while wavenet training, 0 derived errors ignored.
opened this issue · comments
Hi guys.
I'm trying to train wavenet model, but got following error.
Generated 64 train batches of size 8 in 0.393 sec
Exiting due to exception: 2 root error(s) found.
(0) Invalid argument: assertion failed: [] [Condition x == y did not hold element-wise:] [x (WaveNet_model/inference/strided_slice_5:0) = ] [15125] [y (WaveNet_model/inference/strided_slice_6:0) = ] [11000]
[[node WaveNet_model/inference/assert_equal/Assert/Assert (defined at /Tacotron-2/wavenet_vocoder/models/wavenet.py:699) ]]
[[WaveNet_model/clip_by_value_147/_2571]]
(1) Invalid argument: assertion failed: [] [Condition x == y did not hold element-wise:] [x (WaveNet_model/inference/strided_slice_5:0) = ] [15125] [y (WaveNet_model/inference/strided_slice_6:0) = ] [11000]
[[node WaveNet_model/inference/assert_equal/Assert/Assert (defined at /Tacotron-2/wavenet_vocoder/models/wavenet.py:699) ]]
0 successful operations.
0 derived errors ignored.
Machine spec:
Ubuntu 18.04
GPU: Tesla T4
Python 3.6.9
Cuda 10.0, Cudnn 7.6.5
Tensorflow=gpu 1.14
Thanksful any help for this.