MicrobeLab

Hi, What is the GPU memory of your server? The model which I provided as an example should be run in a GPU with 24G memory.

I did not see this error before. Here are a few things you could try. 1. Monitor the memory used from job submission to error stop using nvidia-smi. Does "tf_config.gpu_options.allow_growth=True"...

It seems that the memory issue is not the key problem. You could try some other simple tensorflow scripts using the same environment to check if the work can be...

Hi, It was "parallel" that did not work properly. Could you please check whether parallel has been properly installed? If not, try install parallel by yourself (instead of using the...

Hi, Did you specify the path to the vocabulary file?

The server I am working on does not have a docker installed, so that currently I do not have a plan to make a docker image. Sorry about that.

Hi, here is the output from conda list: Name Version Build Channel _libgcc_mutex 0.1 main conda-forge _tflow_select 2.1.0 gpu defaults absl-py 0.3.0 py_0 conda-forge astor 0.7.1 py_0 conda-forge biopython 1.70...

Hi Ramtin, Sorry for the late reply. I did not notice these differences between CPU and GPU before. Thank you very much for this information.

The parallel is included in bin. You could add it to path. Alternatively, you could install it using the command: (wget -O - pi.dk/3 || curl pi.dk/3/) | bash

The version is 1.9.0