04:22,  3.26it/s]
 32%|███▏      | 406/1261 [02:03<04:21,  3.27it/s]
 32%|███▏      | 407/1261 [02:03<04:15,  3.35it/s]
 32%|███▏      | 408/1261 [02:03<04:14,  3.35it/s]
 32%|███▏      | 409/1261 [02:04<04:18,  3.29it/s]
 33%|███▎      | 410/1261 [02:04<04:17,  3.30it/s]
 33%|███▎      | 411/1261 [02:04<04:11,  3.37it/s]
 33%|███▎      | 412/1261 [02:05<04:14,  3.33it/s]
 33%|███▎      | 413/1261 [02:05<04:17,  3.30it/s]
 33%|███▎      | 414/1261 [02:05<04:11,  3.37it/s]
 33%|███▎      | 415/1261 [02:06<04:09,  3.39it/s]
 33%|███▎      | 416/1261 [02:06<04:12,  3.34it/s]
 33%|███▎      | 417/1261 [02:06<04:08,  3.39it/s]
 33%|███▎      | 418/1261 [02:06<04:09,  3.38it/s]
 33%|███▎      | 419/1261 [02:07<04:15,  3.29it/s]
 33%|███▎      | 420/1261 [02:07<04:17,  3.27it/s]
 33%|███▎      | 421/1261 [02:07<04:23,  3.19it/s]
 33%|███▎      | 422/1261 [02:08<04:23,  3.19it/s]
 34%|███▎      | 423/1261 [02:08<04:16,  3.27it/s]
 34%|███▎      | 424/1261 [02:08<04:14,  3.29it/s]
 34%|███▎      | 425/1261 [02:09<04:08,  3.36it/s]
 34%|███▍      | 426/1261 [02:09<04:10,  3.34it/s]
 34%|███▍      | 427/1261 [02:09<04:05,  3.40it/s]
 34%|███▍      | 428/1261 [02:10<04:09,  3.34it/s]
 34%|███▍      | 429/1261 [02:10<04:06,  3.38it/s]
 34%|███▍      | 430/1261 [02:10<04:07,  3.36it/s]
 34%|███▍      | 431/1261 [02:10<04:02,  3.42it/s]
 34%|███▍      | 432/1261 [02:11<04:04,  3.39it/s]
 34%|███▍      | 433/1261 [02:11<04:01,  3.43it/s]
 34%|███▍      | 434/1261 [02:11<04:04,  3.38it/s]
 34%|███▍      | 435/1261 [02:12<04:04,  3.38it/s]
 35%|███▍      | 436/1261 [02:12<04:10,  3.30it/s]
 35%|███▍      | 437/1261 [02:12<04:08,  3.32it/s]
 35%|███▍      | 438/1261 [02:12<04:05,  3.35it/s]
 35%|███▍      | 439/1261 [02:13<04:07,  3.32it/s]
 35%|███▍      | 440/1261 [02:13<04:07,  3.32it/s]
 35%|███▍      | 441/1261 [02:13<04:01,  3.39it/s]
 35%|███▌      | 442/1261 [02:14<04:02,  3.37it/s]
 35%|███▌      | 443/1261 [02:14<04:03,  3.35it/s]
 35%|███▌      | 444/1261 [02:14<04:03,  3.35it/s]
 35%|███▌      | 445/1261 [02:15<04:02,  3.36it/s]
 35%|███▌      | 446/1261 [02:15<04:05,  3.32it/s]
 35%|███▌      | 447/1261 [02:15<04:02,  3.36it/s]
 36%|███▌      | 448/1261 [02:15<03:59,  3.40it/s]
 36%|███▌      | 449/1261 [02:16<04:01,  3.37it/s]
 36%|███▌      | 450/1261 [02:16<04:05,  3.31it/s]
 36%|███▌      | 451/1261 [02:16<03:59,  3.38it/s]
 36%|███▌      | 452/1261 [02:17<03:56,  3.42it/s]
 36%|███▌      | 453/1261 [02:17<03:54,  3.45it/s]
 36%|███▌      | 454/1261 [02:17<03:56,  3.41it/s]
 36%|███▌      | 455/1261 [02:18<03:57,  3.39it/s]
 36%|███▌      | 456/1261 [02:18<03:58,  3.38it/s]
 36%|███▌      | 457/1261 [02:18<03:59,  3.36it/s]
 36%|███▋      | 458/1261 [02:18<03:55,  3.41it/s]
 36%|███▋      | 459/1261 [02:19<03:56,  3.39it/s]
 36%|███▋      | 460/1261 [02:19<04:01,  3.32it/s]
 37%|███▋      | 461/1261 [02:19<04:01,  3.32it/s]
 37%|███▋      | 462/1261 [02:20<04:00,  3.32it/s]
 37%|███▋      | 463/1261 [02:20<03:56,  3.38it/s]
 37%|███▋      | 464/1261 [02:20<03:56,  3.37it/s]
 37%|███▋      | 465/1261 [02:20<03:53,  3.41it/s]
 37%|███▋      | 466/1261 [02:21<03:58,  3.33it/s]
 37%|███▋      | 467/1261 [02:21<03:54,  3.39it/s]
 37%|███▋      | 468/1261 [02:21<03:55,  3.37it/s]
 37%|███▋      | 469/1261 [02:22<03:51,  3.42it/s]
 37%|███▋      | 470/1261 [02:22<03:53,  3.39it/s]
 37%|███▋      | 471/1261 [02:22<03:53,  3.39it/s]
 37%|███▋      | 472/1261 [02:23<03:54,  3.36it/s]
 38%|███▊      | 473/1261 [02:23<03:53,  3.37it/s]
 38%|███▊      | 474/1261 [02:23<03:54,  3.35it/s]
 38%|███▊      | 475/1261 [02:23<03:53,  3.37it/s]
 38%|███▊      | 476/1261 [02:24<03:59,  3.28it/s]
 38%|███▊      | 477/1261 [02:24<03:56,  3.32it/s]
 38%|███▊      | 478/1261 [02:24<03:58,  3.28it/s]
 38%|███▊      | 479/1261 [02:25<03:52,  3.36it/s]
 38%|███▊      | 480/1261 [02:25<03:52,  3.36it/s]
 38%|███▊      | 481/1261 [02:25<03:53,  3.34it/s]
 38%|███▊      | 482/1261 [02:26<03:52,  3.35it/s]
 38%|███▊      | 483/1261 [02:26<03:48,  3.40it/s]
 38%|███▊      | 484/1261 [02:26<03:56,  3.29it/s]
 38%|███▊      | 485/1261 [02:27<04:10,  3.09it/s]
 39%|███▊      | 486/1261 [02:27<04:07,  3.13it/s]
 39%|███▊      | 487/1261 [02:27<04:01,  3.21it/s]
 39%|███▊      | 488/1261 [02:27<04:01,  3.20it/s]
 39%|███▉      | 489/1261 [02:28<03:54,  3.29it/s]
 39%|███▉      | 490/1261 [02:28<03:53,  3.30it/s]
 39%|███▉      | 491/1261 [02:28<03:55,  3.27it/s]
 39%|███▉      | 492/1261 [02:29<03:54,  3.28it/s]
 39%|███▉      | 493/1261 [02:29<03:51,  3.31it/s]
 39%|███▉      | 494/1261 [02:29<03:45,  3.40it/s]
 39%|███▉      | 495/1261 [02:30<03:47,  3.37it/s]
 39%|███▉      | 496/1261 [02:30<03:50,  3.32it/s]
 39%|███▉      | 497/1261 [02:30<03:57,  3.22it/s]
 39%|███▉      | 498/1261 [02:30<03:55,  3.24it/s]
 40%|███▉      | 499/1261 [02:31<03:52,  3.28it/s]
 40%|███▉      | 500/1261 [02:31<04:00,  3.17it/s]
 40%|███▉      | 501/1261 [02:31<03:51,  3.29it/s]
 40%|███▉      | 502/1261 [02:32<03:49,  3.31it/s]
 40%|███▉      | 503/1261 [02:32<03:46,  3.35it/s]
 40%|███▉      | 504/1261 [02:32<03:48,  3.31it/s]
 40%|████      | 505/1261 [02:33<03:46,  3.33it/s]
 40%|████      | 506/1261 [02:33<03:44,  3.37it/s]
 40%|████      | 507/1261 [02:33<03:41,  3.41it/s]
 40%|████      | 508/1261 [02:33<03:47,  3.31it/s]
 40%|████      | 509/1261 [02:34<03:41,  3.39it/s]
 40%|████      | 510/1261 [02:34<03:49,  3.28it/s]
 41%|████      | 511/1261 [02:34<03:44,  3.34it/s]
 41%|████      | 512/1261 [02:35<03:40,  3.40it/s]
 41%|████      | 513/1261 [02:35<03:40,  3.39it/s]
