In [1]:

    

%load_ext autoreload
%autoreload 2

import cPickle as pickle
import os; import sys; sys.path.append('..'); sys.path.append('../gp/')
import gp
import gp.nets as nets

from nolearn.lasagne.visualize import plot_loss
from nolearn.lasagne.visualize import plot_conv_weights
from nolearn.lasagne.visualize import plot_conv_activity
from nolearn.lasagne.visualize import plot_occlusion

from sklearn.metrics import classification_report, accuracy_score, roc_curve, auc, precision_recall_fscore_support, f1_score, precision_recall_curve, average_precision_score, zero_one_loss


from matplotlib.pyplot import imshow
import matplotlib.pyplot as plt

%matplotlib inline


    

    




/home/d/nolearn/local/lib/python2.7/site-packages/matplotlib/font_manager.py:273: UserWarning: Matplotlib is building the font cache using fc-list. This may take a moment.
  warnings.warn('Matplotlib is building the font cache using fc-list. This may take a moment.')
Using gpu device 0: GeForce GTX TITAN (CNMeM is disabled, CuDNN 4007)
/home/d/nolearn/local/lib/python2.7/site-packages/theano/tensor/signal/downsample.py:6: UserWarning: downsample module has been moved to the theano.tensor.signal.pool module.
  "downsample module has been moved to the theano.tensor.signal.pool module.")

In [ ]:

    




    

In [126]:

    

input_image = []
input_prob = []
input_gold = []
input_rhoana = []

# for z in range(0,50):
test_slices = range(15,25) + range(40,50) + range(65,75)
for z in test_slices:
    image, prob, gold, rhoana = gp.Util.read_cremi_section(os.path.expanduser('/home/d/data/CREMIGP/TEST/'), z)
    input_image.append(image[0:500,0:500])
    input_prob.append(255.-prob[0:500,0:500])
    input_gold.append(gold[0:500,0:500])
    input_rhoana.append(rhoana[0:500,0:500])


    

In [127]:

    

import time
t0 = time.time()
merge_errors = gp.Legacy.get_top5_merge_errors(net, input_image, input_prob, input_rhoana, verbose=True)
print time.time()-t0


    

    




working on slice 0
working on slice 1
working on slice 2
working on slice 3
working on slice 4
working on slice 5
working on slice 6
working on slice 7
working on slice 8
working on slice 9
working on slice 10
working on slice 11
working on slice 12
working on slice 13
working on slice 14
working on slice 15
working on slice 16
working on slice 17
working on slice 18
working on slice 19
working on slice 20
working on slice 21
working on slice 22
working on slice 23
working on slice 24
working on slice 25
working on slice 26
working on slice 27
working on slice 28
working on slice 29
merge error correction done after 1106.43245101 seconds
1106.43267703

In [130]:

    

len(merge_errors)


    

    
Out[130]:





282

In [198]:

    

len(input_gold)


    

    
Out[198]:





30

In [ ]:

    




    

In [84]:

    

NETS = []
NETS.append('../nets/IPMLB_FULL_CREMILARGE.p') # image + prob + binary + large border

network_path = NETS[-1]

with open(network_path, 'rb') as f:
    net = pickle.load(f)


    

In [112]:

    

net.uuid


    

    
Out[112]:





'IPMLB'

In [ ]:

    




    

In [25]:

    




    

In [3]:

    

gp.Util.view(gold)


    

In [8]:

    

gp.Util.view(rhoana)


    

In [16]:

    

gp.Util.view(255.-prob, color=False)


    

In [10]:

    

gp.Util.view(image, color=False)


    

In [137]:

    

original_mean_VI, original_median_VI, original_VI_s = gp.Legacy.VI(input_rhoana, input_gold)


    

In [12]:

    

gp.metrics.adapted_rand(rhoana, gold)


    

    
Out[12]:





0.25980237467181599

In [105]:

    

imshow(input_prob[0], cmap='gray')


    

    
Out[105]:





<matplotlib.image.AxesImage at 0x7fce62901850>






    

In [129]:

    

net.uuid = 'IPMLB'
bigM_cremiA = gp.Legacy.create_bigM_without_mask(net, input_image, input_prob, input_rhoana, verbose=True)


    

    




432 generated in 2.34614109993 seconds.
Grouped into 107 patches in 0.00199794769287 seconds.
448 generated in 3.35771393776 seconds.
Grouped into 111 patches in 0.0021231174469 seconds.
716 generated in 4.43210101128 seconds.
Grouped into 177 patches in 0.00339102745056 seconds.
748 generated in 5.18829798698 seconds.
Grouped into 187 patches in 0.00322103500366 seconds.
692 generated in 5.04825901985 seconds.
Grouped into 171 patches in 0.00323390960693 seconds.
544 generated in 4.12669491768 seconds.
Grouped into 133 patches in 0.0024778842926 seconds.
556 generated in 4.07311797142 seconds.
Grouped into 137 patches in 0.00258779525757 seconds.
660 generated in 4.64634394646 seconds.
Grouped into 165 patches in 0.00292491912842 seconds.
624 generated in 4.81118893623 seconds.
Grouped into 154 patches in 0.00306701660156 seconds.
488 generated in 4.15620493889 seconds.
Grouped into 122 patches in 0.00230979919434 seconds.
340 generated in 2.67669081688 seconds.
Grouped into 67 patches in 0.00161290168762 seconds.
312 generated in 2.54465484619 seconds.
Grouped into 64 patches in 0.00143909454346 seconds.
400 generated in 2.83944201469 seconds.
Grouped into 84 patches in 0.00188612937927 seconds.
512 generated in 3.38380408287 seconds.
Grouped into 119 patches in 0.00233006477356 seconds.
460 generated in 3.53446006775 seconds.
Grouped into 111 patches in 0.00214195251465 seconds.
412 generated in 3.15405893326 seconds.
Grouped into 92 patches in 0.00189614295959 seconds.
448 generated in 2.98341107368 seconds.
Grouped into 102 patches in 0.00212788581848 seconds.
460 generated in 3.50686597824 seconds.
Grouped into 105 patches in 0.00215005874634 seconds.
400 generated in 2.94663596153 seconds.
Grouped into 94 patches in 0.00177192687988 seconds.
356 generated in 2.74619007111 seconds.
Grouped into 86 patches in 0.00171303749084 seconds.
544 generated in 3.34594202042 seconds.
Grouped into 129 patches in 0.00239515304565 seconds.
344 generated in 3.0793299675 seconds.
Grouped into 79 patches in 0.00169110298157 seconds.
260 generated in 2.45038795471 seconds.
Grouped into 57 patches in 0.00119996070862 seconds.
248 generated in 2.04922008514 seconds.
Grouped into 51 patches in 0.00115084648132 seconds.
320 generated in 2.2997469902 seconds.
Grouped into 69 patches in 0.00162601470947 seconds.
408 generated in 2.84290885925 seconds.
Grouped into 87 patches in 0.00206613540649 seconds.
452 generated in 3.06977510452 seconds.
Grouped into 98 patches in 0.00200891494751 seconds.
352 generated in 2.58897399902 seconds.
Grouped into 77 patches in 0.00163888931274 seconds.
328 generated in 2.2063908577 seconds.
Grouped into 67 patches in 0.00151991844177 seconds.
300 generated in 1.99982690811 seconds.
Grouped into 60 patches in 0.00142097473145 seconds.

In [132]:

    

for z in range(len(bigM_cremiA)):
    
    print bigM_cremiA[z].max()


    

    




0.856931686401
0.856931686401
0.856931686401
0.856931686401
0.856931686401
0.855901658535
0.856931686401
0.856931686401
0.856931686401
0.856932997704
0.85269767046
0.856931686401
0.856931686401
0.856931686401
0.856931686401
0.856931686401
0.856931686401
0.856931686401
0.856931686401
0.856931686401
0.856931686401
0.856931686401
0.856931686401
0.856931686401
0.856931686401
0.856931686401
0.856931686401
0.856931686401
0.856249272823
0.856931686401

In [136]:

    

len(input_gold)


    

    
Out[136]:





30

In [151]:

    

output_folder = '/home/d/GPCREMI/'
dojo_vi_95_file = output_folder + '/cremi_vi_95_t61.p'

dojo_merge_vis = output_folder + '/cremi_merge_auto95_vis.p'
dojo_split_vis = output_folder + '/cremi_split_auto95_vis.p'

dojo_merge_fixes = output_folder + '/cremi_merge_auto95_fixes.p'
dojo_split_fixes = output_folder + '/cremi_split_auto95_fixes.p'

dojo_output_95 = output_folder + '/cremi_auto95_output.p'

if os.path.exists(dojo_vi_95_file):
  print 'Loading merge errors p < .05 and split errors p > .95 from file..'
  with open(dojo_vi_95_file, 'rb') as f:
    dojo_vi_95 = pickle.load(f)
else:      
  #
  # perform merge correction with p < .05
  #
  print 'Correcting merge errors with p < .05'
  bigM_dojo_05, corrected_rhoana_05, dojo_auto_merge_fixes, vi_s_per_step = gp.Legacy.perform_auto_merge_correction(net, bigM_cremiA, 
                                                                                                                    input_image, input_prob, input_rhoana, 
                                                                                                                    merge_errors, .05, input_gold=input_gold)

  print '   Mean VI improvement', original_mean_VI-gp.Legacy.VI(input_gold, corrected_rhoana_05)[0]
  print '   Median VI improvement', original_median_VI-gp.Legacy.VI(input_gold, corrected_rhoana_05)[1]

  with open(dojo_merge_vis, 'wb') as f:
    pickle.dump(vi_s_per_step, f)


  with open(dojo_merge_fixes, 'wb') as f:
    pickle.dump(dojo_auto_merge_fixes, f)


    

    




Correcting merge errors with p < .05
fixing 0.00652392674237
fixing 0.0148607259616
fixing 0.0185579415411
fixing 0.0209641493857
fixing 0.0322633720934
fixing 0.011766104959
fixing 0.0254631321877
fixing 0.0316482260823
fixing 0.00714402925223
fixing 0.049994841218
   Mean VI improvement 0.0024243079079
   Median VI improvement 0.0

In [ ]:

    




    

In [ ]:

