E tensorflow/stream_executor/cuda/cuda_dnn.cc:359] Loaded runtime CuDNN library: 8.0.4 but source was compiled with: 8.1.0. CuDNN library needs to have matching major version and equal or higher minor version. If using a binary install, upgrade your CuD

[wxm]

Hi Simon,

Thank your for this great tool. when I run the software, I am having the following error:

[8/1.2] Run blast classifier Model_blast_Conv-87 (by batch)..
Predicting confidence score for all batches of input data [ ] 0%2023-03-09 19:50:03.787123: E tensorflow/stream_executor/cuda/cuda_dnn.cc:359] Loaded runtime CuDNN library: 8.0.4 but source was compiled with: 8.1.0. CuDNN library needs to have matching major version and equal or higher minor version. If using a binary install, upgrade your CuDNN library. If building from sources, make sure the library loaded at runtime is compatible with the version specified during compile configuration.
2023-03-09 19:50:03.794221: W tensorflow/core/framework/op_kernel.cc:1745] OP_REQUIRES failed at conv_ops_fused_impl.h:560 : UNKNOWN: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.

I would be grateful, If you could help with solving this issue.

Thanks

XiaoMeng

[Simon Roux]

Hi,

Looks like a tensforflow install problem (based on other comparable issues e.g. https://github.com/tensorflow/text/issues/554). Did you install iPHoP through Conda ? And if so, maybe trying the docker container may help ?

[wxm]

There are many bugs in this software, which is not friendly for a novice. I have tried many methods, but it has not been solved. Thank you very much for your reply.@Simon Roux