 41%|████      | 514/1261 [02:35<03:42,  3.36it/s]
 41%|████      | 515/1261 [02:36<03:40,  3.38it/s]
 41%|████      | 516/1261 [02:36<03:39,  3.40it/s]
 41%|████      | 517/1261 [02:36<03:36,  3.43it/s]
 41%|████      | 518/1261 [02:36<03:38,  3.41it/s]
 41%|████      | 519/1261 [02:37<03:39,  3.38it/s]
 41%|████      | 520/1261 [02:37<03:39,  3.37it/s]
 41%|████▏     | 521/1261 [02:37<03:41,  3.35it/s]
 41%|████▏     | 522/1261 [02:38<03:40,  3.36it/s]
 41%|████▏     | 523/1261 [02:38<03:37,  3.39it/s]
 42%|████▏     | 524/1261 [02:38<03:41,  3.32it/s]
 42%|████▏     | 525/1261 [02:39<03:50,  3.20it/s]
 42%|████▏     | 526/1261 [02:39<03:57,  3.09it/s]
 42%|████▏     | 527/1261 [02:39<03:50,  3.18it/s]
 42%|████▏     | 528/1261 [02:40<03:47,  3.23it/s]
 42%|████▏     | 529/1261 [02:40<03:44,  3.26it/s]
 42%|████▏     | 530/1261 [02:40<03:43,  3.27it/s]
 42%|████▏     | 531/1261 [02:40<03:40,  3.31it/s]
 42%|████▏     | 532/1261 [02:41<03:42,  3.28it/s]
 42%|████▏     | 533/1261 [02:41<03:39,  3.32it/s]
 42%|████▏     | 534/1261 [02:41<03:34,  3.39it/s]
 42%|████▏     | 535/1261 [02:42<03:33,  3.40it/s]
 43%|████▎     | 536/1261 [02:42<03:36,  3.35it/s]
 43%|████▎     | 537/1261 [02:42<03:31,  3.42it/s]
 43%|████▎     | 538/1261 [02:42<03:34,  3.37it/s]
 43%|████▎     | 539/1261 [02:43<03:31,  3.41it/s]
 43%|████▎     | 540/1261 [02:43<03:38,  3.30it/s]
 43%|████▎     | 541/1261 [02:43<03:35,  3.34it/s]
 43%|████▎     | 542/1261 [02:44<03:38,  3.29it/s]
 43%|████▎     | 543/1261 [02:44<03:35,  3.33it/s]
 43%|████▎     | 544/1261 [02:44<03:36,  3.31it/s]
 43%|████▎     | 545/1261 [02:45<03:36,  3.31it/s]
 43%|████▎     | 546/1261 [02:45<03:37,  3.28it/s]
 43%|████▎     | 547/1261 [02:45<03:47,  3.14it/s]
 43%|████▎     | 548/1261 [02:46<03:57,  3.00it/s]
 44%|████▎     | 549/1261 [02:46<04:06,  2.88it/s]
 44%|████▎     | 550/1261 [02:46<04:11,  2.82it/s]
 44%|████▎     | 551/1261 [02:47<04:10,  2.84it/s]
 44%|████▍     | 552/1261 [02:47<04:04,  2.90it/s]
 44%|████▍     | 553/1261 [02:47<04:13,  2.79it/s]
 44%|████▍     | 554/1261 [02:48<04:13,  2.79it/s]
 44%|████▍     | 555/1261 [02:48<04:11,  2.81it/s]
 44%|████▍     | 556/1261 [02:49<04:11,  2.80it/s]
 44%|████▍     | 557/1261 [02:49<04:20,  2.70it/s]
 44%|████▍     | 558/1261 [02:49<04:13,  2.78it/s]
 44%|████▍     | 559/1261 [02:50<04:08,  2.83it/s]
 44%|████▍     | 560/1261 [02:50<04:04,  2.87it/s]
 44%|████▍     | 561/1261 [02:50<03:54,  2.99it/s]
 45%|████▍     | 562/1261 [02:51<04:01,  2.89it/s]
 45%|████▍     | 563/1261 [02:51<03:50,  3.03it/s]
 45%|████▍     | 564/1261 [02:51<03:51,  3.01it/s]
 45%|████▍     | 565/1261 [02:52<03:45,  3.09it/s]
 45%|████▍     | 566/1261 [02:52<03:44,  3.10it/s]
 45%|████▍     | 567/1261 [02:52<03:47,  3.06it/s]
 45%|████▌     | 568/1261 [02:52<03:40,  3.15it/s]
 45%|████▌     | 569/1261 [02:53<03:42,  3.11it/s]
 45%|████▌     | 570/1261 [02:53<03:41,  3.12it/s]
 45%|████▌     | 571/1261 [02:53<03:46,  3.05it/s]
 45%|████▌     | 572/1261 [02:54<03:48,  3.02it/s]
 45%|████▌     | 573/1261 [02:54<03:57,  2.90it/s]
 46%|████▌     | 574/1261 [02:55<03:50,  2.98it/s]
 46%|████▌     | 575/1261 [02:55<03:43,  3.06it/s]
 46%|████▌     | 576/1261 [02:55<03:37,  3.15it/s]
 46%|████▌     | 577/1261 [02:55<03:37,  3.14it/s]
 46%|████▌     | 578/1261 [02:56<03:34,  3.18it/s]
 46%|████▌     | 579/1261 [02:56<03:33,  3.19it/s]
 46%|████▌     | 580/1261 [02:56<03:42,  3.07it/s]
 46%|████▌     | 581/1261 [02:57<03:42,  3.06it/s]
 46%|████▌     | 582/1261 [02:57<03:37,  3.12it/s]
 46%|████▌     | 583/1261 [02:57<03:29,  3.24it/s]
 46%|████▋     | 584/1261 [02:58<03:26,  3.28it/s]
 46%|████▋     | 585/1261 [02:58<03:19,  3.39it/s]
 46%|████▋     | 586/1261 [02:58<03:19,  3.38it/s]
 47%|████▋     | 587/1261 [02:58<03:16,  3.43it/s]
 47%|████▋     | 588/1261 [02:59<03:17,  3.41it/s]
 47%|████▋     | 589/1261 [02:59<03:15,  3.43it/s]
 47%|████▋     | 590/1261 [02:59<03:19,  3.36it/s]
 47%|████▋     | 591/1261 [03:00<03:25,  3.26it/s]
 47%|████▋     | 592/1261 [03:00<03:26,  3.24it/s]
 47%|████▋     | 593/1261 [03:00<03:25,  3.24it/s]
 47%|████▋     | 594/1261 [03:01<03:34,  3.11it/s]
 47%|████▋     | 595/1261 [03:01<03:35,  3.09it/s]
 47%|████▋     | 596/1261 [03:01<03:49,  2.89it/s]
 47%|████▋     | 597/1261 [03:02<03:49,  2.90it/s]
 47%|████▋     | 598/1261 [03:02<04:00,  2.75it/s]
 48%|████▊     | 599/1261 [03:02<03:48,  2.90it/s]
 48%|████▊     | 600/1261 [03:03<03:39,  3.00it/s]
 48%|████▊     | 601/1261 [03:03<03:33,  3.09it/s]
 48%|████▊     | 602/1261 [03:03<03:30,  3.13it/s]
 48%|████▊     | 603/1261 [03:04<03:27,  3.16it/s]
 48%|████▊     | 604/1261 [03:04<03:30,  3.12it/s]
 48%|████▊     | 605/1261 [03:04<03:45,  2.91it/s]
 48%|████▊     | 606/1261 [03:05<03:37,  3.01it/s]
 48%|████▊     | 607/1261 [03:05<03:37,  3.01it/s]
 48%|████▊     | 608/1261 [03:05<03:38,  2.99it/s]
 48%|████▊     | 609/1261 [03:06<03:34,  3.04it/s]
 48%|████▊     | 610/1261 [03:06<03:32,  3.06it/s]
 48%|████▊     | 611/1261 [03:06<03:28,  3.11it/s]
 49%|████▊     | 612/1261 [03:07<03:27,  3.13it/s]
 49%|████▊     | 613/1261 [03:07<03:23,  3.19it/s]
 49%|████▊     | 614/1261 [03:07<03:24,  3.16it/s]
 49%|████▉     | 615/1261 [03:08<03:17,  3.28it/s]
 49%|████▉     | 616/1261 [03:08<03:15,  3.30it/s]
 49%|████▉     | 617/1261 [03:08<03:17,  3.26it/s]
 49%|████▉     | 618/1261 [03:08<03:15,  3.28it/s]
 49%|████▉     | 619/1261 [03:09<03:17,  3.24it/s]
 49%|████▉     | 620/1261 [03:09<03:16,  3.27it/s]
 49%|████▉     | 621/1261 [03:09<03:14,  3.29it/s]