    




    

In [153]:

    

bigM_cA_after_95, out_cA_volume_after_auto_95, cA_auto_fixes_95, cA_auto_vi_s_95, visperstep = gp.Legacy.splits_global_from_M_automatic(net, 
                                                                                                                            #bigM_cremiA, 
                                                                                                                                        bigM_dojo_05,
                                                                                                                                        
                                                                                                                            input_image, 
                                                                                                                            input_prob, 
                                                                                                                            corrected_rhoana_05,
                                                                                                                            input_gold, 
                                                                                                                            sureness_threshold=.75)


    

    




0.746747910976

In [199]:

    

original_VI_s


    

    
Out[199]:





[1.0549800794594688,
 1.0787705373852496,
 1.0861358078168148,
 0.9675713369670014,
 0.9997668056591769,
 0.9459034373828512,
 0.9877676442733927,
 0.9141360710451147,
 1.031830053143838,
 0.8788253949176683,
 1.6836230208130387,
 1.5795090743954079,
 1.525698278449243,
 1.5294184161061146,
 1.5089478700765797,
 1.5729122516497531,
 1.497966590050276,
 1.509997243873567,
 1.4813236033061328,
 1.5360103698782628,
 1.549647392613978,
 1.5256067574557957,
 1.6481299808338532,
 1.6513143780877426,
 1.4779760288996808,
 1.4864270335469092,
 1.4094745372930033,
 1.3310744400437553,
 1.3739251218870159,
 1.5206372358397617]

In [169]:

    

original_mean_VI


    

    
Out[169]:





1.3448435597716817

In [159]:

    

OUTDIR = '/home/d/GPCREMI/'
merge_vis = OUTDIR + '/cremi_merge_auto95_vis.p'
split_vis = OUTDIR + '/cremi_split_auto95_vis.p'

merge_fixes = OUTDIR + '/cremi_merge_auto95_fixes.p'
split_fixes = OUTDIR + '/cremi_split_auto95_fixes.p'

output_95 = OUTDIR + '/cremi_auto95_output.p'


    

In [158]:

    

with open(merge_vis, 'wb') as f:
    pickle.dump(vi_s_per_step, f)


with open(merge_fixes, 'wb') as f:
    pickle.dump(dojo_auto_merge_fixes, f)


    

In [162]:

    

with open(split_vis, 'wb') as f:
    pickle.dump(visperstep, f)

with open(split_fixes, 'wb') as f:
    pickle.dump(cA_auto_fixes_95, f)       

with open(output_95, 'wb') as f:
    pickle.dump(out_cA_volume_after_auto_95, f)


    

In [187]:

    

len(bigM_cremiA)


    

    
Out[187]:





30

In [163]:

    

merge_vis = OUTDIR + '/cremi_merge_simuser_vis.p'
split_vis = OUTDIR + '/cremi_split_simuser_vis.p'

merge_fixes = OUTDIR + '/cremi_merge_simuser_fixes.p'
split_fixes = OUTDIR + '/cremi_split_simuser_fixes.p'

output_95 = OUTDIR + '/cremi_simuser_output.p'


    

In [190]:

    

bigM_05, corrected_rhoana_05, cylinder_auto_merge_fixes, vi_s_per_step = gp.Legacy.perform_sim_user_merge_correction(net, bigM_cremiA, input_image, input_prob, input_rhoana, input_gold, merge_errors)


    

    




adding 152 to 0 (500, 500) 152 30
adding 154 to 0 (500, 500) 154 30
adding 156 to 0 (500, 500) 156 30
adding 157 to 0 (500, 500) 157 30
adding 159 to 0 (500, 500) 159 30
adding 161 to 0 (500, 500) 161 30
adding 162 to 0 (500, 500) 162 30
adding 164 to 0 (500, 500) 164 30
adding 137 to 1 (500, 500) 137 30
adding 138 to 1 (500, 500) 138 30
adding 140 to 1 (500, 500) 140 30
adding 142 to 1 (500, 500) 142 30
adding 144 to 1 (500, 500) 144 30
adding 146 to 1 (500, 500) 146 30
adding 148 to 1 (500, 500) 148 30
adding 150 to 1 (500, 500) 150 30
adding 152 to 1 (500, 500) 152 30
adding 154 to 1 (500, 500) 154 30
adding 177 to 2 (500, 500) 177 30
adding 178 to 2 (500, 500) 178 30
adding 180 to 2 (500, 500) 180 30
adding 182 to 2 (500, 500) 182 30
adding 184 to 2 (500, 500) 184 30
adding 186 to 2 (500, 500) 186 30
adding 187 to 2 (500, 500) 187 30
adding 179 to 3 (500, 500) 179 30
adding 181 to 3 (500, 500) 181 30
adding 183 to 3 (500, 500) 183 30
adding 185 to 3 (500, 500) 185 30
adding 187 to 3 (500, 500) 187 30
adding 189 to 3 (500, 500) 189 30
adding 191 to 3 (500, 500) 191 30
adding 193 to 3 (500, 500) 193 30
adding 195 to 3 (500, 500) 195 30
adding 197 to 3 (500, 500) 197 30
adding 199 to 3 (500, 500) 199 30
adding 201 to 3 (500, 500) 201 30
adding 203 to 3 (500, 500) 203 30
adding 205 to 3 (500, 500) 205 30
adding 207 to 3 (500, 500) 207 30
adding 196 to 4 (500, 500) 196 30
adding 198 to 4 (500, 500) 198 30
adding 200 to 4 (500, 500) 200 30
adding 202 to 4 (500, 500) 202 30
adding 204 to 4 (500, 500) 204 30
adding 206 to 4 (500, 500) 206 30
adding 208 to 4 (500, 500) 208 30
adding 210 to 4 (500, 500) 210 30
adding 212 to 4 (500, 500) 212 30
adding 214 to 4 (500, 500) 214 30
adding 174 to 5 (500, 500) 174 30
adding 176 to 5 (500, 500) 176 30
adding 178 to 5 (500, 500) 178 30
adding 180 to 5 (500, 500) 180 30
adding 182 to 5 (500, 500) 182 30
adding 184 to 5 (500, 500) 184 30
adding 186 to 5 (500, 500) 186 30
adding 188 to 5 (500, 500) 188 30
adding 190 to 5 (500, 500) 190 30
adding 176 to 6 (500, 500) 176 30
adding 178 to 6 (500, 500) 178 30
adding 180 to 6 (500, 500) 180 30
adding 182 to 6 (500, 500) 182 30
adding 184 to 6 (500, 500) 184 30
adding 186 to 6 (500, 500) 186 30
adding 188 to 6 (500, 500) 188 30
adding 190 to 6 (500, 500) 190 30
adding 192 to 6 (500, 500) 192 30
adding 194 to 6 (500, 500) 194 30
adding 196 to 6 (500, 500) 196 30
adding 188 to 7 (500, 500) 188 30
adding 190 to 7 (500, 500) 190 30
adding 192 to 7 (500, 500) 192 30
adding 194 to 7 (500, 500) 194 30
adding 196 to 7 (500, 500) 196 30
adding 198 to 7 (500, 500) 198 30
adding 200 to 7 (500, 500) 200 30
adding 202 to 7 (500, 500) 202 30
adding 204 to 7 (500, 500) 204 30
adding 205 to 7 (500, 500) 205 30
adding 207 to 7 (500, 500) 207 30
adding 209 to 7 (500, 500) 209 30
adding 210 to 7 (500, 500) 210 30
adding 212 to 7 (500, 500) 212 30
adding 177 to 8 (500, 500) 177 30
adding 179 to 8 (500, 500) 179 30
adding 181 to 8 (500, 500) 181 30
adding 183 to 8 (500, 500) 183 30
adding 185 to 8 (500, 500) 185 30
adding 187 to 8 (500, 500) 187 30
adding 189 to 8 (500, 500) 189 30
adding 191 to 8 (500, 500) 191 30
adding 141 to 9 (500, 500) 141 30
adding 143 to 9 (500, 500) 143 30
adding 145 to 9 (500, 500) 145 30
adding 147 to 9 (500, 500) 147 30
adding 149 to 9 (500, 500) 149 30
adding 90 to 10 (500, 500) 90 30
adding 92 to 10 (500, 500) 92 30
adding 94 to 10 (500, 500) 94 30
adding 96 to 10 (500, 500) 96 30
adding 98 to 10 (500, 500) 98 30
adding 100 to 10 (500, 500) 100 30
adding 101 to 10 (500, 500) 101 30
adding 89 to 11 (500, 500) 89 30
adding 91 to 11 (500, 500) 91 30
adding 93 to 11 (500, 500) 93 30
adding 95 to 11 (500, 500) 95 30
adding 103 to 12 (500, 500) 103 30
adding 105 to 12 (500, 500) 105 30
adding 106 to 12 (500, 500) 106 30
adding 108 to 12 (500, 500) 108 30
adding 109 to 12 (500, 500) 109 30
adding 119 to 13 (500, 500) 119 30
adding 121 to 13 (500, 500) 121 30
adding 123 to 13 (500, 500) 123 30
adding 125 to 13 (500, 500) 125 30
adding 127 to 13 (500, 500) 127 30
adding 129 to 13 (500, 500) 129 30
adding 105 to 14 (500, 500) 105 30
adding 107 to 14 (500, 500) 107 30
adding 109 to 14 (500, 500) 109 30
adding 111 to 14 (500, 500) 111 30
adding 113 to 14 (500, 500) 113 30
adding 115 to 14 (500, 500) 115 30
adding 87 to 15 (500, 500) 87 30
adding 89 to 15 (500, 500) 89 30
adding 91 to 15 (500, 500) 91 30
adding 93 to 15 (500, 500) 93 30
adding 95 to 15 (500, 500) 95 30
adding 97 to 15 (500, 500) 97 30
adding 99 to 15 (500, 500) 99 30
adding 101 to 15 (500, 500) 101 30
adding 78 to 16 (500, 500) 78 30
adding 80 to 16 (500, 500) 80 30
adding 82 to 16 (500, 500) 82 30
adding 84 to 16 (500, 500) 84 30
adding 86 to 16 (500, 500) 86 30
adding 87 to 16 (500, 500) 87 30
adding 94 to 17 (500, 500) 94 30
adding 96 to 17 (500, 500) 96 30
adding 98 to 17 (500, 500) 98 30
adding 100 to 17 (500, 500) 100 30
adding 102 to 17 (500, 500) 102 30
adding 104 to 17 (500, 500) 104 30
adding 106 to 17 (500, 500) 106 30
adding 108 to 17 (500, 500) 108 30
adding 110 to 17 (500, 500) 110 30
adding 81 to 18 (500, 500) 81 30
adding 83 to 18 (500, 500) 83 30
adding 85 to 18 (500, 500) 85 30
adding 87 to 18 (500, 500) 87 30
adding 89 to 18 (500, 500) 89 30
adding 91 to 18 (500, 500) 91 30
adding 93 to 18 (500, 500) 93 30
adding 95 to 18 (500, 500) 95 30
adding 97 to 18 (500, 500) 97 30
adding 74 to 19 (500, 500) 74 30
adding 76 to 19 (500, 500) 76 30
adding 78 to 19 (500, 500) 78 30
adding 80 to 19 (500, 500) 80 30
adding 82 to 19 (500, 500) 82 30
adding 84 to 19 (500, 500) 84 30
adding 86 to 19 (500, 500) 86 30
adding 198 to 20 (500, 500) 198 30
adding 200 to 20 (500, 500) 200 30
adding 202 to 20 (500, 500) 202 30
adding 181 to 21 (500, 500) 181 30
adding 183 to 21 (500, 500) 183 30
adding 185 to 21 (500, 500) 185 30
adding 187 to 21 (500, 500) 187 30
adding 189 to 21 (500, 500) 189 30
adding 190 to 21 (500, 500) 190 30
adding 192 to 21 (500, 500) 192 30
adding 194 to 21 (500, 500) 194 30
adding 176 to 22 (500, 500) 176 30
adding 178 to 22 (500, 500) 178 30
adding 180 to 22 (500, 500) 180 30
adding 182 to 22 (500, 500) 182 30
adding 184 to 22 (500, 500) 184 30
adding 186 to 22 (500, 500) 186 30
adding 188 to 22 (500, 500) 188 30
adding 136 to 23 (500, 500) 136 30
adding 138 to 23 (500, 500) 138 30
adding 140 to 23 (500, 500) 140 30
adding 142 to 23 (500, 500) 142 30
adding 144 to 23 (500, 500) 144 30
adding 146 to 23 (500, 500) 146 30
adding 148 to 23 (500, 500) 148 30
adding 150 to 23 (500, 500) 150 30
adding 152 to 23 (500, 500) 152 30
adding 142 to 24 (500, 500) 142 30
adding 144 to 24 (500, 500) 144 30
adding 146 to 24 (500, 500) 146 30
adding 148 to 24 (500, 500) 148 30
adding 151 to 24 (500, 500) 151 30
adding 153 to 24 (500, 500) 153 30
adding 155 to 24 (500, 500) 155 30
adding 157 to 24 (500, 500) 157 30
adding 159 to 24 (500, 500) 159 30
adding 161 to 24 (500, 500) 161 30
adding 174 to 25 (500, 500) 174 30
adding 176 to 25 (500, 500) 176 30
adding 178 to 25 (500, 500) 178 30
adding 180 to 25 (500, 500) 180 30
adding 182 to 25 (500, 500) 182 30
adding 184 to 25 (500, 500) 184 30
adding 186 to 25 (500, 500) 186 30
adding 188 to 25 (500, 500) 188 30
adding 134 to 26 (500, 500) 134 30
adding 136 to 26 (500, 500) 136 30
adding 138 to 26 (500, 500) 138 30
adding 140 to 26 (500, 500) 140 30
adding 142 to 26 (500, 500) 142 30
adding 144 to 26 (500, 500) 144 30
adding 126 to 27 (500, 500) 126 30
adding 128 to 27 (500, 500) 128 30
adding 129 to 27 (500, 500) 129 30
adding 131 to 27 (500, 500) 131 30
adding 133 to 27 (500, 500) 133 30
adding 135 to 27 (500, 500) 135 30
adding 137 to 27 (500, 500) 137 30
adding 114 to 28 (500, 500) 114 30
adding 116 to 28 (500, 500) 116 30
adding 118 to 28 (500, 500) 118 30
adding 120 to 28 (500, 500) 120 30
adding 122 to 28 (500, 500) 122 30
adding 124 to 28 (500, 500) 124 30
adding 126 to 28 (500, 500) 126 30
adding 98 to 29 (500, 500) 98 30
adding 100 to 29 (500, 500) 100 30
adding 102 to 29 (500, 500) 102 30
adding 104 to 29 (500, 500) 104 30
adding 106 to 29 (500, 500) 106 30
adding 108 to 29 (500, 500) 108 30
adding 112 to 29 (500, 500) 112 30
adding 113 to 29 (500, 500) 113 30

