Skip to content

DeepLabCut (≥ 2.3.9)

DeepLabCut is a toolbox for markerless pose estimation of animals performing various tasks.

DeepLabCut is available as a module on Apocrita.


DeepLabCut only works on GPU nodes

DeepLabCut only works on the GPU nodes. Attempting to run DeepLabCut on any other node type will result in a Python error. Before using DeepLabCut, researchers need to request access to the GPU nodes, or have access to the DERI/Andrena GPU nodes.

Pre-trained models

DeepLabCut will automatically download any required pre-trained models to $HOME/.config/deeplabcut/<version>. Whilst these shouldn't take up a lot of space, it might be wise to monitor this directory in case it fills up.

To run the default version of DeepLabCut, simply load the deeplabcut module:

module load deeplabcut

Loading the module will automatically activate an Anaconda environment, containing DeepLabCut and its dependencies, as well as any required CUDA libraries.

Example job

GPU job

DeepLabCut only uses one GPU

DeepLabCut only uses one GPU, so job scripts should only request one GPU. The following job script will use a script from the DeepLabCut examples directory to create a project and run some tasks.

#$ -cwd
#$ -j y
#$ -pe smp 12
#$ -l h_vmem=7.5G
#$ -l h_rt=240:0:0
#$ -l gpu=1
#$ -l gpu_type="ampere"
# Approved DERI users can include the following line
#$ -l cluster=andrena

module load deeplabcut

cd ~/DeepLabCut/examples
deeplabcut python