No OpKernel was registered to support Op 'EffectiveTransformerInput' used by node EffectiveTransformerInput

[wwy510553871]

I build the effective_transformer successfully, but when I run the benchmark.py, get the error, how can I fix the error

Traceback (most recent call last):
File "/home/luban/miniconda3/envs/study/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1365, in _do_call
return fn(*args)
File "/home/luban/miniconda3/envs/study/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1348, in _run_fn
self._extend_graph()
File "/home/luban/miniconda3/envs/study/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1388, in _extend_graph
tf_session.ExtendSession(self._session)
tensorflow.python.framework.errors_impl.InvalidArgumentError: No OpKernel was registered to support Op 'EffectiveTransformerInput' used by {{node EffectiveTransformerInput}}with these attrs: [batch_size=1, to_seq_len=128, T=DT_FLOAT, head_num=12, from_seq_len=128, size_per_head=64]
Registered devices: [CPU, XLA_CPU, XLA_GPU]
Registered kernels:
device='GPU'; T in [DT_HALF]
device='GPU'; T in [DT_FLOAT]

 [[EffectiveTransformerInput]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "benchmark.py", line 142, in
main(args)
File "benchmark.py", line 105, in main
val1 = sess.run(std_bert).reshape(-1, 768)
File "/home/luban/miniconda3/envs/study/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 956, in run
run_metadata_ptr)
File "/home/luban/miniconda3/envs/study/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1180, in _run
feed_dict_tensor, options, run_metadata)
File "/home/luban/miniconda3/envs/study/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1359, in _do_run
run_metadata)
File "/home/luban/miniconda3/envs/study/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1384, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: No OpKernel was registered to support Op 'EffectiveTransformerInput' used by node EffectiveTransformerInput (defined at /home/luban/miniconda3/envs/study/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py:1748) with these attrs: [batch_size=1, to_seq_len=128, T=DT_FLOAT, head_num=12, from_seq_len=128, size_per_head=64]
Registered devices: [CPU, XLA_CPU, XLA_GPU]
Registered kernels:
device='GPU'; T in [DT_HALF]
device='GPU'; T in [DT_FLOAT]

 [[EffectiveTransformerInput]]

[Meteorix]

please check your tf gpu environment

[VertexC]

hi @wwy510553871, I got similar error here, did you manage to resolve this issue?