In [182]:

    

bigM_cremiA[13].shape


    

    
Out[182]:





(118, 118)

In [172]:

    

cylinder_auto_merge_fixes


    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-172-462b666170fa> in <module>()
----> 1 cylinder_auto_merge_fixes

NameError: name 'cylinder_auto_merge_fixes' is not defined

In [191]:

    

with open(merge_vis, 'wb') as f:
    pickle.dump(vi_s_per_step, f)


with open(merge_fixes, 'wb') as f:
    pickle.dump(cylinder_auto_merge_fixes, f)


    

In [192]:

    

bigM_cylinder_after_95, out_cylinder_volume_after_auto_95, cylinder_auto_fixes_95, cylinder_auto_vi_s_95, vi_s_per_step2 = gp.Legacy.splits_global_from_M(net, bigM_05,
input_image, input_prob, corrected_rhoana_05, input_gold, hours=-1)


    

    




done

In [193]:

    

split_fixes = OUTDIR + '/cylinder_split_simuser_fixes.p'


    

In [194]:

    

split_vis = OUTDIR + '/cylinder_split_simuser_vis.p'


    

In [195]:

    

output_95 = OUTDIR + '/cylinder_simuser_output.p'


    

In [196]:

    

with open(split_vis, 'wb') as f:
    pickle.dump(vi_s_per_step2, f)

with open(split_fixes, 'wb') as f:
    pickle.dump(cylinder_auto_fixes_95, f)       

with open(output_95, 'wb') as f:
    pickle.dump(out_cylinder_volume_after_auto_95, f)


    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [38]:

    

bigM_cA_after_95, out_cA_volume_after_auto_95, cA_auto_fixes_95, cA_auto_vi_s_95, visperstep = gp.Legacy.splits_global_from_M_automatic(net, 
                                                                                                                            bigM_cremiA, 
                                                                                                                            input_image, 
                                                                                                                            input_prob, 
                                                                                                                            input_rhoana,
                                                                                                                            input_gold, 
                                                                                                                            sureness_threshold=.95)


    

    




here

In [135]:

    

gp.Legacy.VI(out_cA_volume_after_auto_95, input_gold)


    

    
Out[135]:





(1.2772683303625527,
 1.4227682148970084,
 [0.9914972295290623,
  1.0065468511430007,
  0.9386433274922785,
  0.8513864951451726,
  0.9020146231854129,
  0.9028561846963399,
  0.9029402917052867,
  0.8343376887584597,
  0.8900334300076347,
  0.7640631368301207,
  1.5897406283580051,
  1.4259567455799158,
  1.4067934875872496,
  1.50799981769243,
  1.4216826061807275,
  1.5739188222653064,
  1.49120944768171,
  1.524625720524651,
  1.4673106923648627,
  1.4389061338649043,
  1.4238538236132894,
  1.2980002460822213,
  1.5434885895724069,
  1.5995917290199704,
  1.477708348120366,
  1.4370088289571,
  1.3529149509418676,
  1.3095287650616445,
  1.5158051045850938,
  1.527686164330098])

In [27]:

    

visperstep


    

    
Out[27]:





