apiVersion: batch/v1 kind: Job metadata: name: ts-spatop-eval-v8-full labels: jobgroup: spatop-job-train spec: template: spec: securityContext: runAsUser: 0 fsGroup: 0 containers: - name: training image: gitlab-registry.nrp-nautilus.io/mquinnan/top-spanet:spatop-container command: - "/bin/bash" - "-c" - | set -e # exit on error echo "Installing SPANet v2.3, tensorboard and rich..." pip install git+https://github.com/billy000400/SPANet@maad_dev pip install tensorboard rich echo "Starting prediction job..." python -m spanet.predict \ /data/spatop/logs/spatop_v8_full_output/version_8/ \ /data/spatop/tpm70_wpm30_FB350_eval/tt_hadronic_v8full.h5 \ -tf /data/spatop/tpm70_wpm30_FB350_testing/all_merged.h5 volumeMounts: - name: dshm mountPath: /dev/shm - mountPath: /data name: spatopvol - name: git-repo mountPath: /opt/repo resources: limits: memory: 64Gi cpu: "16" nvidia.com/gpu: "1" requests: memory: 32Gi cpu: "8" nvidia.com/gpu: "1" initContainers: - name: init-clone-repo image: alpine/git args: - clone - --single-branch - https://github.com/quinnanm/SPAtop - -b - meldev - --recurse-submodules - /opt/repo/SPAtop volumeMounts: - name: git-repo mountPath: /opt/repo volumes: - name: dshm emptyDir: medium: Memory sizeLimit: 8Gi - name: git-repo emptyDir: {} - name: spatopvol persistentVolumeClaim: claimName: traindatavol restartPolicy: Never backoffLimit: 5