Execution Time1.10s

Test: TMVA-DNN-RNN-Backpropagation (Passed)
Build: master-x86_64-mac1014-clang100-opt-exp-cxxmod (macitois21.cern.ch) on 2019-11-14 00:07:23

Test Timing: Passed
Processors1

Show Command Line
Display graphs:

Test output
Testing RNN backward pass
Testing Weight Backprop using RNN with batchsize = 2 input = 10 state = 1 time = 1	using a random input
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m6.70603e-10[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (absolute): [NON-XML-CHAR-0x1B][32m0[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m1.48786e-11[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 2 input = 10 state = 1 time = 2	using a random input
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m1.53171e-10[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m6.33667e-11[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m5.83198e-11[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 2 input = 10 state = 2 time = 1	using a random input
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m2.2469e-10[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (absolute): [NON-XML-CHAR-0x1B][32m0[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m3.39287e-11[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 1 input = 5 state = 2 time = 2	using a random input
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m3.1703e-10[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m1.06041e-10[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m4.29287e-11[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 2 input = 10 state = 3 time = 4	using a random input
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m4.41478e-08[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m6.30377e-09[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m1.43331e-10[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 1 input = 5 state = 4 time = 3	with a fixed input and a dense layer and an extra RNN
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m1.59034e-07[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m3.24737e-08[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m7.48396e-09[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 32 input = 5 state = 10 time = 4	using a random input and a dense layer
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m4.8875e-09[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m2.78595e-07[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m3.79306e-09[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 32 input = 5 state = 10 time = 4	using a random input and a dense layer and an extra RNN
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m7.1874e-08[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m3.43701e-07[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m4.06941e-10[NON-XML-CHAR-0x1B][39m