Open cchauve opened 1 year ago
Hello Cedric @cchauve :
Apologies for the delay. I got absorbed into my teaching duties at SJSU and I just saw a few messages I've missed.
I have not tested it with Singularity, only with Docker. I am guessing there is a conflict as read_fasta2_plasmids.py is old and I need to re-engineer it from Py2 to Py3 (haven't found the time yet, but one of these days will get to it). I believe your issue will be solved if you change the shebang line in read_fasta2_plasmids.py to #!/usr/bin/python2.7 , such that it doesn't conflict with the rest of the code that is py3.
I just released a new Docker image for GPUs, that is built on tensorflow/tensorflow:latest-gpu. I left the CNTK stuff behind and moved to TensorFlow.
As described in the README, the usage is much simpler. For example: docker pull billandreo/deeplasmid.tf.gpu2 sudo /usr/bin/docker run -it -v /path/to/fasta:/srv/jgi-ml/classifier/dl/in.fasta -v /path/to/OUT/dir:/srv/jgi-ml/classifier/dl/outdir billandreo/deeplasmid.tf.gpu2 deeplasmid.sh in.fasta outdir
You may want to try that out. Thanks
Hello
I tried to run deeplasmid using the GPU version. I built a singularity contained from the docker container
billandreo/deeplasmid-gpu
. When I ran it, I got the outputcedric chauve