Execution Time0.31s

Test: TMVA-DNN-RNN-Backpropagation-Cpu (Passed)
Build: master-x86_64-fedora28-gcc8 (sft-fedora-28-1.cern.ch) on 2019-11-16 01:09:06

Test Timing: Passed
Processors1

Show Command Line
Display graphs:

Test output
Testing RNN backward pass
Testing Weight Backprop using RNN with batchsize = 2 input = 2 state = 1 time = 1	using a random input
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m0.0280278[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in weight input gradients
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][31m0.0916595[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 2 input = 2 state = 3 time = 1	using a random input
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in bias state gradients
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m0.0368327[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in weight input gradients
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][31m0.00466246[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 3 input = 5 state = 4 time = 2	using a random input
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m0.326232[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in weight input gradients
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m0.18766[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in weight state gradients
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m0.0815951[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in bias state gradients
Testing Weight Backprop using RNN with batchsize = 2 input = 5 state = 10 time = 4	using a random input
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m1.26011[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in weight input gradients
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m5.52267[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in weight state gradients
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m0.0789913[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in bias state gradients
Testing Weight Backprop using RNN with batchsize = 64 input = 5 state = 10 time = 5	using a random input
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m39.6674[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in weight input gradients
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m4.04491[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in weight state gradients
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m0.0176793[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in bias state gradients
Testing Weight Backprop using RNN with batchsize = 1 input = 5 state = 10 time = 3	with a fixed input
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m0.450972[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in weight input gradients
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m1.12049[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in weight state gradients
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m0.948947[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in bias state gradients
Testing Weight Backprop using RNN with batchsize = 32 input = 20 state = 10 time = 4	using a random input and a dense layer
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m860.879[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in weight input gradients
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m2.20297[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in weight state gradients
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m0.136913[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in bias state gradients
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][31m1.04527[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in weight input gradients
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m2.44957[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in weight state gradients
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m1.10196[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in bias state gradients