[(1.1205187243522197,
  1.1205187243522197,
  [1.0903680301647931, 1.1506694185396462]),
 (1.1205750199211311,
  1.1205750199211311,
  [1.090480621302616, 1.1506694185396462]),
 (1.1205373537420451,
  1.1205373537420451,
  [1.090405288944444, 1.1506694185396462]),
 (1.1204855308356558,
  1.1204855308356558,
  [1.090405288944444, 1.1505657727268677]),
 (1.1204578291693812,
  1.1204578291693812,
  [1.090405288944444, 1.1505103693943184]),
 (1.1204093220969673,
  1.1204093220969673,
  [1.0903082747996162, 1.1505103693943184]),
 (1.1204352670924926,
  1.1204352670924926,
  [1.0903601647906669, 1.1505103693943184]),
 (1.120432408075092,
  1.120432408075092,
  [1.0903601647906669, 1.1505046513595172]),
 (1.1204205447144391,
  1.1204205447144391,
  [1.090336438069361, 1.1505046513595172]),
 (1.1203517795432445,
  1.1203517795432445,
  [1.0901989077269718, 1.1505046513595172]),
 (1.1203197728565311,
  1.1203197728565311,
  [1.090134894353545, 1.1505046513595172]),
 (1.1202874124069959,
  1.1202874124069959,
  [1.090134894353545, 1.150439930460447]),
 (1.1202405820828272,
  1.1202405820828272,
  [1.090134894353545, 1.1503462698121094]),
 (1.1202129273125037,
  1.1202129273125037,
  [1.090079584812898, 1.1503462698121094]),
 (1.1202013194538223,
  1.1202013194538223,
  [1.090079584812898, 1.1503230540947467]),
 (1.1201329366255122,
  1.1201329366255122,
  [1.090079584812898, 1.1501862884381264]),
 (1.1201146017321566,
  1.1201146017321566,
  [1.0900429150261868, 1.1501862884381264]),
 (1.1201505308568995,
  1.1201505308568995,
  [1.0901147732756726, 1.1501862884381264]),
 (1.1199677432258035,
  1.1199677432258035,
  [1.0901147732756726, 1.1498207131759344]),
 (1.1182878443855833,
  1.1182878443855833,
  [1.0867549755952322, 1.1498207131759344]),
 (1.1183316484865609,
  1.1183316484865609,
  [1.0867549755952322, 1.1499083213778896]),
 (1.1159824840157819,
  1.1159824840157819,
  [1.0820566466536743, 1.1499083213778896]),
 (1.1158965599972257,
  1.1158965599972257,
  [1.0818847986165618, 1.1499083213778896]),
 (1.1158660833560505,
  1.1158660833560505,
  [1.0818238453342115, 1.1499083213778896]),
 (1.1173573134845007,
  1.1173573134845007,
  [1.084806305591112, 1.1499083213778896]),
 (1.1172730434146674,
  1.1172730434146674,
  [1.084806305591112, 1.1497397812382228]),
 (1.11686377717007, 1.11686377717007, [1.084806305591112, 1.1489212487490281]),
 (1.1169055729188093,
  1.1169055729188093,
  [1.084806305591112, 1.1490048402465067]),
 (1.1168790450265194,
  1.1168790450265194,
  [1.084806305591112, 1.1489517844619268]),
 (1.1163829746756138,
  1.1163829746756138,
  [1.0838141648893007, 1.1489517844619268]),
 (1.1163425374672382,
  1.1163425374672382,
  [1.0837332904725496, 1.1489517844619268]),
 (1.116220786468026,
  1.116220786468026,
  [1.0834897884741252, 1.1489517844619268]),
 (1.1161100700374291,
  1.1161100700374291,
  [1.0834897884741252, 1.148730351600733]),
 (1.1160742911703894,
  1.1160742911703894,
  [1.0834897884741252, 1.1486587938666535]),
 (1.1160083808345354,
  1.1160083808345354,
  [1.0834897884741252, 1.1485269731949455]),
 (1.1159081049861674,
  1.1159081049861674,
  [1.0832892367773894, 1.1485269731949455]),
 (1.1158902463177842,
  1.1158902463177842,
  [1.083253519440623, 1.1485269731949455]),
 (1.1158452294363972,
  1.1158452294363972,
  [1.083163485677849, 1.1485269731949455]),
 (1.1158169872532646,
  1.1158169872532646,
  [1.0831070013115838, 1.1485269731949455]),
 (1.1143162949371437,
  1.1143162949371437,
  [1.0831070013115838, 1.1455255885627036]),
 (1.1143086519227152,
  1.1143086519227152,
  [1.0831070013115838, 1.1455103025338467]),
 (1.1143042144007334,
  1.1143042144007334,
  [1.08309812626762, 1.1455103025338467]),
 (1.1142821965893033,
  1.1142821965893033,
  [1.0830540906447599, 1.1455103025338467]),
 (1.1142305029949533,
  1.1142305029949533,
  [1.08295070345606, 1.1455103025338467]),
 (1.1142349795768585,
  1.1142349795768585,
  [1.0829596566198703, 1.1455103025338467]),
 (1.1141287244690643,
  1.1141287244690643,
  [1.082747146404282, 1.1455103025338467]),
 (1.1128984201046679,
  1.1128984201046679,
  [1.080286537675489, 1.1455103025338467]),
 (1.1128839840028784,
  1.1128839840028784,
  [1.08025766547191, 1.1455103025338467]),
 (1.1128464892071834,
  1.1128464892071834,
  [1.0801826758805202, 1.1455103025338467]),
 (1.1128077931777698,
  1.1128077931777698,
  [1.0801826758805202, 1.1454329104750194]),
 (1.1127227362564858,
  1.1127227362564858,
  [1.0801826758805202, 1.1452627966324513]),
 (1.1126601214286209,
  1.1126601214286209,
  [1.0800574462247905, 1.1452627966324513]),
 (1.112642235737324,
  1.112642235737324,
  [1.0800574462247905, 1.1452270252498575]),
 (1.1125818705838126,
  1.1125818705838126,
  [1.0799367159177677, 1.1452270252498575]),
 (1.1125396502084763,
  1.1125396502084763,
  [1.0799367159177677, 1.145142584499185]),
 (1.112359758680773,
  1.112359758680773,
  [1.079576932862361, 1.145142584499185]),
 (1.1123661401937426,
  1.1123661401937426,
  [1.0795896958883002, 1.145142584499185]),
 (1.1121833402780918,
  1.1121833402780918,
  [1.0792240960569988, 1.145142584499185]),
 (1.1121603561898095,
  1.1121603561898095,
  [1.079178127880434, 1.145142584499185]),
 (1.1119326685479285,
  1.1119326685479285,
  [1.079178127880434, 1.144687209215423]),
 (1.11191937943717, 1.11191937943717, [1.079151549658917, 1.144687209215423]),
 (1.1118214661976715,
  1.1118214661976715,
  [1.079151549658917, 1.144491382736426]),
 (1.1118123235699002,
  1.1118123235699002,
  [1.079151549658917, 1.1444730974808834]),
 (1.1118045062966804,
  1.1118045062966804,
  [1.079151549658917, 1.1444574629344437]),
 (1.111768352942244,
  1.111768352942244,
  [1.079151549658917, 1.144385156225571]),
 (1.111722210753066,
  1.111722210753066,
  [1.079151549658917, 1.144292871847215]),
 (1.1117262896544169,
  1.1117262896544169,
  [1.079151549658917, 1.1443010296499168]),
 (1.1117101258968694,
  1.1117101258968694,
  [1.079119222143822, 1.1443010296499168]),
 (1.1117153514224043,
  1.1117153514224043,
  [1.079119222143822, 1.1443114807009866]),
 (1.1115331677754794,
  1.1115331677754794,
  [1.0787548548499721, 1.1443114807009866]),
 (1.1111814458656619,
  1.1111814458656619,
  [1.0780514110303372, 1.1443114807009866]),
 (1.1111719126851742,
  1.1111719126851742,
  [1.0780323446693618, 1.1443114807009866]),
 (1.1108794383701399,
  1.1108794383701399,
  [1.0774473960392932, 1.1443114807009866]),
 (1.1108702912881805,
  1.1108702912881805,
  [1.0774291018753743, 1.1443114807009866]),
 (1.1107805225500966,
  1.1107805225500966,
  [1.0772495643992066, 1.1443114807009866]),
 (1.1107598908683718,
  1.1107598908683718,
  [1.0772495643992066, 1.144270217337537]),
 (1.1097364204561719,
  1.1097364204561719,
  [1.0772495643992066, 1.1422232765131373]),
 (1.1095961699306223,
  1.1095961699306223,
  [1.0769690633481073, 1.1422232765131373]),
 (1.1089739300206816,
  1.1089739300206816,
  [1.0757245835282259, 1.1422232765131373]),
 (1.1089222342795129,
  1.1089222342795129,
  [1.0757245835282259, 1.1421198850307999]),
 (1.1088338013654786,
  1.1088338013654786,
  [1.0755477177001573, 1.1421198850307999]),
 (1.1087747610618335,
  1.1087747610618335,
  [1.075429637092867, 1.1421198850307999]),
 (1.1086200912413018,
  1.1086200912413018,
  [1.0751202974518037, 1.1421198850307999]),
 (1.1086174343568764,
  1.1086174343568764,
  [1.0751202974518037, 1.1421145712619492]),
 (1.1103294002326098,
  1.1103294002326098,
  [1.0785442292032705, 1.1421145712619492]),
 (1.1101463075067572,
  1.1101463075067572,
  [1.0785442292032705, 1.141748385810244]),
 (1.1100568774554427,
  1.1100568774554427,
  [1.0783653691006414, 1.141748385810244]),
 (1.1100992022515062,
  1.1100992022515062,
  [1.0783653691006414, 1.141833035402371]),
 (1.1100846616652031,
  1.1100846616652031,
  [1.0783653691006414, 1.1418039542297649]),
 (1.1100548262744274,
  1.1100548262744274,
  [1.0783653691006414, 1.1417442834482134]),
 (1.1086642928017403,
  1.1086642928017403,
  [1.0783653691006414, 1.1389632165028392]),
 (1.1084306469331899,
  1.1084306469331899,
  [1.0778980773635407, 1.1389632165028392]),
 (1.1083579572914504,
  1.1083579572914504,
  [1.0777526980800616, 1.1389632165028392]),
 (1.1077950451404277,
  1.1077950451404277,
  [1.0777526980800616, 1.1378373922007938]),
 (1.107732037554066,
  1.107732037554066,
  [1.0776266829073382, 1.1378373922007938]),
 (1.1077297116667681,
  1.1077297116667681,
  [1.0776220311327425, 1.1378373922007938]),
 (1.1076820487330004,
  1.1076820487330004,
  [1.0775267052652069, 1.1378373922007938]),
 (1.1075740041911564,
  1.1075740041911564,
  [1.077310616181519, 1.1378373922007938]),
 (1.1075359881092455,
  1.1075359881092455,
  [1.0772345840176971, 1.1378373922007938]),
 (1.1060415236586882,
  1.1060415236586882,
  [1.0742456551165827, 1.1378373922007938]),
 (1.1060632204565541,
  1.1060632204565541,
  [1.0742890487123145, 1.1378373922007938]),
 (1.1060603117427981,
  1.1060603117427981,
  [1.0742832312848023, 1.1378373922007938]),
 (1.1060446275272611,
  1.1060446275272611,
  [1.0742518628537283, 1.1378373922007938]),
 (1.1060205470889635,
  1.1060205470889635,
  [1.074203701977133, 1.1378373922007938]),
 (1.1055602303663941,
  1.1055602303663941,
  [1.0732830685319943, 1.1378373922007938]),
