Repository for dip
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
tenant-catalog/kubeflow/apps/katib/upstream/components/controller/trial-templates.yaml

77 lines
2.5 KiB

---
apiVersion: v1
kind: ConfigMap
metadata:
name: trial-templates
namespace: kubeflow
labels:
katib.kubeflow.org/component: trial-templates
data:
defaultTrialTemplate.yaml: |-
apiVersion: batch/v1
kind: Job
spec:
template:
spec:
containers:
- name: training-container
image: ghcr.io/kubeflow/katib/pytorch-mnist-cpu:v0.18.0
command:
- "python3"
- "/opt/pytorch-mnist/mnist.py"
- "--epochs=1"
- "--batch-size=16"
- "--lr=${trialParameters.learningRate}"
- "--momentum=${trialParameters.momentum}"
restartPolicy: Never
# For ConfigMap templates double quotes must set in commands to correct parse JSON parameters in Trial Template (e.g nn_config, architecture)
enasCPUTemplate: |-
apiVersion: batch/v1
kind: Job
spec:
template:
spec:
containers:
- name: training-container
image: ghcr.io/kubeflow/katib/enas-cnn-cifar10-cpu:v0.18.0
command:
- python3
- -u
- RunTrial.py
- --num_epochs=1
- "--architecture=\"${trialParameters.neuralNetworkArchitecture}\""
- "--nn_config=\"${trialParameters.neuralNetworkConfig}\""
restartPolicy: Never
pytorchJobTemplate: |-
apiVersion: kubeflow.org/v1
kind: PyTorchJob
spec:
pytorchReplicaSpecs:
Master:
replicas: 1
restartPolicy: OnFailure
template:
spec:
containers:
- name: pytorch
image: ghcr.io/kubeflow/katib/pytorch-mnist-cpu:v0.18.0
command:
- "python3"
- "/opt/pytorch-mnist/mnist.py"
- "--epochs=1"
- "--lr=${trialParameters.learningRate}"
- "--momentum=${trialParameters.momentum}"
Worker:
replicas: 2
restartPolicy: OnFailure
template:
spec:
containers:
- name: pytorch
image: ghcr.io/kubeflow/katib/pytorch-mnist-cpu:v0.18.0
command:
- "python3"
- "/opt/pytorch-mnist/mnist.py"
- "--epochs=1"
- "--lr=${trialParameters.learningRate}"
- "--momentum=${trialParameters.momentum}"