-
Launch an instance with the Deep Learning Base GPU AMI. Note that this AMI currently only supports P5, P4de, P4d, P3, G5, G3, and G4dn instances.
-
Log into the instance and configure GPUs to run inside Docker containers
sudo nvidia-ctk runtime configure --runtime=docker sudo systemctl restart docker
-
Pull the image:
docker pull martinkim0/scvi-tools:py3.11-cu11-autotune-main
-
Mount the AWS drive to a directory
sudo mkdir /data sudo mount /dev/mapper/name-of-drive /data
-
Clone this repository
git clone https://github.com/YosefLab/census-scvi.git
-
Run the container in detached mode with a mounted volume
docker run --name autotune --rm --gpus all --volume /data:/data -dit martinkim0/scvi-tools:py3.11-cu11-autotune-main /bin/bash
-
Copy the repository into the container
docker cp census-scvi autotune:census-scvi
-
Execute the autotune script in the container
docker exec -d autotune python /census-scvi/bin/autotune_scvi_v2.py --adata_path path_to_adata --batch_key batch_key --num_cpus num_cpus --num_gpus num_gpus --experiment_name experiment_name --save_dir /data
-
After the experiment finishes, you can stop the container
docker stop autotune
-
All logs are stored in the
save_dir
argument passed into (6)
-
Notifications
You must be signed in to change notification settings - Fork 0
YosefLab/census-scvi
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published