 (1.1046737348753517,
  1.1046737348753517,
  [1.0715100775499096, 1.1378373922007938]),
 (1.1087737141727603,
  1.1087737141727603,
  [1.0715100775499096, 1.146037350795611]),
 (1.1087566160079829,
  1.1087566160079829,
  [1.0714758812203549, 1.146037350795611]),
 (1.1087352429359569,
  1.1087352429359569,
  [1.071433135076303, 1.146037350795611]),
 (1.1086973866996637,
  1.1086973866996637,
  [1.0713574226037164, 1.146037350795611]),
 (1.1086223775227344,
  1.1086223775227344,
  [1.0712074042498578, 1.146037350795611]),
 (1.1083452395502791,
  1.1083452395502791,
  [1.0706531283049472, 1.146037350795611]),
 (1.1083306979797944,
  1.1083306979797944,
  [1.070624045163978, 1.146037350795611]),
 (1.1083750766252338,
  1.1083750766252338,
  [1.070624045163978, 1.1461261080864897]),
 (1.1083130692445309,
  1.1083130692445309,
  [1.070500030402572, 1.1461261080864897]),
 (1.1074549352077261,
  1.1074549352077261,
  [1.070500030402572, 1.1444098400128802]),
 (1.1073642120953355,
  1.1073642120953355,
  [1.070318584177791, 1.1444098400128802]),
 (1.1075239277795346,
  1.1075239277795346,
  [1.070318584177791, 1.1447292713812782]),
 (1.1074509156057095,
  1.1074509156057095,
  [1.070318584177791, 1.1445832470336281]),
 (1.1071297267785072,
  1.1071297267785072,
  [1.0696762065233862, 1.1445832470336281]),
 (1.1070236618438374,
  1.1070236618438374,
  [1.0696762065233862, 1.1443711171642885]),
 (1.106541540741997,
  1.106541540741997,
  [1.0687119643197054, 1.1443711171642885]),
 (1.1068089818322315,
  1.1068089818322315,
  [1.0687119643197054, 1.1449059993447577]),
 (1.1061684222991417,
  1.1061684222991417,
  [1.0687119643197054, 1.143624880278578]),
 (1.106116691923674,
  1.106116691923674,
  [1.0687119643197054, 1.1435214195276426]),
 (1.1061692491600628,
  1.1061692491600628,
  [1.0687119643197054, 1.1436265340004201]),
 (1.1061688096980298,
  1.1061688096980298,
  [1.0687119643197054, 1.1436256550763542]),
 (1.1049719667633475,
  1.1049719667633475,
  [1.0663182784503409, 1.1436256550763542]),
 (1.1049470385106419,
  1.1049470385106419,
  [1.0663182784503409, 1.143575798570943]),
 (1.104248072377759,
  1.104248072377759,
  [1.0663182784503409, 1.1421778663051771]),
 (1.1039974133115038,
  1.1039974133115038,
  [1.0663182784503409, 1.1416765481726667]),
 (1.1040012862346664,
  1.1040012862346664,
  [1.0663260242966661, 1.1416765481726667]),
 (1.1039839194358656,
  1.1039839194358656,
  [1.0662912906990645, 1.1416765481726667]),
 (1.1036126737555714,
  1.1036126737555714,
  [1.065548799338476, 1.1416765481726667]),
 (1.1034683360929805,
  1.1034683360929805,
  [1.065548799338476, 1.1413878728474849]),
 (1.1063641205392845,
  1.1063641205392845,
  [1.071340368231084, 1.1413878728474849]),
 (1.1057035399214712,
  1.1057035399214712,
  [1.0700192069954575, 1.1413878728474849]),
 (1.107128480074631,
  1.107128480074631,
  [1.0700192069954575, 1.1442377531538046]),
 (1.1069016089009702,
  1.1069016089009702,
  [1.0695654646481358, 1.1442377531538046]),
 (1.1068800830384768,
  1.1068800830384768,
  [1.0695654646481358, 1.1441947014288179]),
 (1.106843098029902,
  1.106843098029902,
  [1.0695654646481358, 1.1441207314116681]),
 (1.1068199383041284,
  1.1068199383041284,
  [1.0695654646481358, 1.144074411960121]),
 (1.106818755341437,
  1.106818755341437,
  [1.0695654646481358, 1.1440720460347382]),
 (1.1067423883019112,
  1.1067423883019112,
  [1.0695654646481358, 1.1439193119556865]),
 (1.1067275518495343,
  1.1067275518495343,
  [1.069535791743382, 1.1439193119556865]),
 (1.1054158588695948,
  1.1054158588695948,
  [1.069535791743382, 1.1412959259958075]),
 (1.1054261702626551,
  1.1054261702626551,
  [1.0695564145295027, 1.1412959259958075]),
 (1.1053988368291812,
  1.1053988368291812,
  [1.0695564145295027, 1.1412412591288597]),
 (1.1055445786860423,
  1.1055445786860423,
  [1.0695564145295027, 1.1415327428425819]),
 (1.1055690019699682,
  1.1055690019699682,
  [1.0695564145295027, 1.1415815894104338]),
 (1.1055666758302287,
  1.1055666758302287,
  [1.0695517622500237, 1.1415815894104338]),
 (1.1067572045551364,
  1.1067572045551364,
  [1.071932819699839, 1.1415815894104338]),
 (1.1067536273700638,
  1.1067536273700638,
  [1.0719256653296938, 1.1415815894104338]),
 (1.1067480617875844,
  1.1067480617875844,
  [1.0719145341647351, 1.1415815894104338]),
 (1.1067214600892887,
  1.1067214600892887,
  [1.0719145341647351, 1.1415283860138423]),
 (1.1066931655678358,
  1.1066931655678358,
  [1.0719145341647351, 1.1414717969709365]),
 (1.1066387150605612,
  1.1066387150605612,
  [1.0719145341647351, 1.1413628959563873]),
 (1.1066290637299856,
  1.1066290637299856,
  [1.071895231503584, 1.1413628959563873]),
 (1.1065722047447606,
  1.1065722047447606,
  [1.071895231503584, 1.1412491779859373]),
 (1.1065642624136949,
  1.1065642624136949,
  [1.071895231503584, 1.1412332933238059]),
 (1.1065383434819074,
  1.1065383434819074,
  [1.071843393640009, 1.1412332933238059]),
 (1.1065016677981543,
  1.1065016677981543,
  [1.0717700422725027, 1.1412332933238059]),
 (1.106494344425264,
  1.106494344425264,
  [1.0717700422725027, 1.1412186465780252]),
 (1.1061633571693017,
  1.1061633571693017,
  [1.0711080677605782, 1.1412186465780252]),
 (1.1061578546416824,
  1.1061578546416824,
  [1.0711080677605782, 1.1412076415227865]),
 (1.1061435165608113,
  1.1061435165608113,
  [1.0711080677605782, 1.1411789653610445]),
 (1.1061192379880822,
  1.1061192379880822,
  [1.0711080677605782, 1.1411304082155862]),
 (1.1055419253976755,
  1.1055419253976755,
  [1.0699534425797648, 1.1411304082155862]),
 (1.1054993544342731,
  1.1054993544342731,
  [1.0699534425797648, 1.1410452662887813]),
 (1.1054406008073601,
  1.1054406008073601,
  [1.0699534425797648, 1.1409277590349554]),
 (1.1054146583027471,
  1.1054146583027471,
  [1.0699534425797648, 1.1408758740257294]),
 (1.1053994045693534,
  1.1053994045693534,
  [1.0699229351129773, 1.1408758740257294]),
 (1.1061891963827213,
  1.1061891963827213,
  [1.0699229351129773, 1.1424554576524653]),
 (1.1083487027716412,
  1.1083487027716412,
  [1.0699229351129773, 1.1467744704303051]),
 (1.1083238558346347,
  1.1083238558346347,
  [1.0698732412389642, 1.1467744704303051]),
 (1.1082269238297204,
  1.1082269238297204,
  [1.0698732412389642, 1.1465806064204767]),
 (1.1081777549848271,
  1.1081777549848271,
  [1.0697749035491775, 1.1465806064204767]),
 (1.1081388783290498,
  1.1081388783290498,
  [1.0697749035491775, 1.146502853108922]),
 (1.1081660592599247,
  1.1081660592599247,
  [1.0698292654109274, 1.146502853108922]),
 (1.1083050007602164,
  1.1083050007602164,
  [1.0698292654109274, 1.1467807361095055]),
 (1.1076636003871023,
  1.1076636003871023,
  [1.0698292654109274, 1.1454979353632773]),
 (1.1069311750224982,
  1.1069311750224982,
  [1.068364414681719, 1.1454979353632773]),
 (1.1068492815787012,
  1.1068492815787012,
  [1.0682006277941252, 1.1454979353632773]),
 (1.1082057225902133,
  1.1082057225902133,
  [1.0682006277941252, 1.1482108173863015]),
 (1.1081972030609792,
  1.1081972030609792,
  [1.068183588735657, 1.1482108173863015]),
 (1.1081914567647067,
  1.1081914567647067,
  [1.0681720961431118, 1.1482108173863015]),
 (1.108148125901522,
  1.108148125901522,
  [1.0681720961431118, 1.1481241556599322]),
 (1.108039528270373,
  1.108039528270373,
  [1.0679549008808138, 1.1481241556599322]),
 (1.1080380906209681,
  1.1080380906209681,
  [1.067952025582004, 1.1481241556599322]),
 (1.1080153412000735,
  1.1080153412000735,
  [1.0679065267402148, 1.1481241556599322]),
 (1.1079283653022616,
  1.1079283653022616,
  [1.0679065267402148, 1.1479502038643083]),
 (1.1073357082541477,
  1.1073357082541477,
  [1.0667212126439871, 1.1479502038643083]),
 (1.1073121672850608,
  1.1073121672850608,
  [1.0666741307058132, 1.1479502038643083]),
 (1.1081423118157412,
  1.1081423118157412,
  [1.0666741307058132, 1.1496104929256692]),
 (1.1112545093398207,
  1.1112545093398207,
  [1.0666741307058132, 1.1558348879738283]),
 (1.1103225869922095,
  1.1103225869922095,
  [1.0648102860105908, 1.1558348879738283]),
 (1.1104077906583703,
  1.1104077906583703,
  [1.0649806933429122, 1.1558348879738283]),
 (1.1103594373726198,
  1.1103594373726198,
  [1.0648839867714113, 1.1558348879738283]),
 (1.1103219039267822,
  1.1103219039267822,
  [1.0648839867714113, 1.1557598210821531]),
 (1.110076062255744,
  1.110076062255744,
  [1.0648839867714113, 1.1552681377400766]),
 (1.1097600388139757,
  1.1097600388139757,
  [1.0648839867714113, 1.15463609085654]),
 (1.1090420130565555,
  1.1090420130565555,
  [1.0648839867714113, 1.1532000393416997]),
 (1.1090042322571927,
  1.1090042322571927,
  [1.0648084251726857, 1.1532000393416997]),
 (1.1089805023744903,
  1.1089805023744903,
  [1.0648084251726857, 1.153152579576295]),
 (1.1090680925686662,
  1.1090680925686662,
  [1.0648084251726857, 1.1533277599646468]),
 (1.1082957923354808,
  1.1082957923354808,
  [1.0648084251726857, 1.151783159498276]),
 (1.108228200778786,
  1.108228200778786,
  [1.0646732420592961, 1.151783159498276]),
 (1.1082059230676142,
  1.1082059230676142,
  [1.0646732420592961, 1.1517386040759323]),
 (1.1076753429986992,
  1.1076753429986992,
  [1.063612081921466, 1.1517386040759323]),
 (1.1076550403716947,
  1.1076550403716947,
