SUMMER1234
SUMMER1234
I try to change ALBERT optimizer to RAdam, but got this error after 1000steps. I tried lower batch size but still not work Traceback (most recent call last): File "/usr/lib/python3.5/runpy.py",...
*** forward translation *** run.sh: line 64: t2t-decoder: command not found *** backward translation *** run.sh: line 77: t2t-decoder: command not found
/Users/summer-sun/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py:110: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory. "Converting sparse IndexedSlices to a dense Tensor of unknown shape....
what cuda version should use? I always get this error for rnn RuntimeError: CuDNN error: CUDNN_STATUS_SUCCESS after upgrade cuda error solved but code not worked