 49%|████▉     | 622/1261 [03:10<03:10,  3.36it/s]
 49%|████▉     | 623/1261 [03:10<03:16,  3.24it/s]
 49%|████▉     | 624/1261 [03:10<03:15,  3.26it/s]
 50%|████▉     | 625/1261 [03:11<03:13,  3.28it/s]
 50%|████▉     | 626/1261 [03:11<03:15,  3.24it/s]
 50%|████▉     | 627/1261 [03:11<03:16,  3.22it/s]
 50%|████▉     | 628/1261 [03:12<03:13,  3.26it/s]
 50%|████▉     | 629/1261 [03:12<03:15,  3.22it/s]
 50%|████▉     | 630/1261 [03:12<03:13,  3.26it/s]
 50%|█████     | 631/1261 [03:12<03:12,  3.28it/s]
 50%|█████     | 632/1261 [03:13<03:11,  3.29it/s]
 50%|█████     | 633/1261 [03:13<03:09,  3.31it/s]
 50%|█████     | 634/1261 [03:13<03:10,  3.29it/s]
 50%|█████     | 635/1261 [03:14<03:10,  3.28it/s]
 50%|█████     | 636/1261 [03:14<03:11,  3.27it/s]
 51%|█████     | 637/1261 [03:14<03:11,  3.25it/s]
 51%|█████     | 638/1261 [03:15<03:10,  3.27it/s]
 51%|█████     | 639/1261 [03:15<03:08,  3.29it/s]
 51%|█████     | 640/1261 [03:15<03:04,  3.36it/s]
 51%|█████     | 641/1261 [03:15<03:07,  3.30it/s]
 51%|█████     | 642/1261 [03:16<03:07,  3.31it/s]
 51%|█████     | 643/1261 [03:16<03:09,  3.27it/s]
 51%|█████     | 644/1261 [03:16<03:05,  3.33it/s]
 51%|█████     | 645/1261 [03:17<03:04,  3.34it/s]
 51%|█████     | 646/1261 [03:17<03:04,  3.33it/s]
 51%|█████▏    | 647/1261 [03:17<03:03,  3.34it/s]
 51%|█████▏    | 648/1261 [03:18<03:01,  3.38it/s]
 51%|█████▏    | 649/1261 [03:18<03:00,  3.39it/s]
 52%|█████▏    | 650/1261 [03:18<02:58,  3.41it/s]
 52%|█████▏    | 651/1261 [03:18<02:56,  3.46it/s]
 52%|█████▏    | 652/1261 [03:19<02:54,  3.50it/s]
 52%|█████▏    | 653/1261 [03:19<02:57,  3.43it/s]
 52%|█████▏    | 654/1261 [03:19<02:58,  3.40it/s]
 52%|█████▏    | 655/1261 [03:20<02:59,  3.38it/s]
 52%|█████▏    | 656/1261 [03:20<03:00,  3.36it/s]
 52%|█████▏    | 657/1261 [03:20<03:00,  3.34it/s]
 52%|█████▏    | 658/1261 [03:20<02:59,  3.36it/s]
 52%|█████▏    | 659/1261 [03:21<03:00,  3.34it/s]
 52%|█████▏    | 660/1261 [03:21<02:57,  3.39it/s]
 52%|█████▏    | 661/1261 [03:21<03:00,  3.33it/s]
 52%|█████▏    | 662/1261 [03:22<03:12,  3.12it/s]
 53%|█████▎    | 663/1261 [03:22<03:15,  3.05it/s]
 53%|█████▎    | 664/1261 [03:22<03:13,  3.09it/s]
 53%|█████▎    | 665/1261 [03:23<03:12,  3.10it/s]
 53%|█████▎    | 666/1261 [03:23<03:04,  3.22it/s]
 53%|█████▎    | 667/1261 [03:23<03:00,  3.30it/s]
 53%|█████▎    | 668/1261 [03:24<03:07,  3.15it/s]
 53%|█████▎    | 669/1261 [03:24<03:04,  3.21it/s]
 53%|█████▎    | 670/1261 [03:24<02:59,  3.29it/s]
 53%|█████▎    | 671/1261 [03:25<03:00,  3.27it/s]
 53%|█████▎    | 672/1261 [03:25<02:57,  3.31it/s]
 53%|█████▎    | 673/1261 [03:25<02:59,  3.27it/s]
 53%|█████▎    | 674/1261 [03:25<03:00,  3.25it/s]
 54%|█████▎    | 675/1261 [03:26<02:59,  3.26it/s]
 54%|█████▎    | 676/1261 [03:26<02:55,  3.33it/s]
 54%|█████▎    | 677/1261 [03:26<02:54,  3.35it/s]
 54%|█████▍    | 678/1261 [03:27<03:02,  3.20it/s]
 54%|█████▍    | 679/1261 [03:27<03:00,  3.22it/s]
 54%|█████▍    | 680/1261 [03:27<02:55,  3.31it/s]
 54%|█████▍    | 681/1261 [03:28<02:59,  3.24it/s]
 54%|█████▍    | 682/1261 [03:28<02:59,  3.23it/s]
 54%|█████▍    | 683/1261 [03:28<02:56,  3.27it/s]
 54%|█████▍    | 684/1261 [03:29<02:55,  3.29it/s]
 54%|█████▍    | 685/1261 [03:29<02:54,  3.31it/s]
 54%|█████▍    | 686/1261 [03:29<02:51,  3.36it/s]
 54%|█████▍    | 687/1261 [03:29<02:51,  3.35it/s]
 55%|█████▍    | 688/1261 [03:30<02:49,  3.37it/s]
 55%|█████▍    | 689/1261 [03:30<03:03,  3.12it/s]
 55%|█████▍    | 690/1261 [03:30<03:08,  3.03it/s]
 55%|█████▍    | 691/1261 [03:31<03:14,  2.94it/s]
 55%|█████▍    | 692/1261 [03:31<03:08,  3.01it/s]
 55%|█████▍    | 693/1261 [03:31<03:02,  3.12it/s]
 55%|█████▌    | 694/1261 [03:32<03:04,  3.07it/s]
 55%|█████▌    | 695/1261 [03:32<03:01,  3.12it/s]
 55%|█████▌    | 696/1261 [03:32<02:58,  3.16it/s]
 55%|█████▌    | 697/1261 [03:33<03:01,  3.10it/s]
 55%|█████▌    | 698/1261 [03:33<03:02,  3.09it/s]
 55%|█████▌    | 699/1261 [03:33<03:00,  3.11it/s]
 56%|█████▌    | 700/1261 [03:34<03:03,  3.07it/s]
 56%|█████▌    | 701/1261 [03:34<03:19,  2.80it/s]
 56%|█████▌    | 702/1261 [03:35<03:56,  2.36it/s]
 56%|█████▌    | 703/1261 [03:35<03:57,  2.34it/s]
 56%|█████▌    | 704/1261 [03:36<04:01,  2.31it/s]
 56%|█████▌    | 705/1261 [03:36<04:00,  2.32it/s]
 56%|█████▌    | 706/1261 [03:36<03:53,  2.38it/s]
 56%|█████▌    | 707/1261 [03:37<03:49,  2.41it/s]
 56%|█████▌    | 708/1261 [03:37<03:52,  2.38it/s]
 56%|█████▌    | 709/1261 [03:38<03:50,  2.39it/s]
 56%|█████▋    | 710/1261 [03:38<03:40,  2.50it/s]
 56%|█████▋    | 711/1261 [03:38<03:37,  2.52it/s]
 56%|█████▋    | 712/1261 [03:39<03:22,  2.71it/s]
 57%|█████▋    | 713/1261 [03:39<03:08,  2.90it/s]
 57%|█████▋    | 714/1261 [03:39<03:01,  3.02it/s]
 57%|█████▋    | 715/1261 [03:40<03:03,  2.98it/s]
 57%|█████▋    | 716/1261 [03:40<03:00,  3.01it/s]
 57%|█████▋    | 717/1261 [03:40<02:52,  3.15it/s]
 57%|█████▋    | 718/1261 [03:41<02:50,  3.18it/s]
 57%|█████▋    | 719/1261 [03:41<02:54,  3.11it/s]
 57%|█████▋    | 720/1261 [03:41<02:59,  3.01it/s]
 57%|█████▋    | 721/1261 [03:42<03:09,  2.86it/s]
 57%|█████▋    | 722/1261 [03:42<03:20,  2.69it/s]
 57%|█████▋    | 723/1261 [03:43<03:34,  2.51it/s]
 57%|█████▋    | 724/1261 [03:43<03:35,  2.49it/s]
 57%|█████▋    | 725/1261 [03:43<03:15,  2.74it/s]
 58%|█████▊    | 726/1261 [03:43<03:03,  2.91it/s]
 58%|█████▊    | 727/1261 [03:44<03:04,  2.90it/s]
 58%|█████▊    | 728/1261 [03:44<02:59,  2.96it/s]
 58%|█████▊    | 729/1261 [03:44<02:54,  3.06it/s]
