-
Notifications
You must be signed in to change notification settings - Fork 42
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #117 from dinal/horovoc_cpu
add horovod cpu and change dir location
- Loading branch information
Showing
10 changed files
with
1,246 additions
and
21 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
216 changes: 216 additions & 0 deletions
216
demos/horovod/cpu/image-classification/02-train-with-horovod-cats-n-dogs.ipynb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,216 @@ | ||
| { | ||
| "cells": [ | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 1, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "!pip install git+https://github.com/v3io/v3io-gputils" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 2, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "!rm -f /User/demos/horovod/cpu/image-classification/cats_dogs.hd5\n", | ||
| "!mkdir /User/demos/horovod/cpu/image-classification/checkpoints" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 3, | ||
| "metadata": {}, | ||
| "outputs": [], | ||
| "source": [ | ||
| "HOROVOD_JOB_NAME = \"horovod-cats-n-dogs\"" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 4, | ||
| "metadata": {}, | ||
| "outputs": [ | ||
| { | ||
| "name": "stdout", | ||
| "output_type": "stream", | ||
| "text": [ | ||
| "{'apiVersion': 'kubeflow.org/v1alpha1',\n", | ||
| " 'kind': 'MPIJob',\n", | ||
| " 'metadata': {'creationTimestamp': '2019-07-02T07:41:59Z',\n", | ||
| " 'generation': 1,\n", | ||
| " 'name': 'horovod-cats-n-dogs',\n", | ||
| " 'namespace': 'default-tenant',\n", | ||
| " 'resourceVersion': '1391131',\n", | ||
| " 'selfLink': '/apis/kubeflow.org/v1alpha1/namespaces/default-tenant/mpijobs/horovod-cats-n-dogs',\n", | ||
| " 'uid': 'df9b08a1-9c9c-11e9-98d3-d8c4972b0204'},\n", | ||
| " 'spec': {'replicas': 8,\n", | ||
| " 'template': {'spec': {'containers': [{'command': ['mpirun',\n", | ||
| " 'python',\n", | ||
| " '/User/demos/horovod/cpu/image-classification/horovod_train_cats_n_dogs.py',\n", | ||
| " '/User/demos/horovod/cpu/image-classification/cats_and_dogs_filtered',\n", | ||
| " '/User/demos/horovod/cpu/image-classification'],\n", | ||
| " 'image': 'iguaziodocker/horovod-cpu:0.0.1',\n", | ||
| " 'name': 'horovod-cats-n-dogs',\n", | ||
| " 'resources': {'limits': {'nvidia.com/gpu': 0}},\n", | ||
| " 'securityContext': {'capabilities': {'add': ['IPC_LOCK']}},\n", | ||
| " 'volumeMounts': [{'mountPath': '/User',\n", | ||
| " 'name': 'v3io'}]}],\n", | ||
| " 'volumes': [{'flexVolume': {'driver': 'v3io/fuse',\n", | ||
| " 'options': {'accessKey': '1e52ff93-a541-4880-abf1-d9b948af77de',\n", | ||
| " 'container': 'users',\n", | ||
| " 'subPath': '/iguazio'}},\n", | ||
| " 'name': 'v3io'}]}}}}\n" | ||
| ] | ||
| } | ||
| ], | ||
| "source": [ | ||
| "from v3io_gputils.mpijob import MpiJob\n", | ||
| "\n", | ||
| "job = MpiJob(HOROVOD_JOB_NAME, 'iguaziodocker/horovod-cpu:0.0.1', ['/User/demos/horovod/cpu/image-classification/horovod_train_cats_n_dogs.py',\n", | ||
| " '/User/demos/horovod/cpu/image-classification/cats_and_dogs_filtered',\n", | ||
| " '/User/demos/horovod/cpu/image-classification'])\n", | ||
| "\n", | ||
| "job.replicas(2).gpus(0)\n", | ||
| "job.submit()" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 5, | ||
| "metadata": {}, | ||
| "outputs": [ | ||
| { | ||
| "name": "stdout", | ||
| "output_type": "stream", | ||
| "text": [ | ||
| "horovod-cats-n-dogs-launcher-8kg8c 1/1 Running 0 75s\n", | ||
| "horovod-cats-n-dogs-worker-0 1/1 Running 0 83s\n", | ||
| "horovod-cats-n-dogs-worker-1 1/1 Running 0 83s\n", | ||
