Hi I am fairly new at this all. And I’m not going to be a heavy user for this. I’m just trying to train a model to use it later. I will probably only have to do this once.
So here goes.
This is the project https://github.com/ml5js/training-styletransfer
I’m following the docker steps on the AWS machine with P2xlarge (which should be enough to run the training)
step without explanation:
curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | \
sudo apt-key add -
distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | \
sudo tee /etc/apt/sources.list.d/nvidia-docker.list
sudo apt-get update
This wasn’t necessary becaus everything is pre-installed, but did it anyway and got no issues.
sudo apt-get install -y nvidia-docker2
sudo pkill -SIGHUP dockerd
everything still fine
docker pull cvalenzuelab/styletransfer:latest
everything got pulled in.
sudo nvidia-docker run -e USER=$USER -e USERID=$UID -v $PWD:$PWD -w=$PWD -it -p 8888:8888 -p 6006:6006 -v ~/home/YourUserName/:/home cvalenzuelab/styletransfer bash
This however I don’t really get or didn’t give me a solution ( i just changed an only changed the ~/home/YourUserName/ part)
But the folder doesn’t show up anywhere.
*The latest command line should give you a linux prompt with access to your home folder.
You can now navigate to the folder you cloned this repo and follow the “Usage” instructions from step 3.*
So I can’t continue to step three which asks me to upload an image following:
bash run.sh
Does anybody know what I should do to get this training to work. Or what I’m doing wrong at the moment.
Kindest regards,
