Execution Time0.06s

Test: TMVA-DNN-RNN-FullRNN-Cpu (Passed)
Build: PR-4279-x86_64-ubuntu16-gcc54-opt (sft-ubuntu-1604-4) on 2019-11-14 21:01:42
Repository revision: eb9d2d64c365eec560379f62009bcc1579861643

Test Timing: Passed
Processors1

Show Command Line
Display graphs:

Test output
Training RNN to identity firstCopying output into input
Copying output into input
loss: 0.528085
loss: 0.210558
loss: 0.0834646
loss: 0.0344969
loss: 0.0157702
loss: 0.0083044
loss: 0.00505424
loss: 0.00347144
loss: 0.00261245
loss: 0.00210264
loss: 0.00177748
loss: 0.00155681
loss: 0.00139811
loss: 0.00127745
loss: 0.00118092
loss: 0.0011002
loss: 0.00103028
loss: 0.000968058
loss: 0.000911625
loss: 0.000859766
loss: 0.000811657
loss: 0.000766778
loss: 0.000724743
loss: 0.000685264
loss: 0.000648118
loss: 0.000613135
loss: 0.000580161
loss: 0.000549062
loss: 0.000519718
loss: 0.000492024
loss: 0.000465881
loss: 0.000441194
loss: 0.000417882
loss: 0.000395859
loss: 0.000375051
loss: 0.000355396
loss: 0.000336821
loss: 0.000319265
loss: 0.000302669
loss: 0.000286983
loss: 0.000272147
loss: 0.00025812
loss: 0.000244853
loss: 0.000232304
loss: 0.000220431
loss: 0.000209196
loss: 0.000198566
loss: 0.000188507
loss: 0.000178984
loss: 0.000169968
Training RNN to simple time dependent data iter = 1 loss: 0.811662
iter = 2 loss: 0.77582
iter = 3 loss: 0.754523
iter = 4 loss: 0.737922
iter = 5 loss: 0.722727
iter = 6 loss: 0.706929
iter = 7 loss: 0.691102
iter = 8 loss: 0.676872
iter = 9 loss: 0.66505
iter = 10 loss: 0.65503
iter = 11 loss: 0.645015
iter = 12 loss: 0.634222
iter = 13 loss: 0.622432
iter = 14 loss: 0.609575
iter = 15 loss: 0.595603
iter = 16 loss: 0.580476
iter = 17 loss: 0.564187
iter = 18 loss: 0.546807
iter = 19 loss: 0.52853
iter = 20 loss: 0.509677
iter = 21 loss: 0.490641
iter = 22 loss: 0.47177
iter = 23 loss: 0.453279
iter = 24 loss: 0.435246
iter = 25 loss: 0.417667
iter = 26 loss: 0.400524
iter = 27 loss: 0.383813
iter = 28 loss: 0.367549
iter = 29 loss: 0.351755
iter = 30 loss: 0.336461
iter = 31 loss: 0.321695
iter = 32 loss: 0.307479
iter = 33 loss: 0.293831
iter = 34 loss: 0.280762
iter = 35 loss: 0.268276
iter = 36 loss: 0.256372
iter = 37 loss: 0.245043
iter = 38 loss: 0.23428
iter = 39 loss: 0.224066
iter = 40 loss: 0.214385
iter = 41 loss: 0.205219
iter = 42 loss: 0.196545
iter = 43 loss: 0.188343
iter = 44 loss: 0.180591
iter = 45 loss: 0.173265
iter = 46 loss: 0.166345
iter = 47 loss: 0.159809
iter = 48 loss: 0.153635
iter = 49 loss: 0.147802
iter = 50 loss: 0.142292

2x64 matrix is as follows

     |       0    |       1    |       2    |       3    |       4    |
----------------------------------------------------------------------
   0 |          1           1           0           1           0 
   1 |     0.9168       0.848      0.1393      0.8967      0.1348 


     |       5    |       6    |       7    |       8    |       9    |
----------------------------------------------------------------------
   0 |          1           0           1           1           1 
   1 |     0.9053      0.1418      0.9113      0.9123      0.8655 


     |      10    |      11    |      12    |      13    |      14    |
----------------------------------------------------------------------
   0 |          1           1           0           1           1 
   1 |     0.8257      0.9132      0.1378       0.902      0.8814 


     |      15    |      16    |      17    |      18    |      19    |
----------------------------------------------------------------------
   0 |          1           0           1           0           0 
   1 |     0.9108      0.1503      0.9124      0.1109      0.1496 


     |      20    |      21    |      22    |      23    |      24    |
----------------------------------------------------------------------
   0 |          1           0           0           0           1 
   1 |     0.8087      0.1353      0.1185      0.1321      0.9181 


     |      25    |      26    |      27    |      28    |      29    |
----------------------------------------------------------------------
   0 |          1           1           0           0           1 
   1 |     0.9011      0.8565      0.1379      0.1409      0.8892 


     |      30    |      31    |      32    |      33    |      34    |
----------------------------------------------------------------------
   0 |          1           0           0           0           0 
   1 |      0.881      0.1252      0.1358      0.1223      0.1382 


     |      35    |      36    |      37    |      38    |      39    |
----------------------------------------------------------------------
   0 |          1           0           0           1           0 
   1 |     0.8593      0.1336      0.1397      0.9005      0.1312 


     |      40    |      41    |      42    |      43    |      44    |
----------------------------------------------------------------------
   0 |          0           1           1           1           1 
   1 |     0.1305      0.8835      0.9086      0.9005      0.9044 


     |      45    |      46    |      47    |      48    |      49    |
----------------------------------------------------------------------
   0 |          1           0           0           1           0 
   1 |     0.7747      0.1412      0.1257      0.9063      0.1317 


     |      50    |      51    |      52    |      53    |      54    |
----------------------------------------------------------------------
   0 |          0           0           1           1           0 
   1 |     0.1339      0.2497      0.8319      0.9166      0.1375 


     |      55    |      56    |      57    |      58    |      59    |
----------------------------------------------------------------------
   0 |          1           1           0           1           0 
   1 |     0.8286      0.9045      0.1317      0.8822      0.1372 


     |      60    |      61    |      62    |      63    |
----------------------------------------------------------------------
   0 |          0           1           1           1 
   1 |     0.2627      0.9136      0.8998      0.9189 

ROC integral is 0.453247
Test full RNN passed : Efficiencies are 0 and 1