 58%|█████▊    | 730/1261 [03:45<03:10,  2.79it/s]
 58%|█████▊    | 731/1261 [03:45<03:39,  2.42it/s]
 58%|█████▊    | 732/1261 [03:46<03:38,  2.42it/s]
 58%|█████▊    | 733/1261 [03:46<03:32,  2.49it/s]
 58%|█████▊    | 734/1261 [03:47<03:43,  2.35it/s]
 58%|█████▊    | 735/1261 [03:47<03:43,  2.36it/s]
 58%|█████▊    | 736/1261 [03:48<03:54,  2.24it/s]
 58%|█████▊    | 737/1261 [03:48<03:57,  2.21it/s]
 59%|█████▊    | 738/1261 [03:48<03:46,  2.31it/s]
 59%|█████▊    | 739/1261 [03:49<03:42,  2.34it/s]
 59%|█████▊    | 740/1261 [03:49<03:39,  2.38it/s]
 59%|█████▉    | 741/1261 [03:50<03:44,  2.32it/s]
 59%|█████▉    | 742/1261 [03:50<03:29,  2.48it/s]
 59%|█████▉    | 743/1261 [03:50<03:13,  2.67it/s]
 59%|█████▉    | 744/1261 [03:51<03:13,  2.67it/s]
 59%|█████▉    | 745/1261 [03:51<03:23,  2.53it/s]
 59%|█████▉    | 746/1261 [03:52<03:24,  2.52it/s]
 59%|█████▉    | 747/1261 [03:52<03:11,  2.68it/s]
 59%|█████▉    | 748/1261 [03:52<03:07,  2.74it/s]
 59%|█████▉    | 749/1261 [03:53<03:19,  2.57it/s]
 59%|█████▉    | 750/1261 [03:53<03:26,  2.47it/s]
 60%|█████▉    | 751/1261 [03:54<03:20,  2.54it/s]
 60%|█████▉    | 752/1261 [03:54<03:26,  2.47it/s]
 60%|█████▉    | 753/1261 [03:54<03:21,  2.52it/s]
 60%|█████▉    | 754/1261 [03:55<03:24,  2.48it/s]
 60%|█████▉    | 755/1261 [03:55<03:30,  2.41it/s]
 60%|█████▉    | 756/1261 [03:56<03:21,  2.51it/s]
 60%|██████    | 757/1261 [03:56<03:15,  2.58it/s]
 60%|██████    | 758/1261 [03:56<03:17,  2.55it/s]
 60%|██████    | 759/1261 [03:57<03:06,  2.69it/s]
 60%|██████    | 760/1261 [03:57<02:57,  2.82it/s]
 60%|██████    | 761/1261 [03:57<02:55,  2.85it/s]
 60%|██████    | 762/1261 [03:58<02:53,  2.87it/s]
 61%|██████    | 763/1261 [03:58<02:54,  2.85it/s]
 61%|██████    | 764/1261 [03:58<02:46,  2.99it/s]
 61%|██████    | 765/1261 [03:59<02:46,  2.97it/s]
 61%|██████    | 766/1261 [03:59<02:43,  3.03it/s]
 61%|██████    | 767/1261 [03:59<02:39,  3.10it/s]
 61%|██████    | 768/1261 [04:00<02:33,  3.22it/s]
 61%|██████    | 769/1261 [04:00<02:29,  3.30it/s]
 61%|██████    | 770/1261 [04:00<02:27,  3.33it/s]
 61%|██████    | 771/1261 [04:00<02:28,  3.31it/s]
 61%|██████    | 772/1261 [04:01<02:27,  3.31it/s]
 61%|██████▏   | 773/1261 [04:01<02:47,  2.91it/s]
 61%|██████▏   | 774/1261 [04:02<03:02,  2.67it/s]
 61%|██████▏   | 775/1261 [04:02<03:10,  2.55it/s]
 62%|██████▏   | 776/1261 [04:02<03:06,  2.61it/s]
 62%|██████▏   | 777/1261 [04:03<03:05,  2.61it/s]
 62%|██████▏   | 778/1261 [04:03<03:03,  2.63it/s]
 62%|██████▏   | 779/1261 [04:03<02:54,  2.76it/s]
 62%|██████▏   | 780/1261 [04:04<02:48,  2.86it/s]
 62%|██████▏   | 781/1261 [04:04<02:42,  2.95it/s]
 62%|██████▏   | 782/1261 [04:05<02:47,  2.87it/s]
 62%|██████▏   | 783/1261 [04:05<02:43,  2.92it/s]
 62%|██████▏   | 784/1261 [04:05<02:47,  2.84it/s]
 62%|██████▏   | 785/1261 [04:06<02:54,  2.74it/s]
 62%|██████▏   | 786/1261 [04:06<02:45,  2.87it/s]
 62%|██████▏   | 787/1261 [04:06<02:38,  2.98it/s]
 62%|██████▏   | 788/1261 [04:07<02:44,  2.87it/s]
 63%|██████▎   | 789/1261 [04:07<02:35,  3.04it/s]
 63%|██████▎   | 790/1261 [04:07<02:38,  2.98it/s]
 63%|██████▎   | 791/1261 [04:08<02:40,  2.92it/s]
 63%|██████▎   | 792/1261 [04:08<02:36,  3.00it/s]
 63%|██████▎   | 793/1261 [04:08<02:39,  2.94it/s]
 63%|██████▎   | 794/1261 [04:09<02:40,  2.91it/s]
 63%|██████▎   | 795/1261 [04:09<02:41,  2.88it/s]
 63%|██████▎   | 796/1261 [04:09<02:36,  2.97it/s]
 63%|██████▎   | 797/1261 [04:10<02:35,  2.99it/s]
 63%|██████▎   | 798/1261 [04:10<02:32,  3.04it/s]
 63%|██████▎   | 799/1261 [04:10<02:28,  3.12it/s]
 63%|██████▎   | 800/1261 [04:11<02:24,  3.19it/s]
 64%|██████▎   | 801/1261 [04:11<02:25,  3.17it/s]
 64%|██████▎   | 802/1261 [04:11<02:24,  3.17it/s]
 64%|██████▎   | 803/1261 [04:11<02:25,  3.16it/s]
 64%|██████▍   | 804/1261 [04:12<02:25,  3.13it/s]
 64%|██████▍   | 805/1261 [04:12<02:27,  3.09it/s]
 64%|██████▍   | 806/1261 [04:12<02:27,  3.09it/s]
 64%|██████▍   | 807/1261 [04:13<02:22,  3.19it/s]
 64%|██████▍   | 808/1261 [04:13<02:19,  3.25it/s]
 64%|██████▍   | 809/1261 [04:13<02:16,  3.31it/s]
 64%|██████▍   | 810/1261 [04:14<02:18,  3.26it/s]
 64%|██████▍   | 811/1261 [04:14<02:16,  3.28it/s]
 64%|██████▍   | 812/1261 [04:14<02:17,  3.27it/s]
 64%|██████▍   | 813/1261 [04:15<02:15,  3.30it/s]
 65%|██████▍   | 814/1261 [04:15<02:17,  3.25it/s]
 65%|██████▍   | 815/1261 [04:15<02:16,  3.28it/s]
 65%|██████▍   | 816/1261 [04:16<02:21,  3.15it/s]
 65%|██████▍   | 817/1261 [04:16<02:17,  3.22it/s]
 65%|██████▍   | 818/1261 [04:16<02:21,  3.14it/s]
 65%|██████▍   | 819/1261 [04:16<02:16,  3.24it/s]
 65%|██████▌   | 820/1261 [04:17<02:16,  3.23it/s]
 65%|██████▌   | 821/1261 [04:17<02:15,  3.25it/s]
 65%|██████▌   | 822/1261 [04:17<02:13,  3.29it/s]
 65%|██████▌   | 823/1261 [04:18<02:10,  3.36it/s]
 65%|██████▌   | 824/1261 [04:18<02:10,  3.35it/s]
 65%|██████▌   | 825/1261 [04:18<02:12,  3.29it/s]
 66%|██████▌   | 826/1261 [04:19<02:14,  3.25it/s]
 66%|██████▌   | 827/1261 [04:19<02:10,  3.33it/s]
 66%|██████▌   | 828/1261 [04:19<02:10,  3.32it/s]
 66%|██████▌   | 829/1261 [04:19<02:09,  3.32it/s]
 66%|██████▌   | 830/1261 [04:20<02:09,  3.32it/s]
 66%|██████▌   | 831/1261 [04:20<02:10,  3.29it/s]
 66%|██████▌   | 832/1261 [04:20<02:08,  3.35it/s]
 66%|██████▌   | 833/1261 [04:21<02:06,  3.40it/s]
 66%|██████▌   | 834/1261 [04:21<02:08,  3.32it/s]
 66%|██████▌   | 835/1261 [04:21<02:06,  3.37it/s]
 66%|██████▋   | 836/1261 [04:22<02:06,  3.37it/s]
 66%|██████▋   | 837/1261 [04:22<02:06,  3.36it/s]
 66%|██████▋   | 838/1261 [04:22<02:06,  3.35it/s]
