Execution Time0.32s

Test: TMVA-DNN-RNN-Backpropagation-Cpu (Passed)
Build: master-x86_64-fedora28-gcc8 (sft-fedora-28-1.cern.ch) on 2019-11-15 01:10:47

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][31m0.0160617[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][31m0.0280169[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 = 2 state = 3 time = 1	using a random input
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m0.194259[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][31m0.0143932[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 = 3 input = 5 state = 4 time = 2	using a random input
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m0.231247[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][31m4.60162[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][31m6.76952[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][31m7.49398[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][31m1.02923[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][31m0.0748593[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][31m0.783099[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][31m1.08968[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m0.0290852[NON-XML-CHAR-0x1B][39m
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][31m0.628494[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m4.0705[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][31m0.0908398[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 32 input = 20 state = 10 time = 4	using a random input and a dense layer
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in weight state gradients
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in bias state gradients
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in weight input gradients
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in weight state gradients
[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][31m98.2807[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][31m1.99016[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][31m0.488906[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][31m12.4321[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][31m5.67031[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][31m13.7994[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in bias state gradients