DLC Project Configuration

Move the Project to the Clutser#

Mount a Remote Server (optional)#

Mount your sshfs volume.

$ sshfs username@crane.unl.edu:/work/chaselab/username /path/to/sshfs

important

Replace username with your username on the cluster.

Move the project folder to the sshfs volume.
Open your project folder inside the sshfs volume.
Open the yaml.config file to change parameters and identify label names. This is a crucial step!

    # Project definitions (do not edit)
Task: myproject
scorer: myname
date: Jun30
multianimalproject: false

    # Project path (change when moving around)
project_path: /work/chaselab/username/myproject-myname-2020-06-30

    # Annotation data set configuration (and individual video cropping parameters)
video_sets:
  /work/chaselab/username/myproject-myname-2020-06-30/videos/wheel.mp4:
    crop: 0, 1280, 0, 720
bodyparts:
- bodypart1
- bodypart2
- bodypart3
- objectA
start: 0
stop: 1
numframes2pick: 20

    # Plotting configuration
skeleton:
- - bodypart1
  - bodypart2
- - objectA
  - bodypart3
skeleton_color: black
pcutoff: 0.6
dotsize: 12
alphavalue: 0.7
colormap: plasma

    # Training,Evaluation and Analysis configuration
TrainingFraction:
- 0.95
iteration: 0
default_net_type: resnet_50
default_augmenter: default
snapshotindex: -1
batch_size: 8

    # Cropping Parameters (for analysis and outlier frame detection)
cropping: false
croppedtraining: false
    #if cropping is true for analysis, then set the values here:
x1: 0
x2: 640
y1: 277
y2: 624

    # Refinement configuration (parameters from annotation dataset configuration also relevant in this stage)
corner2move2:
- 50
- 50
move2corner: true

Replace username with your username and the example project name with your project name under project_path:.
Replace username, project, and video name with your project's information under video_sets:.
Save and close.

important

Make sure that your path in the config file matches the path you will will use on the cluster.