 67%|██████▋   | 839/1261 [04:22<02:05,  3.36it/s]
 67%|██████▋   | 840/1261 [04:23<02:05,  3.35it/s]
 67%|██████▋   | 841/1261 [04:23<02:05,  3.34it/s]
 67%|██████▋   | 842/1261 [04:23<02:05,  3.34it/s]
 67%|██████▋   | 843/1261 [04:24<02:01,  3.44it/s]
 67%|██████▋   | 844/1261 [04:24<02:03,  3.37it/s]
 67%|██████▋   | 845/1261 [04:24<02:00,  3.46it/s]
 67%|██████▋   | 846/1261 [04:24<02:01,  3.42it/s]
 67%|██████▋   | 847/1261 [04:25<02:02,  3.39it/s]
 67%|██████▋   | 848/1261 [04:25<02:02,  3.38it/s]
 67%|██████▋   | 849/1261 [04:25<02:02,  3.35it/s]
 67%|██████▋   | 850/1261 [04:26<02:02,  3.37it/s]
 67%|██████▋   | 851/1261 [04:26<02:02,  3.34it/s]
 68%|██████▊   | 852/1261 [04:26<02:08,  3.19it/s]
 68%|██████▊   | 853/1261 [04:27<02:04,  3.28it/s]
 68%|██████▊   | 854/1261 [04:27<02:16,  2.98it/s]
 68%|██████▊   | 855/1261 [04:27<02:10,  3.11it/s]
 68%|██████▊   | 856/1261 [04:28<02:07,  3.17it/s]
 68%|██████▊   | 857/1261 [04:28<02:06,  3.19it/s]
 68%|██████▊   | 858/1261 [04:28<02:05,  3.20it/s]
 68%|██████▊   | 859/1261 [04:29<02:08,  3.13it/s]
 68%|██████▊   | 860/1261 [04:29<02:07,  3.14it/s]
 68%|██████▊   | 861/1261 [04:29<02:07,  3.14it/s]
 68%|██████▊   | 862/1261 [04:30<02:05,  3.18it/s]
 68%|██████▊   | 863/1261 [04:30<02:04,  3.19it/s]
 69%|██████▊   | 864/1261 [04:30<02:03,  3.21it/s]
 69%|██████▊   | 865/1261 [04:30<02:09,  3.05it/s]
 69%|██████▊   | 866/1261 [04:31<02:08,  3.06it/s]
 69%|██████▉   | 867/1261 [04:31<02:14,  2.93it/s]
 69%|██████▉   | 868/1261 [04:32<02:12,  2.98it/s]
 69%|██████▉   | 869/1261 [04:32<02:12,  2.95it/s]
 69%|██████▉   | 870/1261 [04:32<02:09,  3.02it/s]
 69%|██████▉   | 871/1261 [04:32<02:08,  3.05it/s]
 69%|██████▉   | 872/1261 [04:33<02:02,  3.17it/s]
 69%|██████▉   | 873/1261 [04:33<02:03,  3.15it/s]
 69%|██████▉   | 874/1261 [04:33<01:59,  3.23it/s]
 69%|██████▉   | 875/1261 [04:34<01:59,  3.23it/s]
 69%|██████▉   | 876/1261 [04:34<02:00,  3.19it/s]
 70%|██████▉   | 877/1261 [04:34<02:07,  3.01it/s]
 70%|██████▉   | 878/1261 [04:35<02:04,  3.06it/s]
 70%|██████▉   | 879/1261 [04:35<01:59,  3.19it/s]
 70%|██████▉   | 880/1261 [04:35<01:59,  3.19it/s]
 70%|██████▉   | 881/1261 [04:36<01:55,  3.30it/s]
 70%|██████▉   | 882/1261 [04:36<02:01,  3.12it/s]
 70%|███████   | 883/1261 [04:36<01:59,  3.15it/s]
 70%|███████   | 884/1261 [04:37<02:03,  3.05it/s]
 70%|███████   | 885/1261 [04:37<02:02,  3.08it/s]
 70%|███████   | 886/1261 [04:37<02:00,  3.11it/s]
 70%|███████   | 887/1261 [04:38<01:56,  3.22it/s]
 70%|███████   | 888/1261 [04:38<01:58,  3.15it/s]
 70%|███████   | 889/1261 [04:38<01:57,  3.16it/s]
 71%|███████   | 890/1261 [04:38<01:57,  3.16it/s]
 71%|███████   | 891/1261 [04:39<01:57,  3.16it/s]
 71%|███████   | 892/1261 [04:39<01:56,  3.18it/s]
 71%|███████   | 893/1261 [04:39<01:55,  3.18it/s]
 71%|███████   | 894/1261 [04:40<01:53,  3.24it/s]
 71%|███████   | 895/1261 [04:40<01:51,  3.27it/s]
 71%|███████   | 896/1261 [04:40<01:49,  3.34it/s]
 71%|███████   | 897/1261 [04:41<01:47,  3.39it/s]
 71%|███████   | 898/1261 [04:41<01:47,  3.37it/s]
 71%|███████▏  | 899/1261 [04:41<01:49,  3.31it/s]
 71%|███████▏  | 900/1261 [04:42<01:50,  3.27it/s]
 71%|███████▏  | 901/1261 [04:42<01:51,  3.24it/s]
 72%|███████▏  | 902/1261 [04:42<01:51,  3.21it/s]
 72%|███████▏  | 903/1261 [04:42<01:50,  3.24it/s]
 72%|███████▏  | 904/1261 [04:43<01:52,  3.17it/s]
 72%|███████▏  | 905/1261 [04:43<01:53,  3.12it/s]
 72%|███████▏  | 906/1261 [04:43<01:51,  3.17it/s]
 72%|███████▏  | 907/1261 [04:44<01:49,  3.23it/s]
 72%|███████▏  | 908/1261 [04:44<01:48,  3.26it/s]
 72%|███████▏  | 909/1261 [04:44<01:49,  3.20it/s]
 72%|███████▏  | 910/1261 [04:45<01:51,  3.16it/s]
 72%|███████▏  | 911/1261 [04:45<01:50,  3.15it/s]
 72%|███████▏  | 912/1261 [04:45<01:50,  3.16it/s]
 72%|███████▏  | 913/1261 [04:46<01:50,  3.15it/s]
 72%|███████▏  | 914/1261 [04:46<01:48,  3.20it/s]
 73%|███████▎  | 915/1261 [04:46<01:46,  3.24it/s]
 73%|███████▎  | 916/1261 [04:47<01:45,  3.27it/s]
 73%|███████▎  | 917/1261 [04:47<01:43,  3.34it/s]
 73%|███████▎  | 918/1261 [04:47<01:42,  3.35it/s]
 73%|███████▎  | 919/1261 [04:47<01:40,  3.39it/s]
 73%|███████▎  | 920/1261 [04:48<01:42,  3.33it/s]
 73%|███████▎  | 921/1261 [04:48<01:42,  3.33it/s]
 73%|███████▎  | 922/1261 [04:48<01:38,  3.43it/s]
 73%|███████▎  | 923/1261 [04:49<01:42,  3.31it/s]
 73%|███████▎  | 924/1261 [04:49<01:43,  3.25it/s]
 73%|███████▎  | 925/1261 [04:49<01:40,  3.33it/s]
 73%|███████▎  | 926/1261 [04:50<01:41,  3.29it/s]
 74%|███████▎  | 927/1261 [04:50<01:39,  3.34it/s]
 74%|███████▎  | 928/1261 [04:50<01:39,  3.33it/s]
 74%|███████▎  | 929/1261 [04:50<01:41,  3.28it/s]
 74%|███████▍  | 930/1261 [04:51<01:38,  3.35it/s]
 74%|███████▍  | 931/1261 [04:51<01:40,  3.29it/s]
 74%|███████▍  | 932/1261 [04:51<01:41,  3.24it/s]
 74%|███████▍  | 933/1261 [04:52<01:39,  3.28it/s]
 74%|███████▍  | 934/1261 [04:52<01:39,  3.29it/s]
 74%|███████▍  | 935/1261 [04:52<01:37,  3.36it/s]
 74%|███████▍  | 936/1261 [04:53<01:36,  3.36it/s]
 74%|███████▍  | 937/1261 [04:53<01:39,  3.25it/s]
 74%|███████▍  | 938/1261 [04:53<01:44,  3.08it/s]
 74%|███████▍  | 939/1261 [04:54<01:42,  3.14it/s]
 75%|███████▍  | 940/1261 [04:54<01:41,  3.15it/s]
 75%|███████▍  | 941/1261 [04:54<01:42,  3.13it/s]
 75%|███████▍  | 942/1261 [04:54<01:41,  3.16it/s]
 75%|███████▍  | 943/1261 [04:55<01:37,  3.25it/s]
 75%|███████▍  | 944/1261 [04:55<01:36,  3.28it/s]
 75%|███████▍  | 945/1261 [04:55<01:36,  3.29it/s]
 75%|███████▌  | 946/1261 [04:56<01:35,  3.30it/s]