| "horovod-cats-n-dogs-worker-2 1/1 Running 0 83s\n", | ||
| "horovod-cats-n-dogs-worker-3 1/1 Running 0 83s\n", | ||
| "horovod-cats-n-dogs-worker-4 1/1 Running 0 83s\n", | ||
| "horovod-cats-n-dogs-worker-5 1/1 Running 0 83s\n", | ||
| "horovod-cats-n-dogs-worker-6 1/1 Running 0 83s\n", | ||
| "horovod-cats-n-dogs-worker-7 1/1 Running 0 83s\n" | ||
| ] | ||
| } | ||
| ], | ||
| "source": [ | ||
| "\n", | ||
| "!kubectl get pods | grep $HOROVOD_JOB_NAME" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 6, | ||
| "metadata": {}, | ||
| "outputs": [ | ||
| { | ||
| "name": "stdout", | ||
| "output_type": "stream", | ||
| "text": [ | ||
| "apiVersion: kubeflow.org/v1alpha1\n", | ||
| "kind: MPIJob\n", | ||
| "metadata:\n", | ||
| " creationTimestamp: 2019-07-02T06:49:07Z\n", | ||
| " generation: 1\n", | ||
| " name: horovod-cats-n-dogs\n", | ||
| " namespace: default-tenant\n", | ||
| " resourceVersion: \"1386982\"\n", | ||
| " selfLink: /apis/kubeflow.org/v1alpha1/namespaces/default-tenant/mpijobs/horovod-cats-n-dogs\n", | ||
| " uid: 7d0cd80c-9c95-11e9-98d3-d8c4972b0204\n", | ||
| "spec:\n", | ||
| " backoffLimit: 6\n", | ||
| " replicas: 8\n", | ||
| " template:\n", | ||
| " metadata:\n", | ||
| " creationTimestamp: null\n", | ||
| " spec:\n", | ||
| " containers:\n", | ||
| " - command:\n", | ||
| " - mpirun\n", | ||
| " - python\n", | ||
| " - /User/demos/horovod/cpu/image-classification/horovod_train_cats_n_dogs.py\n", | ||
| " - /User/demos/horovod/cpu/image-classification/cats_and_dogs_filtered\n", | ||
| " - /User/demos/horovod/cpu/image-classification\n", | ||
| " image: iguaziodocker/cpu/horovod-cpu:0.1.1\n", | ||
| " name: horovod-cats-n-dogs\n", | ||
| " resources:\n", | ||
| " limits:\n", | ||
| " nvidia.com/gpu: \"1\"\n", | ||
| " securityContext:\n", | ||
| " capabilities:\n", | ||
| " add:\n", | ||
| " - IPC_LOCK\n", | ||
| " volumeMounts:\n", | ||
| " - mountPath: /User\n", | ||
| " name: v3io\n", | ||
| " volumes:\n", | ||
| " - flexVolume:\n", | ||
| " driver: v3io/fuse\n", | ||
| " options:\n", | ||
| " accessKey: 1e52ff93-a541-4880-abf1-d9b948af77de\n", | ||
| " container: users\n", | ||
| " subPath: /iguazio\n", | ||
| " name: v3io\n", | ||
| "status:\n", | ||
| " completionTime: 2019-07-02T06:56:20Z\n", | ||
| " launcherStatus: Succeeded\n", | ||
| " startTime: 2019-07-02T06:49:14Z\n" | ||
| ] | ||
| } | ||
| ], | ||
| "source": [ | ||
| "!kubectl get mpijob $HOROVOD_JOB_NAME -o yaml" | ||
| ] | ||
| }, | ||
| { | ||
| "cell_type": "code", | ||
| "execution_count": 7, | ||
| "metadata": {}, | ||
| "outputs": [ | ||
| { | ||
| "name": "stdout", | ||
| "output_type": "stream", | ||
| "text": [ | ||
| "{'apiVersion': 'v1',\n", | ||
| " 'details': {'group': 'kubeflow.org',\n", | ||
| " 'kind': 'mpijobs',\n", | ||
| " 'name': 'horovod-cats-n-dogs',\n", | ||
| " 'uid': '1b58dd58-9c97-11e9-98d3-d8c4972b0204'},\n", | ||
| " 'kind': 'Status',\n", | ||
| " 'metadata': {},\n", | ||
| " 'status': 'Success'}\n" | ||
| ] | ||
| } | ||
| ], | ||
| "source": [ | ||
| "job.delete()" | ||
| ] | ||
| } | ||
| ], | ||
| "metadata": { | ||
| "kernelspec": { | ||
| "display_name": "Python 3", | ||
| "language": "python", | ||
| "name": "python3" | ||
| }, | ||
| "language_info": { | ||
| "codemirror_mode": { | ||
| "name": "ipython", | ||
| "version": 3 | ||
| }, | ||
| "file_extension": ".py", | ||
| "mimetype": "text/x-python", | ||
| "name": "python", | ||
| "nbconvert_exporter": "python", | ||
| "pygments_lexer": "ipython3", | ||
| "version": "3.6.8" | ||
| } | ||
| }, | ||
| "nbformat": 4, | ||
| "nbformat_minor": 2 | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.