Execution Time0.81s

Test: TMVA-DNN-RNN-Backpropagation (Passed)
Build: v6-18-00-patches-x86_64-mac1015-clang110-opt (macitois17.cern.ch) on 2019-11-14 00:46:16

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][32m2.95445e-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][33m1.2901e-09[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][33m1.02161e-08[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m6.62397e-10[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m1.4305e-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][32m8.54694e-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][32m1.0037e-10[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][32m4.84024e-10[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m9.54019e-11[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m1.0945e-10[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][33m3.33305e-08[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m9.45518e-09[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m5.2769e-10[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 1 input = 5 state = 4 time = 3	with a fixed input
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m1.73938e-09[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m4.77557e-09[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m3.81105e-08[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][33m5.94025e-08[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m1.6374e-08[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m9.66927e-10[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][33m7.64236e-08[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m2.38101e-08[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m6.72321e-10[NON-XML-CHAR-0x1B][39m