 75%|███████▌  | 947/1261 [04:56<01:34,  3.32it/s]
 75%|███████▌  | 948/1261 [04:56<01:34,  3.31it/s]
 75%|███████▌  | 949/1261 [04:57<01:35,  3.27it/s]
 75%|███████▌  | 950/1261 [04:57<01:35,  3.24it/s]
 75%|███████▌  | 951/1261 [04:57<01:33,  3.32it/s]
 75%|███████▌  | 952/1261 [04:57<01:34,  3.26it/s]
 76%|███████▌  | 953/1261 [04:58<01:32,  3.35it/s]
 76%|███████▌  | 954/1261 [04:58<01:32,  3.34it/s]
 76%|███████▌  | 955/1261 [04:58<01:34,  3.24it/s]
 76%|███████▌  | 956/1261 [04:59<01:33,  3.27it/s]
 76%|███████▌  | 957/1261 [04:59<01:32,  3.28it/s]
 76%|███████▌  | 958/1261 [04:59<01:33,  3.23it/s]
 76%|███████▌  | 959/1261 [05:00<01:30,  3.33it/s]
 76%|███████▌  | 960/1261 [05:00<01:28,  3.39it/s]
 76%|███████▌  | 961/1261 [05:00<01:29,  3.37it/s]
 76%|███████▋  | 962/1261 [05:00<01:29,  3.36it/s]
 76%|███████▋  | 963/1261 [05:01<01:32,  3.24it/s]
 76%|███████▋  | 964/1261 [05:01<01:32,  3.23it/s]
 77%|███████▋  | 965/1261 [05:01<01:29,  3.30it/s]
 77%|███████▋  | 966/1261 [05:02<01:34,  3.12it/s]
 77%|███████▋  | 967/1261 [05:02<01:32,  3.16it/s]
 77%|███████▋  | 968/1261 [05:02<01:35,  3.08it/s]
 77%|███████▋  | 969/1261 [05:03<01:31,  3.18it/s]
 77%|███████▋  | 970/1261 [05:03<01:32,  3.14it/s]
 77%|███████▋  | 971/1261 [05:03<01:29,  3.24it/s]
 77%|███████▋  | 972/1261 [05:04<01:29,  3.21it/s]
 77%|███████▋  | 973/1261 [05:04<01:28,  3.24it/s]
 77%|███████▋  | 974/1261 [05:04<01:36,  2.97it/s]
 77%|███████▋  | 975/1261 [05:05<01:38,  2.89it/s]
 77%|███████▋  | 976/1261 [05:05<01:39,  2.86it/s]
 77%|███████▋  | 977/1261 [05:05<01:39,  2.85it/s]
 78%|███████▊  | 978/1261 [05:06<01:38,  2.86it/s]
 78%|███████▊  | 979/1261 [05:06<01:40,  2.82it/s]
 78%|███████▊  | 980/1261 [05:07<01:38,  2.85it/s]
 78%|███████▊  | 981/1261 [05:07<01:37,  2.88it/s]
 78%|███████▊  | 982/1261 [05:07<01:37,  2.86it/s]
 78%|███████▊  | 983/1261 [05:08<01:34,  2.95it/s]
 78%|███████▊  | 984/1261 [05:08<01:30,  3.07it/s]
 78%|███████▊  | 985/1261 [05:08<01:33,  2.94it/s]
 78%|███████▊  | 986/1261 [05:08<01:29,  3.09it/s]
 78%|███████▊  | 987/1261 [05:09<01:27,  3.14it/s]
 78%|███████▊  | 988/1261 [05:09<01:28,  3.09it/s]
 78%|███████▊  | 989/1261 [05:09<01:25,  3.19it/s]
 79%|███████▊  | 990/1261 [05:10<01:23,  3.24it/s]
 79%|███████▊  | 991/1261 [05:10<01:22,  3.28it/s]
 79%|███████▊  | 992/1261 [05:10<01:23,  3.20it/s]
 79%|███████▊  | 993/1261 [05:11<01:25,  3.12it/s]
 79%|███████▉  | 994/1261 [05:11<01:26,  3.10it/s]
 79%|███████▉  | 995/1261 [05:11<01:29,  2.97it/s]
 79%|███████▉  | 996/1261 [05:12<01:29,  2.98it/s]
 79%|███████▉  | 997/1261 [05:12<01:31,  2.90it/s]
 79%|███████▉  | 998/1261 [05:12<01:32,  2.85it/s]
 79%|███████▉  | 999/1261 [05:13<01:34,  2.79it/s]
 79%|███████▉  | 1000/1261 [05:13<01:35,  2.73it/s]
 79%|███████▉  | 1001/1261 [05:14<01:32,  2.81it/s]
 79%|███████▉  | 1002/1261 [05:14<01:31,  2.83it/s]
 80%|███████▉  | 1003/1261 [05:14<01:32,  2.78it/s]
 80%|███████▉  | 1004/1261 [05:15<01:27,  2.93it/s]
 80%|███████▉  | 1005/1261 [05:15<01:24,  3.04it/s]
 80%|███████▉  | 1006/1261 [05:15<01:24,  3.03it/s]
 80%|███████▉  | 1007/1261 [05:16<01:24,  3.00it/s]
 80%|███████▉  | 1008/1261 [05:16<01:26,  2.92it/s]
 80%|████████  | 1009/1261 [05:16<01:23,  3.00it/s]
 80%|████████  | 1010/1261 [05:17<01:22,  3.03it/s]
 80%|████████  | 1011/1261 [05:17<01:22,  3.04it/s]
 80%|████████  | 1012/1261 [05:17<01:19,  3.15it/s]
 80%|████████  | 1013/1261 [05:17<01:18,  3.14it/s]
 80%|████████  | 1014/1261 [05:18<01:18,  3.16it/s]
 80%|████████  | 1015/1261 [05:18<01:17,  3.18it/s]
 81%|████████  | 1016/1261 [05:18<01:16,  3.19it/s]
 81%|████████  | 1017/1261 [05:19<01:18,  3.09it/s]
 81%|████████  | 1018/1261 [05:19<01:18,  3.11it/s]
 81%|████████  | 1019/1261 [05:19<01:21,  2.98it/s]
 81%|████████  | 1020/1261 [05:20<01:19,  3.01it/s]
 81%|████████  | 1021/1261 [05:20<01:17,  3.09it/s]
 81%|████████  | 1022/1261 [05:20<01:15,  3.19it/s]
 81%|████████  | 1023/1261 [05:21<01:15,  3.15it/s]
 81%|████████  | 1024/1261 [05:21<01:15,  3.13it/s]
 81%|████████▏ | 1025/1261 [05:21<01:14,  3.18it/s]
 81%|████████▏ | 1026/1261 [05:22<01:15,  3.10it/s]
 81%|████████▏ | 1027/1261 [05:22<01:19,  2.93it/s]
 82%|████████▏ | 1028/1261 [05:22<01:19,  2.91it/s]
 82%|████████▏ | 1029/1261 [05:23<01:18,  2.97it/s]
 82%|████████▏ | 1030/1261 [05:23<01:14,  3.11it/s]
 82%|████████▏ | 1031/1261 [05:23<01:14,  3.07it/s]
 82%|████████▏ | 1032/1261 [05:24<01:16,  3.00it/s]
 82%|████████▏ | 1033/1261 [05:24<01:13,  3.11it/s]
 82%|████████▏ | 1034/1261 [05:24<01:10,  3.21it/s]
 82%|████████▏ | 1035/1261 [05:25<01:12,  3.13it/s]
 82%|████████▏ | 1036/1261 [05:25<01:11,  3.13it/s]
 82%|████████▏ | 1037/1261 [05:25<01:13,  3.05it/s]
 82%|████████▏ | 1038/1261 [05:26<01:14,  2.97it/s]
 82%|████████▏ | 1039/1261 [05:26<01:13,  3.01it/s]
 82%|████████▏ | 1040/1261 [05:26<01:11,  3.10it/s]
 83%|████████▎ | 1041/1261 [05:27<01:10,  3.13it/s]
 83%|████████▎ | 1042/1261 [05:27<01:07,  3.24it/s]
 83%|████████▎ | 1043/1261 [05:27<01:14,  2.94it/s]
 83%|████████▎ | 1044/1261 [05:28<01:11,  3.03it/s]
 83%|████████▎ | 1045/1261 [05:28<01:10,  3.07it/s]
 83%|████████▎ | 1046/1261 [05:28<01:09,  3.10it/s]
 83%|████████▎ | 1047/1261 [05:28<01:07,  3.16it/s]
 83%|████████▎ | 1048/1261 [05:29<01:05,  3.25it/s]
 83%|████████▎ | 1049/1261 [05:29<01:03,  3.33it/s]
 83%|████████▎ | 1050/1261 [05:29<01:04,  3.28it/s]
 83%|████████▎ | 1051/1261 [05:30<01:03,  3.29it/s]
 83%|████████▎ | 1052/1261 [05:30<01:04,  3.26it/s]
 84%|████████▎ | 1053/1261 [05:30<01:04,  3.24it/s]
