Execution Time0.84s

Test: TMVA-DNN-RNN-Backpropagation-Cpu (Passed)
Build: PR-4279-x86_64-fedora29-gcc8-opt (root-fedora29-3.cern.ch) on 2019-11-14 21:03:34

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][31m0.0331521[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][31m0.0449807[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][31m0.0461754[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][31m0.013487[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][31m0.410696[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][31m0.149639[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][31m0.20157[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][31m3.70913[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][31m6.40656[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][31m0.023741[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][31m10.7005[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][31m1.41844[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][31m0.0279785[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][31m0.785914[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][31m78.9608[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][31m0.813166[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][31m10.2829[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][31m2.79264[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][31m0.0491775[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][31m276.228[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][31m1.22107[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][31m0.528499[NON-XML-CHAR-0x1B][39m
[NON-XML-CHAR-0x1B][31m Error [NON-XML-CHAR-0x1B][39m in bias state gradients