  [1.063571476667457, 1.1517386040759323]),
 (1.1071379637231518,
  1.1071379637231518,
  [1.0625373233703712, 1.1517386040759323]),
 (1.1071756903029693,
  1.1071756903029693,
  [1.0625373233703712, 1.1518140572355673]),
 (1.1071736097719391,
  1.1071736097719391,
  [1.062533162308311, 1.1518140572355673]),
 (1.1071146924025221,
  1.1071146924025221,
  [1.062415327569477, 1.1518140572355673]),
 (1.1071680186216772,
  1.1071680186216772,
  [1.062415327569477, 1.1519207096738775]),
 (1.108018309023274,
  1.108018309023274,
  [1.0641159083726706, 1.1519207096738775]),
 (1.1075834498921608,
  1.1075834498921608,
  [1.0641159083726706, 1.1510509914116511]),
 (1.1066894774402511,
  1.1066894774402511,
  [1.0623279634688512, 1.1510509914116511]),
 (1.1063465391726819,
  1.1063465391726819,
  [1.0623279634688512, 1.1503651148765126]),
 (1.1063442127806242,
  1.1063442127806242,
  [1.0623233106847358, 1.1503651148765126]),
 (1.1083077169383486,
  1.1083077169383486,
  [1.0623233106847358, 1.1542921231919614]),
 (1.1083023835532391,
  1.1083023835532391,
  [1.0623126439145167, 1.1542921231919614]),
 (1.1083038001726626,
  1.1083038001726626,
  [1.0623126439145167, 1.1542949564308085]),
 (1.1083025136684315,
  1.1083025136684315,
  [1.0623100709060544, 1.1542949564308085]),
 (1.1082983838115332,
  1.1082983838115332,
  [1.062301811192258, 1.1542949564308085]),
 (1.1082969518105266,
  1.1082969518105266,
  [1.0622989471902446, 1.1542949564308085]),
 (1.1094022695530006,
  1.1094022695530006,
  [1.0645095826751927, 1.1542949564308085]),
 (1.1096725145772872,
  1.1096725145772872,
  [1.065050072723766, 1.1542949564308085]),
 (1.109657521279372,
  1.109657521279372,
  [1.065050072723766, 1.154264969834978]),
 (1.1096195186906606,
  1.1096195186906606,
  [1.065050072723766, 1.1541889646575552]),
 (1.1099932529958236,
  1.1099932529958236,
  [1.065050072723766, 1.1549364332678813]),
 (1.1099979670018181,
  1.1099979670018181,
  [1.0650595007357548, 1.1549364332678813]),
 (1.1101307960102069,
  1.1101307960102069,
  [1.0650595007357548, 1.155202091284659]),
 (1.1142242375977807,
  1.1142242375977807,
  [1.0732463839109023, 1.155202091284659]),
 (1.1141518824309093,
  1.1141518824309093,
  [1.0732463839109023, 1.1550573809509164]),
 (1.1139039751006496,
  1.1139039751006496,
  [1.072750569250383, 1.1550573809509164]),
 (1.1133902767307831,
  1.1133902767307831,
  [1.0717231725106497, 1.1550573809509164]),
 (1.1147470553687802,
  1.1147470553687802,
  [1.0717231725106497, 1.1577709382269106]),
 (1.1147161413926057,
  1.1147161413926057,
  [1.0717231725106497, 1.1577091102745616]),
 (1.1145948885872974,
  1.1145948885872974,
  [1.0714806669000332, 1.1577091102745616]),
 (1.1144547027235259,
  1.1144547027235259,
  [1.0712002951724902, 1.1577091102745616]),
 (1.1158802547311106,
  1.1158802547311106,
  [1.0740513991876597, 1.1577091102745616]),
 (1.1155088536577731,
  1.1155088536577731,
  [1.0733085970409846, 1.1577091102745616]),
 (1.1154933151382496,
  1.1154933151382496,
  [1.0733085970409846, 1.1576780332355145]),
 (1.1154921973841407,
  1.1154921973841407,
  [1.073306361532767, 1.1576780332355145]),
 (1.1154917537699447,
  1.1154917537699447,
  [1.073306361532767, 1.1576771460071225]),
 (1.1153393665278362,
  1.1153393665278362,
  [1.073306361532767, 1.1573723715229054]),
 (1.1153296895682443,
  1.1153296895682443,
  [1.0732870076135832, 1.1573723715229054]),
 (1.1210408275494963,
  1.1210408275494963,
  [1.0847092835760872, 1.1573723715229054]),
 (1.1215292523553604,
  1.1215292523553604,
  [1.0856861331878154, 1.1573723715229054]),
 (1.1211297548206609,
  1.1211297548206609,
  [1.0848871381184164, 1.1573723715229054]),
 (1.1231422765748862,
  1.1231422765748862,
  [1.0848871381184164, 1.161397415031356]),
 (1.1245221422751825,
  1.1245221422751825,
  [1.0876468695190091, 1.161397415031356]),
 (1.1245067348618569,
  1.1245067348618569,
  [1.0876468695190091, 1.1613666002047047]),
 (1.1236379428824499,
  1.1236379428824499,
  [1.085909285560195, 1.1613666002047047]),
 (1.1236753938752937,
  1.1236753938752937,
  [1.0859841875458827, 1.1613666002047047]),
 (1.1237494205692204,
  1.1237494205692204,
  [1.0861322409337362, 1.1613666002047047]),
 (1.1237447792814024,
  1.1237447792814024,
  [1.0861322409337362, 1.1613573176290686]),
 (1.1236860665668429,
  1.1236860665668429,
  [1.0860148155046172, 1.1613573176290686]),
 (1.1236762771198965,
  1.1236762771198965,
  [1.0859952366107244, 1.1613573176290686]),
 (1.1236749753718067,
  1.1236749753718067,
  [1.0859926331145449, 1.1613573176290686]),
 (1.1235921943878004,
  1.1235921943878004,
  [1.0859926331145449, 1.161191755661056]),
 (1.1235825669738162,
  1.1235825669738162,
  [1.0859926331145449, 1.1611725008330875]),
 (1.1264059050837236,
  1.1264059050837236,
  [1.0859926331145449, 1.1668191770529024]),
 (1.1264187133451955,
  1.1264187133451955,
  [1.0860182496374886, 1.1668191770529024]),
 (1.126395321587558,
  1.126395321587558,
  [1.0859714661222135, 1.1668191770529024]),
 (1.1283783719983349,
  1.1283783719983349,
  [1.0899375669437674, 1.1668191770529024]),
 (1.128734020792586,
  1.128734020792586,
  [1.0899375669437674, 1.1675304746414046]),
 (1.1285896101590414,
  1.1285896101590414,
  [1.0899375669437674, 1.1672416533743153]),
 (1.1296359524426016,
  1.1296359524426016,
  [1.092030251510888, 1.1672416533743153]),
 (1.1296266638104981,
  1.1296266638104981,
  [1.092011674246681, 1.1672416533743153]),
 (1.1296237309848172,
  1.1296237309848172,
  [1.092005808595319, 1.1672416533743153]),
 (1.1296375067806732,
  1.1296375067806732,
  [1.0920333601870311, 1.1672416533743153]),
 (1.1296365825847294,
  1.1296365825847294,
  [1.0920315117951436, 1.1672416533743153]),
 (1.1296337250072943,
  1.1296337250072943,
  [1.0920315117951436, 1.167235938219445]),
 (1.1320795143964597,
  1.1320795143964597,
  [1.0920315117951436, 1.1721275169977758]),
 (1.1320759371632745,
  1.1320759371632745,
  [1.0920243573287731, 1.1721275169977758]),
 (1.1320723599180624,
  1.1320723599180624,
  [1.092017202838349, 1.1721275169977758]),
 (1.1320719163038664,
  1.1320719163038664,
  [1.092017202838349, 1.1721266297693838]),
 (1.1324173947097931,
  1.1324173947097931,
  [1.0927081596502024, 1.1721266297693838]),
 (1.1350595630715103,
  1.1350595630715103,
  [1.097992496373637, 1.1721266297693838]),
 (1.1345063059435851,
  1.1345063059435851,
  [1.097992496373637, 1.1710201155135334]),
 (1.1344755890794742,
  1.1344755890794742,
  [1.097992496373637, 1.1709586817853115]),
 (1.1343989008601731,
  1.1343989008601731,
  [1.0978391199350348, 1.1709586817853115]),
 (1.1317552857660917,
  1.1317552857660917,
  [1.092551889746872, 1.1709586817853115]),
 (1.1342097456453981,
  1.1342097456453981,
  [1.0974608095054847, 1.1709586817853115]),
 (1.1342013331854304,
  1.1342013331854304,
  [1.0974439845855493, 1.1709586817853115]),
 (1.1341838137320037,
  1.1341838137320037,
  [1.097408945678696, 1.1709586817853115]),
 (1.1333661507671122,
  1.1333661507671122,
  [1.097408945678696, 1.1693233558555285]),
 (1.1328311123508126,
  1.1328311123508126,
  [1.097408945678696, 1.1682532790229292]),
 (1.1328235242984617,
  1.1328235242984617,
  [1.0973937695739941, 1.1682532790229292]),
 (1.1318378213536846,
  1.1318378213536846,
  [1.0973937695739941, 1.166281873133375]),
 (1.131665716304485,
  1.131665716304485,
  [1.0973937695739941, 1.1659376630349758]),
 (1.1316369744525607,
  1.1316369744525607,
  [1.0973362858701456, 1.1659376630349758]),
 (1.1315392882637711,
  1.1315392882637711,
  [1.0971409134925665, 1.1659376630349758]),
 (1.1354917219255194,
  1.1354917219255194,
  [1.105045780816063, 1.1659376630349758]),
 (1.1384682810015931,
  1.1384682810015931,
  [1.105045780816063, 1.1718907811871233]),
 (1.1385566863819694,
  1.1385566863819694,
  [1.1052225915768155, 1.1718907811871233]),
 (1.1386691380296323,
  1.1386691380296323,
  [1.1054474948721413, 1.1718907811871233]),
 (1.1386671505259933,
  1.1386671505259933,
  [1.1054435198648633, 1.1718907811871233]),
 (1.1386317278745981,
  1.1386317278745981,
  [1.1053726745620729, 1.1718907811871233]),
 (1.1386178287580719,
  1.1386178287580719,
  [1.1053448763290206, 1.1718907811871233]),
 (1.1385032068999026,
  1.1385032068999026,
  [1.1051156326126819, 1.1718907811871233]),
 (1.1384423298322064,
  1.1384423298322064,
  [1.1051156326126819, 1.171769027051731]),
 (1.1384401269318563,
  1.1384401269318563,
  [1.1051112268119816, 1.171769027051731]),
 (1.1380615159867986,
  1.1380615159867986,
  [1.1043540049218663, 1.171769027051731]),
 (1.1380597737332474,
  1.1380597737332474,
  [1.1043540049218663, 1.1717655425446285]),
 (1.1389419695969778,
  1.1389419695969778,
  [1.1043540049218663, 1.1735299342720893]),
 (1.1389368627521224,
  1.1389368627521224,
  [1.1043540049218663, 1.1735197205823784]),
 (1.1398818543632103,
  1.1398818543632103,
  [1.1043540049218663, 1.1754097038045543]),
 (1.1391254798787696,
  1.1391254798787696,
  [1.1043540049218663, 1.1738969548356728]),
 (1.1389577836321871,
  1.1389577836321871,
  [1.1043540049218663, 1.173561562342508]),
 (1.1387903158045267,
  1.1387903158045267,
  [1.1043540049218663, 1.1732266266871871]),
 (1.1414275996615943,
  1.1414275996615943,
  [1.1096285726360016, 1.1732266266871871]),
 (1.1431689183343448,