 84%|████████▎ | 1054/1261 [05:31<01:03,  3.24it/s]
 84%|████████▎ | 1055/1261 [05:31<01:04,  3.19it/s]
 84%|████████▎ | 1056/1261 [05:31<01:02,  3.26it/s]
 84%|████████▍ | 1057/1261 [05:32<01:02,  3.25it/s]
 84%|████████▍ | 1058/1261 [05:32<01:01,  3.29it/s]
 84%|████████▍ | 1059/1261 [05:32<01:01,  3.27it/s]
 84%|████████▍ | 1060/1261 [05:32<01:02,  3.24it/s]
 84%|████████▍ | 1061/1261 [05:33<01:02,  3.19it/s]
 84%|████████▍ | 1062/1261 [05:33<01:01,  3.26it/s]
 84%|████████▍ | 1063/1261 [05:33<01:01,  3.23it/s]
 84%|████████▍ | 1064/1261 [05:34<01:00,  3.26it/s]
 84%|████████▍ | 1065/1261 [05:34<00:59,  3.28it/s]
 85%|████████▍ | 1066/1261 [05:34<00:59,  3.29it/s]
 85%|████████▍ | 1067/1261 [05:35<01:00,  3.21it/s]
 85%|████████▍ | 1068/1261 [05:35<00:59,  3.22it/s]
 85%|████████▍ | 1069/1261 [05:35<00:59,  3.22it/s]
 85%|████████▍ | 1070/1261 [05:36<00:58,  3.26it/s]
 85%|████████▍ | 1071/1261 [05:36<00:58,  3.23it/s]
 85%|████████▌ | 1072/1261 [05:36<00:58,  3.23it/s]
 85%|████████▌ | 1073/1261 [05:36<00:57,  3.29it/s]
 85%|████████▌ | 1074/1261 [05:37<00:56,  3.29it/s]
 85%|████████▌ | 1075/1261 [05:37<00:57,  3.25it/s]
 85%|████████▌ | 1076/1261 [05:37<00:56,  3.28it/s]
 85%|████████▌ | 1077/1261 [05:38<00:55,  3.30it/s]
 85%|████████▌ | 1078/1261 [05:38<00:55,  3.30it/s]
 86%|████████▌ | 1079/1261 [05:38<00:55,  3.25it/s]
 86%|████████▌ | 1080/1261 [05:39<00:56,  3.22it/s]
 86%|████████▌ | 1081/1261 [05:39<00:55,  3.22it/s]
 86%|████████▌ | 1082/1261 [05:39<00:54,  3.30it/s]
 86%|████████▌ | 1083/1261 [05:39<00:54,  3.25it/s]
 86%|████████▌ | 1084/1261 [05:40<00:53,  3.33it/s]
 86%|████████▌ | 1085/1261 [05:40<00:54,  3.22it/s]
 86%|████████▌ | 1086/1261 [05:40<00:54,  3.21it/s]
 86%|████████▌ | 1087/1261 [05:41<00:53,  3.24it/s]
 86%|████████▋ | 1088/1261 [05:41<00:53,  3.25it/s]
 86%|████████▋ | 1089/1261 [05:41<00:53,  3.19it/s]
 86%|████████▋ | 1090/1261 [05:42<00:52,  3.23it/s]
 87%|████████▋ | 1091/1261 [05:42<00:52,  3.22it/s]
 87%|████████▋ | 1092/1261 [05:42<00:51,  3.27it/s]
 87%|████████▋ | 1093/1261 [05:43<00:52,  3.21it/s]
 87%|████████▋ | 1094/1261 [05:43<00:51,  3.21it/s]
 87%|████████▋ | 1095/1261 [05:43<00:50,  3.27it/s]
 87%|████████▋ | 1096/1261 [05:43<00:50,  3.30it/s]
 87%|████████▋ | 1097/1261 [05:44<00:50,  3.25it/s]
 87%|████████▋ | 1098/1261 [05:44<00:50,  3.22it/s]
 87%|████████▋ | 1099/1261 [05:44<00:52,  3.11it/s]
 87%|████████▋ | 1100/1261 [05:45<00:53,  3.02it/s]
 87%|████████▋ | 1101/1261 [05:45<00:53,  2.99it/s]
 87%|████████▋ | 1102/1261 [05:46<00:53,  2.98it/s]
 87%|████████▋ | 1103/1261 [05:46<00:53,  2.96it/s]
 88%|████████▊ | 1104/1261 [05:46<00:52,  3.01it/s]
 88%|████████▊ | 1105/1261 [05:47<00:52,  2.98it/s]
 88%|████████▊ | 1106/1261 [05:47<00:51,  3.03it/s]
 88%|████████▊ | 1107/1261 [05:47<00:49,  3.09it/s]
 88%|████████▊ | 1108/1261 [05:48<00:54,  2.82it/s]
 88%|████████▊ | 1109/1261 [05:48<00:53,  2.82it/s]
 88%|████████▊ | 1110/1261 [05:48<00:53,  2.82it/s]
 88%|████████▊ | 1111/1261 [05:49<00:50,  2.97it/s]
 88%|████████▊ | 1112/1261 [05:49<00:52,  2.86it/s]
 88%|████████▊ | 1113/1261 [05:49<00:49,  2.97it/s]
 88%|████████▊ | 1114/1261 [05:50<00:47,  3.09it/s]
 88%|████████▊ | 1115/1261 [05:50<00:47,  3.05it/s]
 89%|████████▊ | 1116/1261 [05:50<00:48,  3.01it/s]
 89%|████████▊ | 1117/1261 [05:51<00:49,  2.92it/s]
 89%|████████▊ | 1118/1261 [05:51<00:49,  2.91it/s]
 89%|████████▊ | 1119/1261 [05:51<00:46,  3.03it/s]
 89%|████████▉ | 1120/1261 [05:52<00:45,  3.12it/s]
 89%|████████▉ | 1121/1261 [05:52<00:44,  3.18it/s]
 89%|████████▉ | 1122/1261 [05:52<00:43,  3.22it/s]
 89%|████████▉ | 1123/1261 [05:52<00:44,  3.10it/s]
 89%|████████▉ | 1124/1261 [05:53<00:43,  3.11it/s]
 89%|████████▉ | 1125/1261 [05:53<00:44,  3.07it/s]
 89%|████████▉ | 1126/1261 [05:53<00:44,  3.03it/s]
 89%|████████▉ | 1127/1261 [05:54<00:46,  2.88it/s]
 89%|████████▉ | 1128/1261 [05:54<00:44,  3.00it/s]
 90%|████████▉ | 1129/1261 [05:55<00:44,  2.96it/s]
 90%|████████▉ | 1130/1261 [05:55<00:42,  3.08it/s]
 90%|████████▉ | 1131/1261 [05:55<00:41,  3.14it/s]
 90%|████████▉ | 1132/1261 [05:55<00:41,  3.09it/s]
 90%|████████▉ | 1133/1261 [05:56<00:42,  3.02it/s]
 90%|████████▉ | 1134/1261 [05:56<00:44,  2.87it/s]
 90%|█████████ | 1135/1261 [05:57<00:43,  2.88it/s]
 90%|█████████ | 1136/1261 [05:57<00:42,  2.91it/s]
 90%|█████████ | 1137/1261 [05:57<00:42,  2.90it/s]
 90%|█████████ | 1138/1261 [05:58<00:43,  2.84it/s]
 90%|█████████ | 1139/1261 [05:58<00:42,  2.84it/s]
 90%|█████████ | 1140/1261 [05:58<00:42,  2.86it/s]
 90%|█████████ | 1141/1261 [05:59<00:41,  2.88it/s]
 91%|█████████ | 1142/1261 [05:59<00:41,  2.86it/s]
 91%|█████████ | 1143/1261 [05:59<00:39,  2.99it/s]
 91%|█████████ | 1144/1261 [06:00<00:38,  3.05it/s]
 91%|█████████ | 1145/1261 [06:00<00:37,  3.06it/s]
 91%|█████████ | 1146/1261 [06:00<00:37,  3.08it/s]
 91%|█████████ | 1147/1261 [06:01<00:37,  3.05it/s]
 91%|█████████ | 1148/1261 [06:01<00:36,  3.08it/s]
 91%|█████████ | 1149/1261 [06:01<00:34,  3.24it/s]
 91%|█████████ | 1150/1261 [06:01<00:34,  3.25it/s]
 91%|█████████▏| 1151/1261 [06:02<00:33,  3.27it/s]
 91%|█████████▏| 1152/1261 [06:02<00:33,  3.23it/s]
 91%|█████████▏| 1153/1261 [06:02<00:34,  3.16it/s]
 92%|█████████▏| 1154/1261 [06:03<00:33,  3.23it/s]
 92%|█████████▏| 1155/1261 [06:03<00:31,  3.40it/s]
 92%|█████████▏| 1156/1261 [06:03<00:30,  3.39it/s]
 92%|█████████▏| 1157/1261 [06:04<00:29,  3.47it/s]
 92%|█████████▏| 1158/1261 [06:04<00:30,  3.38it/s]
 92%|█████████▏| 1159/1261 [06:04<00:29,  3.49it/s]
