GraphSAGE_dist.yaml

apiVersion: qihoo.net/v1alpha1
kind: DGLJob
metadata:
  name: dgl-graphsage
  namespace: dgl-operator
spec:
  partitionMode: DGL-API
  cleanPodPolicy: Running
  dglReplicaSpecs:
    Launcher:
      replicas: 1
      template:
        spec:
          containers:
          - image: dgloperator/examples:graphsage-dist
            name: dgl-graphsage
            imagePullPolicy: Always
            command:
            - dglrun
            args:
            - --graph-name
            - graphsage
            # partition
            - --partition-entry-point
            - code/load_and_partition_graph.py
            - --num-partitions
            - "2"
            - --balance-train
            - --balance-edges
            - --dataset-url
            - http://snap.stanford.edu/ogb/data/nodeproppred/products.zip
            # training
            - --train-entry-point
            - code/train_dist.py
            - --num-epochs
            - "1"
            - --batch-size
            - "1000"
            - --num-trainers
            - "1"
            - --num-samplers
            - "4"
            - --num-servers
            - "1"
    Worker:
      replicas: 2
      template:
        spec:
          containers:
          - image: dgloperator/examples:graphsage-dist
            name: dgl-graphsage
            imagePullPolicy: Always
            resources:
              requests:
                memory: "20Gi"
                cpu: "10"
              limits:
                memory: "20Gi"
                cpu: "10"