  1.1431689183343448,
  [1.1131112099815024, 1.1732266266871871]),
 (1.1431675747811623,
  1.1431675747811623,
  [1.1131085228751374, 1.1732266266871871]),
 (1.143135585791307,
  1.143135585791307,
  [1.1131085228751374, 1.1731626487074767]),
 (1.1438857981635113,
  1.1438857981635113,
  [1.114608947619546, 1.1731626487074767]),
 (1.1438209539374204,
  1.1438209539374204,
  [1.1144792591673642, 1.1731626487074767]),
 (1.1452259834016925,
  1.1452259834016925,
  [1.1172893180959083, 1.1731626487074767]),
 (1.145209833205282,
  1.145209833205282,
  [1.1172893180959083, 1.1731303483146558]),
 (1.1447643492214947,
  1.1447643492214947,
  [1.1172893180959083, 1.1722393803470812]),
 (1.1447647981498452,
  1.1447647981498452,
  [1.1172902159526092, 1.1722393803470812]),
 (1.1466733027605782,
  1.1466733027605782,
  [1.1211072251740752, 1.1722393803470812]),
 (1.1466166092414456,
  1.1466166092414456,
  [1.12099383813581, 1.1722393803470812]),
 (1.1466173501885599,
  1.1466173501885599,
  [1.1209953200300387, 1.1722393803470812]),
 (1.1465607422605748,
  1.1465607422605748,
  [1.1208821041740684, 1.1722393803470812]),
 (1.1465515307574821,
  1.1465515307574821,
  [1.1208821041740684, 1.1722209573408957]),
 (1.1466363575862246,
  1.1466363575862246,
  [1.1210517578315535, 1.1722209573408957]),
 (1.1466335184673362,
  1.1466335184673362,
  [1.1210517578315535, 1.1722152791031188]),
 (1.1466166894195169,
  1.1466166894195169,
  [1.1210517578315535, 1.1721816210074802]),
 (1.1466079220848178,
  1.1466079220848178,
  [1.1210517578315535, 1.172164086338082]),
 (1.1465850610971087,
  1.1465850610971087,
  [1.1210060358561353, 1.172164086338082]),
 (1.1466700922223945,
  1.1466700922223945,
  [1.1210060358561353, 1.1723341485886536]),
 (1.1466864741223377,
  1.1466864741223377,
  [1.1210060358561353, 1.17236691238854]),
 (1.1470762476466234,
  1.1470762476466234,
  [1.1217855829047068, 1.17236691238854]),
 (1.1469888035311993,
  1.1469888035311993,
  [1.1217855829047068, 1.1721920241576917]),
 (1.150079032338982,
  1.150079032338982,
  [1.1217855829047068, 1.1783724817732573]),
 (1.1500626137866865,
  1.1500626137866865,
  [1.1217527458001157, 1.1783724817732573]),
 (1.1500579970059279,
  1.1500579970059279,
  [1.1217527458001157, 1.17836324821174]),
 (1.1505036348906286,
  1.1505036348906286,
  [1.1217527458001157, 1.1792545239811414]),
 (1.1504954766733171,
  1.1504954766733171,
  [1.1217364293654928, 1.1792545239811414]),
 (1.1504844357507151,
  1.1504844357507151,
  [1.1217143475202889, 1.1792545239811414]),
 (1.1531623214940216,
  1.1531623214940216,
  [1.1217143475202889, 1.1846102954677544]),
 (1.156842146858887,
  1.156842146858887,
  [1.1217143475202889, 1.191969946197485]),
 (1.1571382645639483,
  1.1571382645639483,
  [1.1217143475202889, 1.1925621816076077]),
 (1.1562427036445246,
  1.1562427036445246,
  [1.1199232256814415, 1.1925621816076077]),
 (1.1568305244053256,
  1.1568305244053256,
  [1.1199232256814415, 1.1937378231292097]),
 (1.1581154319250286,
  1.1581154319250286,
  [1.1199232256814415, 1.1963076381686157]),
 (1.1594813445927148,
  1.1594813445927148,
  [1.1226550510168138, 1.1963076381686157]),
 (1.1594785644784356,
  1.1594785644784356,
  [1.1226494907882554, 1.1963076381686157]),
 (1.1593629555353218,
  1.1593629555353218,
  [1.1226494907882554, 1.1960764202823881]),
 (1.1593706634783336,
  1.1593706634783336,
  [1.122664906674279, 1.1960764202823881]),
 (1.1594247590767832,
  1.1594247590767832,
  [1.1227730978711783, 1.1960764202823881]),
 (1.1594215059879049,
  1.1594215059879049,
  [1.1227665916934217, 1.1960764202823881]),
 (1.1607707972858794,
  1.1607707972858794,
  [1.1254651742893707, 1.1960764202823881]),
 (1.160765311915358,
  1.160765311915358,
  [1.125454203548328, 1.1960764202823881]),
 (1.1609302187301855,
  1.1609302187301855,
  [1.125784017177983, 1.1960764202823881]),
 (1.1609149857167589,
  1.1609149857167589,
  [1.1257535511511296, 1.1960764202823881]),
 (1.1603373576242557,
  1.1603373576242557,
  [1.1257535511511296, 1.1949211640973818]),
 (1.1597219162325789,
  1.1597219162325789,
  [1.1257535511511296, 1.1936902813140282]),
 (1.1591659883689607,
  1.1591659883689607,
  [1.1246416954238931, 1.1936902813140282]),
 (1.1579586908538273,
  1.1579586908538273,
  [1.1222271003936264, 1.1936902813140282]),
 (1.157956830433017,
  1.157956830433017,
  [1.1222233795520058, 1.1936902813140282]),
 (1.1579558812145949,
  1.1579558812145949,
  [1.1222214811151616, 1.1936902813140282]),
 (1.1579541662186701,
  1.1579541662186701,
  [1.1222214811151616, 1.1936868513221786]),
 (1.1580847544619299,
  1.1580847544619299,
  [1.1224826576016813, 1.1936868513221786]),
 (1.1580871104103556,
  1.1580871104103556,
  [1.1224826576016813, 1.19369156321903]),
 (1.1579234909804414,
  1.1579234909804414,
  [1.1224826576016813, 1.1933643243592016]),
 (1.1592324525077915,
  1.1592324525077915,
  [1.1224826576016813, 1.1959822474139017]),
 (1.1606223873400516,
  1.1606223873400516,
  [1.1224826576016813, 1.198762117078422]),
 (1.1605971402572148,
  1.1605971402572148,
  [1.1224321634360077, 1.198762117078422]),
 (1.1605902631294036,
  1.1605902631294036,
  [1.1224321634360077, 1.1987483628227995]),
 (1.1603707694224692,
  1.1603707694224692,
  [1.1219931760221389, 1.1987483628227995]),
 (1.1632182010113681,
  1.1632182010113681,
  [1.1219931760221389, 1.2044432260005973]),
 (1.16738937934739, 1.16738937934739, [1.1219931760221389, 1.212785582672641]),
 (1.1673790182847954,
  1.1673790182847954,
  [1.1219931760221389, 1.212764860547452]),
 (1.1673786018376298,
  1.1673786018376298,
  [1.1219923431278076, 1.212764860547452]),
 (1.1673759143302496,
  1.1673759143302496,
  [1.1219923431278076, 1.2127594855326915]),
 (1.1673732266279595,
  1.1673732266279595,
  [1.1219923431278076, 1.2127541101281114]),
 (1.1673291477875027,
  1.1673291477875027,
  [1.121904185446894, 1.2127541101281114]),
 (1.1684200824366808,
  1.1684200824366808,
  [1.121904185446894, 1.2149359794264676]),
 (1.1700271085843221,
  1.1700271085843221,
  [1.1251182377421767, 1.2149359794264676]),
 (1.1689250306635923,
  1.1689250306635923,
  [1.122914081900717, 1.2149359794264676]),
 (1.1689148919867671,
  1.1689148919867671,
  [1.122914081900717, 1.2149157020728172]),
 (1.1687728975711984,
  1.1687728975711984,
  [1.122914081900717, 1.2146317132416797]),
 (1.1705971345737192,
  1.1705971345737192,
  [1.1265625559057586, 1.2146317132416797]),
 (1.1708029902922128,
  1.1708029902922128,
  [1.1269742673427459, 1.2146317132416797]),
 (1.1713548463879322,
  1.1713548463879322,
  [1.1280779795341846, 1.2146317132416797]),
 (1.1710794396182544,
  1.1710794396182544,
  [1.1280779795341846, 1.2140808997023242]),
 (1.1728862120419832,
  1.1728862120419832,
  [1.1280779795341846, 1.2176944445497817]),
 (1.1728834158166332,
  1.1728834158166332,
  [1.1280723870834848, 1.2176944445497817]),
 (1.1728917264893912,
  1.1728917264893912,
  [1.1280723870834848, 1.2177110658952977]),
 (1.1728823224648419,
  1.1728823224648419,
  [1.1280723870834848, 1.217692257846199]),
 (1.175874030832099,
  1.175874030832099,
  [1.1280723870834848, 1.2236756745807131]),
 (1.1754697826720752,
  1.1754697826720752,
  [1.1272638907634374, 1.2236756745807131]),
 (1.1754561334757536,
  1.1754561334757536,
  [1.1272638907634374, 1.2236483761880699]),
 (1.1754522040506457,
  1.1754522040506457,
  [1.1272638907634374, 1.223640517337854]),
 (1.1786346779893533,
  1.1786346779893533,
  [1.1272638907634374, 1.2300054652152692]),
 (1.1798045833589859,
  1.1798045833589859,
  [1.1272638907634374, 1.2323452759545344]),
 (1.1832225311672753,
  1.1832225311672753,
  [1.1272638907634374, 1.2391811715711132]),
 (1.1860890533961967,
  1.1860890533961967,
  [1.1329969352212803, 1.2391811715711132]),
 (1.187047149596494,
  1.187047149596494,
  [1.134913127621875, 1.2391811715711132]),
 (1.1874688747164548,
  1.1874688747164548,
  [1.134913127621875, 1.2400246218110347]),
 (1.1874563180763307,
  1.1874563180763307,
  [1.1348880143416267, 1.2400246218110347]),
 (1.1876696512626284,
  1.1876696512626284,
  [1.1348880143416267, 1.24045128818363]),
 (1.1912185963745321,
  1.1912185963745321,
  [1.1348880143416267, 1.2475491784074375]),
 (1.1932272253525857,
  1.1932272253525857,
  [1.138905272297734, 1.2475491784074375]),
 (1.1932167792813351,
  1.1932167792813351,
  [1.1388843801552326, 1.2475491784074375]),
 (1.1931883850380158,
  1.1931883850380158,
  [1.1388275916685942, 1.2475491784074375]),
 (1.1964671893721448,
  1.1964671893721448,
  [1.1388275916685942, 1.2541067870756955]),
 (1.1964639443051848,
  1.1964639443051848,
  [1.138821101534674, 1.2541067870756955]),
 (1.1992541192103952,
  1.1992541192103952,
  [1.138821101534674, 1.2596871368861162]),
 (1.2008152335294131,
  1.2008152335294131,
  [1.14194333017271, 1.2596871368861162]),
 (1.2002746808040312,
  1.2002746808040312,
  [1.14194333017271, 1.2586060314353524]),
 (1.1985363200467134,
  1.1985363200467134,
  [1.1384666086580744, 1.2586060314353524]),
 (1.1985301522316334,
  1.1985301522316334,
  [1.1384542730279144, 1.2586060314353524]),
 (1.1985005236934283,
  1.1985005236934283,
  [1.1384542730279144, 1.2585467743589422]),
 (1.197996129373438,
  1.197996129373438,
  [1.1374454843879338, 1.2585467743589422])]