 92%|█████████▏| 1160/1261 [06:04<00:29,  3.42it/s]
 92%|█████████▏| 1161/1261 [06:05<00:29,  3.40it/s]
 92%|█████████▏| 1162/1261 [06:05<00:28,  3.45it/s]
 92%|█████████▏| 1163/1261 [06:05<00:28,  3.47it/s]
 92%|█████████▏| 1164/1261 [06:06<00:27,  3.49it/s]
 92%|█████████▏| 1165/1261 [06:06<00:27,  3.51it/s]
 92%|█████████▏| 1166/1261 [06:06<00:27,  3.47it/s]
 93%|█████████▎| 1167/1261 [06:06<00:27,  3.48it/s]
 93%|█████████▎| 1168/1261 [06:07<00:26,  3.54it/s]
 93%|█████████▎| 1169/1261 [06:07<00:26,  3.49it/s]
 93%|█████████▎| 1170/1261 [06:07<00:25,  3.51it/s]
 93%|█████████▎| 1171/1261 [06:08<00:26,  3.38it/s]
 93%|█████████▎| 1172/1261 [06:08<00:25,  3.42it/s]
 93%|█████████▎| 1173/1261 [06:08<00:25,  3.46it/s]
 93%|█████████▎| 1174/1261 [06:08<00:24,  3.49it/s]
 93%|█████████▎| 1175/1261 [06:09<00:24,  3.45it/s]
 93%|█████████▎| 1176/1261 [06:09<00:24,  3.48it/s]
 93%|█████████▎| 1177/1261 [06:09<00:24,  3.41it/s]
 93%|█████████▎| 1178/1261 [06:10<00:24,  3.39it/s]
 93%|█████████▎| 1179/1261 [06:10<00:25,  3.26it/s]
 94%|█████████▎| 1180/1261 [06:10<00:25,  3.19it/s]
 94%|█████████▎| 1181/1261 [06:11<00:26,  3.07it/s]
 94%|█████████▎| 1182/1261 [06:11<00:26,  2.98it/s]
 94%|█████████▍| 1183/1261 [06:11<00:27,  2.82it/s]
 94%|█████████▍| 1184/1261 [06:12<00:26,  2.88it/s]
 94%|█████████▍| 1185/1261 [06:12<00:27,  2.79it/s]
 94%|█████████▍| 1186/1261 [06:12<00:25,  2.95it/s]
 94%|█████████▍| 1187/1261 [06:13<00:24,  2.99it/s]
 94%|█████████▍| 1188/1261 [06:13<00:24,  3.03it/s]
 94%|█████████▍| 1189/1261 [06:13<00:23,  3.06it/s]
 94%|█████████▍| 1190/1261 [06:14<00:22,  3.11it/s]
 94%|█████████▍| 1191/1261 [06:14<00:22,  3.07it/s]
 95%|█████████▍| 1192/1261 [06:14<00:22,  3.12it/s]
 95%|█████████▍| 1193/1261 [06:15<00:21,  3.14it/s]
 95%|█████████▍| 1194/1261 [06:15<00:21,  3.11it/s]
 95%|█████████▍| 1195/1261 [06:15<00:20,  3.17it/s]
 95%|█████████▍| 1196/1261 [06:16<00:20,  3.10it/s]
 95%|█████████▍| 1197/1261 [06:16<00:20,  3.15it/s]
 95%|█████████▌| 1198/1261 [06:16<00:19,  3.23it/s]
 95%|█████████▌| 1199/1261 [06:17<00:19,  3.16it/s]
 95%|█████████▌| 1200/1261 [06:17<00:19,  3.13it/s]
 95%|█████████▌| 1201/1261 [06:17<00:19,  3.14it/s]
 95%|█████████▌| 1202/1261 [06:18<00:19,  3.10it/s]
 95%|█████████▌| 1203/1261 [06:18<00:19,  3.02it/s]
 95%|█████████▌| 1204/1261 [06:18<00:19,  2.94it/s]
 96%|█████████▌| 1205/1261 [06:19<00:18,  2.95it/s]
 96%|█████████▌| 1206/1261 [06:19<00:18,  2.95it/s]
 96%|█████████▌| 1207/1261 [06:19<00:18,  2.99it/s]
 96%|█████████▌| 1208/1261 [06:20<00:17,  3.04it/s]
 96%|█████████▌| 1209/1261 [06:20<00:16,  3.09it/s]
 96%|█████████▌| 1210/1261 [06:20<00:16,  3.03it/s]
 96%|█████████▌| 1211/1261 [06:21<00:16,  3.07it/s]
 96%|█████████▌| 1212/1261 [06:21<00:15,  3.13it/s]
 96%|█████████▌| 1213/1261 [06:21<00:15,  3.03it/s]
 96%|█████████▋| 1214/1261 [06:21<00:15,  3.12it/s]
 96%|█████████▋| 1215/1261 [06:22<00:14,  3.12it/s]
 96%|█████████▋| 1216/1261 [06:22<00:14,  3.07it/s]
 97%|█████████▋| 1217/1261 [06:22<00:14,  3.07it/s]
 97%|█████████▋| 1218/1261 [06:23<00:13,  3.08it/s]
 97%|█████████▋| 1219/1261 [06:23<00:14,  2.94it/s]
 97%|█████████▋| 1220/1261 [06:24<00:14,  2.89it/s]
 97%|█████████▋| 1221/1261 [06:24<00:13,  2.87it/s]
 97%|█████████▋| 1222/1261 [06:24<00:13,  2.85it/s]
 97%|█████████▋| 1223/1261 [06:25<00:13,  2.81it/s]
 97%|█████████▋| 1224/1261 [06:25<00:13,  2.81it/s]
 97%|█████████▋| 1225/1261 [06:25<00:12,  2.94it/s]
 97%|█████████▋| 1226/1261 [06:26<00:11,  2.98it/s]
 97%|█████████▋| 1227/1261 [06:26<00:11,  2.94it/s]
 97%|█████████▋| 1228/1261 [06:26<00:10,  3.01it/s]
 97%|█████████▋| 1229/1261 [06:27<00:10,  3.05it/s]
 98%|█████████▊| 1230/1261 [06:27<00:09,  3.20it/s]
 98%|█████████▊| 1231/1261 [06:27<00:09,  3.19it/s]
 98%|█████████▊| 1232/1261 [06:28<00:10,  2.85it/s]
 98%|█████████▊| 1233/1261 [06:28<00:09,  2.97it/s]
 98%|█████████▊| 1234/1261 [06:28<00:08,  3.05it/s]
 98%|█████████▊| 1235/1261 [06:29<00:08,  2.99it/s]
 98%|█████████▊| 1236/1261 [06:29<00:08,  2.99it/s]
 98%|█████████▊| 1237/1261 [06:29<00:08,  2.94it/s]
 98%|█████████▊| 1238/1261 [06:30<00:07,  2.99it/s]
 98%|█████████▊| 1239/1261 [06:30<00:07,  2.98it/s]
 98%|█████████▊| 1240/1261 [06:30<00:06,  3.11it/s]
 98%|█████████▊| 1241/1261 [06:30<00:06,  3.18it/s]
 98%|█████████▊| 1242/1261 [06:31<00:06,  3.13it/s]
 99%|█████████▊| 1243/1261 [06:31<00:05,  3.06it/s]
 99%|█████████▊| 1244/1261 [06:32<00:05,  3.00it/s]
 99%|█████████▊| 1245/1261 [06:32<00:05,  2.96it/s]
 99%|█████████▉| 1246/1261 [06:32<00:04,  3.04it/s]
 99%|█████████▉| 1247/1261 [06:32<00:04,  3.11it/s]
 99%|█████████▉| 1248/1261 [06:33<00:04,  3.05it/s]
 99%|█████████▉| 1249/1261 [06:33<00:03,  3.11it/s]
 99%|█████████▉| 1250/1261 [06:33<00:03,  3.08it/s]
 99%|█████████▉| 1251/1261 [06:34<00:03,  3.14it/s]
 99%|█████████▉| 1252/1261 [06:34<00:02,  3.03it/s]
 99%|█████████▉| 1253/1261 [06:34<00:02,  2.97it/s]
 99%|█████████▉| 1254/1261 [06:35<00:02,  2.95it/s]
100%|█████████▉| 1255/1261 [06:35<00:01,  3.04it/s]
100%|█████████▉| 1256/1261 [06:35<00:01,  3.09it/s]
100%|█████████▉| 1257/1261 [06:36<00:01,  3.18it/s]
100%|█████████▉| 1258/1261 [06:36<00:00,  3.11it/s]
100%|█████████▉| 1259/1261 [06:36<00:00,  3.01it/s]
100%|█████████▉| 1260/1261 [06:37<00:00,  2.98it/s]






    




[MoviePy] Done.
[MoviePy] >>>> Video ready: ../output_videos/project_video.mp4 

Wall time: 6min 39s

In [56]:

    

HTML("""
<video width="960" height="540" controls>
  <source src="{0}">
</videot
""".format(video_output))


    

    
Out[56]:

In [ ]: