Skip to end of metadata
Go to start of metadata

Source code

  1. (python version of CDEEP3M)
  2. (Docker container for the python version of CDEEP3M)
  3. (Docker container for PRP workflow for the python version of CDEEP3M)

Build scripts for the above are in the .gitlab-ci.yml file in each repo. The builds are dependent so 3 uses the output from 2 and 2 uses the output from 1. Builds are triggered by any change to the repo. The latest build for the registries is tagged as :latest

CIL Image Viewer

Source code:

Kubenetes yaml file:



Interactive testing on a PRP node

  1. spin up a node

    sudo -u apache kubectl create -f /export2/temp/cdeep3m/cil-cdeep3m_py.yaml --validate=false
  2. wait for running state

    sudo -u apache kubectl get pods
    NAME                             READY     STATUS             RESTARTS   AGE
    gpu-pod-cil-cdeep3m-py-testing   1/1       Running            0          1m
  3. connect to the pod

    sudo -u apache kubectl exec -it gpu-pod-cil-cdeep3m-py-testing bash
  4. test

    ./CDEEP3M_prp --augspeed 1 --models 1fm --overlay --enhance --pod_id=A 3515 10.7295/W9CDEEP3M3

    to rerun previously run jobs in ~/CDEEP3M_prp change line 130

     }else {
        print  LOG getLoggingTime()."\t(".__LINE__.') '."$pod_id is not the first!! $data\n";
        exit 0;


     }else {
        print  LOG getLoggingTime()."\t(".__LINE__.') '."$pod_id is not the first!! $data\n";
        leave (0);

    and uncomment line 513

    sub leave{
      my $code =shift;
      if ($code){
        post_url ("$image_api_uri/Image_process_rest/update_cdeep3m_error/stage/$crop_id",'error => true',$image_api_user,$image_api_pass);

    then run the testing command, the first time through will reset the status and the second time it will run the prediction. 

  5. When finished exit the pod with "exit" or CTRL d then delete the running pod

    sudo -u apache kubectl delete  -f /export2/temp/cdeep3m/cil-cdeep3m_py.yaml

API & urls of interest

  • No labels