.gitlab-ci.yml

stages:
    - test
    - deploy
# Test in a CPU, only 1 epoch
test:
    stage: test
    image: tensorflow/tensorflow:1.10.0-py3
    script:
        - python code-to-run.py 1
# Deploy in a GPU and run all epochs
deploy:
    image: google/cloud-sdk
    stage: deploy
    script:
        # Install kubectl from https://gitlab.com/gitlab-examples/kubernetes-deploy
        - curl -L -o /usr/bin/kubectl https://storage.googleapis.com/kubernetes-release/release/$(curl -s https://storage.googleapis.com/kubernetes-release/release/latest.txt)/bin/linux/amd64/kubectl && chmod +x /usr/bin/kubectl
        - kubectl version --client
        - echo "${KUBE_CA_PEM}" > kube_ca.pem
        - kubectl config set-cluster default-cluster --server=${KUBE_URL} --certificate-authority="$(pwd)/kube_ca.pem"
        - kubectl config set-credentials default-admin --token=${KUBE_TOKEN}
        - kubectl config set-context default-system --cluster=default-cluster --user=default-admin --namespace=${CI_PROJECT_NAME}
        - kubectl config use-context default-system        
        - kubectl cluster-info || true
        # Secrets
        - kubectl delete secret regsecret --namespace=${CI_PROJECT_NAME} || true
        - kubectl create secret docker-registry regsecret --docker-server="nvcr.io" --docker-username='$oauthtoken' --docker-password=${DOCKER_REGISTRY_PASSWORD} --docker-email="email@email.com" --namespace=${CI_PROJECT_NAME} || true
        # Code as configmap
        - kubectl delete configmap code-to-run --namespace=${CI_PROJECT_NAME} || true
        - kubectl create configmap code-to-run --from-file=code-to-run.py --namespace=${CI_PROJECT_NAME}
        # Run the code as a job
        - kubectl delete -f gke-gpu-gitlab-job.yaml --namespace=${CI_PROJECT_NAME} || true
        - kubectl create -f gke-gpu-gitlab-job.yaml --namespace=${CI_PROJECT_NAME}
        # Wait until the code is finished
        - until kubectl get jobs my-gpu-job --namespace=${CI_PROJECT_NAME} -o jsonpath='{.status.conditions[?(@.type=="Complete")].status}' | grep True ; do sleep 5 ; echo "job in progress"; done;
        # Get results
        - kubectl logs $(kubectl get pods --selector=job-name=my-gpu-job --output=jsonpath={.items..metadata.name} --namespace=${CI_PROJECT_NAME}) --namespace=${CI_PROJECT_NAME}