In [56]:

    

gp.metrics.adapted_rand(out_cA_volume_after_auto_95, input_gold)


    

    
Out[56]:





0.51512425659267813

In [57]:

    

cA_auto_fixes_95


    

    
Out[57]:





[(0, 0.99999964237213135),
 (1, 0.99993455410003662),
 (0, 0.99991738796234131),
 (0, 0.99988996982574463),
 (0, 0.99985110759735107),
 (0, 0.99977564811706543),
 (0, 0.9997628927230835),
 (1, 0.99975866079330444),
 (0, 0.99974793195724487),
 (0, 0.99972277879714966),
 (0, 0.99971282482147217),
 (0, 0.99967020750045776),
 (1, 0.99959456920623779),
 (1, 0.999583899974823),
 (0, 0.99957650899887085),
 (1, 0.99951696395874023),
 (1, 0.99937832355499268),
 (0, 0.99928903579711914),
 (1, 0.99907684326171875),
 (0, 0.99902892112731934),
 (0, 0.99892705678939819),
 (0, 0.99888914823532104),
 (1, 0.9998706579208374),
 (1, 0.99888545274734497),
 (1, 0.99886083602905273),
 (0, 0.99883228540420532),
 (0, 0.99930858612060547),
 (0, 0.99880576133728027),
 (0, 0.99867504835128784),
 (1, 0.99838781356811523),
 (0, 0.99836021661758423),
 (1, 0.998313307762146),
 (0, 0.99977326393127441),
 (1, 0.99948069096907322),
 (0, 0.99829679727554321),
 (0, 0.99823164939880371),
 (0, 0.99810117483139038),
 (0, 0.99805045127868652),
 (0, 0.99798670411109924),
 (0, 0.99796545505523682),
 (1, 0.99765539169311523),
 (0, 0.99762481451034546),
 (1, 0.99757093191146851),
 (0, 0.99745088815689087),
 (1, 0.99744629859924316),
 (1, 0.99806791543960571),
 (0, 0.99728477001190186),
 (0, 0.99722194671630859),
 (1, 0.99717354774475098),
 (0, 0.99704605340957642),
 (0, 0.99807000160217285),
 (0, 0.99698829650878906),
 (0, 0.99676239490509033),
 (0, 0.99669891595840454),
 (0, 0.99664163589477539),
 (0, 0.99662810564041138),
 (0, 0.99655932188034058),
 (0, 0.99610930681228638),
 (1, 0.99609392881393433),
 (0, 0.99608230590820312),
 (0, 0.99596571922302246),
 (0, 0.99592643976211548),
 (0, 0.99586522579193115),
 (1, 0.99584603309631348),
 (1, 0.99571734666824341),
 (0, 0.99563068151473999),
 (0, 0.99558982253074646),
 (0, 0.99545818567276001),
 (1, 0.99520617723464966),
 (1, 0.99858176708221436),
 (0, 0.99508821964263916),
 (1, 0.99479794502258301),
 (1, 0.99470651149749756),
 (1, 0.9941592812538147),
 (1, 0.99396717548370361),
 (0, 0.99283701181411743),
 (0, 0.99251586198806763),
 (0, 0.99240303039550781),
 (1, 0.99220532178878784),
 (1, 0.99119514226913452),
 (0, 0.99049967527389526),
 (0, 0.99032366275787354),
 (0, 0.9902946949005127),
 (0, 0.98964732885360718),
 (0, 0.98952430486679077),
 (1, 0.98878282308578491),
 (1, 0.98830831050872803),
 (1, 0.98825187203676801),
 (1, 0.98817014694213867),
 (1, 0.98795485496520996),
 (1, 0.98782742023468018),
 (0, 0.98770588636398315),
 (0, 0.98676592111587524),
 (0, 0.98664224147796631),
 (0, 0.99529153108596802),
 (0, 0.98566669225692749),
 (1, 0.98557388782501221),
 (0, 0.98524630069732666),
 (0, 0.98451739549636841),
 (0, 0.98307508230209351),
 (1, 0.99812740087509155),
 (0, 0.99524879455566406),
 (0, 0.98302602767944336),
 (0, 0.98286211490631104),
 (0, 0.98253953456878662),
 (0, 0.98217910528182983),
 (1, 0.98078876733779907),
 (0, 0.98034143447875977),
 (1, 0.98022262223979884),
 (1, 0.97997605800628662),
 (0, 0.97958779335021973),
 (0, 0.9959639310836792),
 (0, 0.9790610671043396),
 (1, 0.98605304956436157),
 (0, 0.98372703790664673),
 (0, 0.97891914844512939),
 (0, 0.97822648286819458),
 (0, 0.97803950309753418),
 (0, 0.97624921798706055),
 (0, 0.97606635093688965),
 (0, 0.97589010000228882),
 (0, 0.9756653904914856),
 (0, 0.97457212209701538),
 (0, 0.97356939315795898),
 (0, 0.97215241193771362),
 (1, 0.96742033958435059),
 (0, 0.9673839807510376),
 (0, 0.96642327308654785),
 (0, 0.99197017055354353),
 (0, 0.9648902416229248),
 (0, 0.96455860137939453),
 (1, 0.96431434154510498),
 (1, 0.96414023637771606),
 (1, 0.96714228391647339),
 (0, 0.9639352560043335),
 (1, 0.97564470767974854),
 (0, 0.96214890480041504),
 (1, 0.96146029233932495),
 (1, 0.95773845911026001),
 (1, 0.9564635157585144),
 (0, 0.95535880327224731),
 (0, 0.95426416397094727),
 (0, 0.98732763528823853),
 (1, 0.95347857475280762),
 (1, 0.95283713042736051),
 (0, 0.95283502340316772),
 (1, 0.9515417218208313),
 (0, 0.95060360431671143)]

In [64]:

    

import numpy as np


    

In [70]:

    

p = np.load('/tmp/trainB.npz.npy', mmap_mode='r')
t = np.load('/tmp/trainB_targets.npz.npy', mmap_mode='r')


    

In [80]:

    

gp.Util.view(p[2][0], color=False)


    

In [81]:

    

gp.Util.view(p[2][1], color=False)


    

In [83]:

    

gp.Util.view(p[2][3], color=False)


    

In [79]:

    

t[2]


    

    
Out[79]:





1.0

In [ ]: