Execution Time1.05s

Test: TMVA-DNN-RNN-Backpropagation-Cpu (Passed)
Build: PR-4847-x86_64-mac1014-clang100-opt (macphsft17.dyndns.cern.ch) on 2020-01-23 17:24:23

Test Timing: Passed
Processors1

Show Command Line
Display graphs:

Test output
Testing RNN backward pass
Testing Weight Backprop using RNN with batchsize = 2 input = 2 state = 1 time = 1	using a random input
Error in <AddBasicRNNLayer>: Inconsistent time steps with input layout - it should be 1 instead of 1
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m1.44202e-09[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][32m1.36098e-11[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 2 input = 2 state = 3 time = 1	using a random input
Error in <AddBasicRNNLayer>: Inconsistent time steps with input layout - it should be 1 instead of 1
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m3.85729e-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][32m1.22265e-10[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 3 input = 5 state = 4 time = 2	using a random input
Error in <AddBasicRNNLayer>: Inconsistent time steps with input layout - it should be 2 instead of 2
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m2.12178e-09[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m1.4499e-09[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m3.65119e-10[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 2 input = 5 state = 10 time = 4	using a random input
Error in <AddBasicRNNLayer>: Inconsistent time steps with input layout - it should be 4 instead of 4
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m1.57629e-07[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m4.41123e-07[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m6.12986e-09[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 64 input = 5 state = 10 time = 5	using a random input
Error in <AddBasicRNNLayer>: Inconsistent time steps with input layout - it should be 5 instead of 5
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m3.16965e-06[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m2.65575e-07[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m1.29672e-07[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 1 input = 5 state = 10 time = 3	with a fixed input and a dense layer and an extra RNN
Error in <AddBasicRNNLayer>: Inconsistent time steps with input layout - it should be 3 instead of 3
Error in <AddBasicRNNLayer>: Inconsistent time steps with input layout - it should be 3 instead of 3
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m4.47949e-09[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m4.17313e-07[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m6.8363e-09[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
Error in <AddBasicRNNLayer>: Inconsistent time steps with input layout - it should be 4 instead of 4
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m3.0522e-07[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m6.50019e-08[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m1.59246e-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
Error in <AddBasicRNNLayer>: Inconsistent time steps with input layout - it should be 4 instead of 4
Error in <AddBasicRNNLayer>: Inconsistent time steps with input layout - it should be 4 instead of 4
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m3.95935e-06[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m9.02742e-08[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m3.52804e-09[NON-XML-CHAR-0x1B][39m