Execution Time0.91s

Test: TMVA-DNN-RNN-Backpropagation-Cpu (Passed)
Build: PR-4885-x86_64-fedora30-gcc9-opt (root-fedora30-1.cern.ch) on 2020-01-29 09:47:30

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][33m3.99223e-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][32m1.77534e-11[NON-XML-CHAR-0x1B][39m
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][32m7.19855e-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][32m4.66079e-11[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][33m1.58278e-08[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m3.42183e-08[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][32m5.79759e-10[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 2 input = 5 state = 10 time = 4	usingError in <AddBasicRNNLayer>: Inconsistent time steps with input layout - it should be 1 instead of 1
Error in <AddBasicRNNLayer>: Inconsistent time steps with input layout - it should be 2 instead of 2
Error in <AddBasicRNNLayer>: Inconsistent time steps with input layout - it should be 4 instead of 4
 a random input
Testing weight input gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m2.78356e-07[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m1.95343e-07[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m2.61189e-08[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][33m1.12772e-06[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m1.23528e-06[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m6.33469e-08[NON-XML-CHAR-0x1B][39m
Testing Weight Backprop using RNN with batchsize = 1 input = 5 state = 10 time = 3	with a fixed input
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][33m1.28386e-07[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m6.39032e-08[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m4.41461e-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][33m9.48144e-07[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m2.76886e-07[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m3.27142e-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 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][33m1.64485e-07[NON-XML-CHAR-0x1B][39m
Testing weight state gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m8.86293e-08[NON-XML-CHAR-0x1B][39m
Testing bias gradients:      maximum error (relative): [NON-XML-CHAR-0x1B][33m1.43465e-08[NON-XML-CHAR-0x1B][39m