ML+DEVOPS=MLOPS

AUTOMATION OF MACHINE LEARNING WITH DEVOPS

 In industry generally machine learning guys and developer + operational guys termed as devops guys ,don’t about each other . I mean to say there is a silos between them and this leads many problem and needs many manual efforts.

But what if we combine both the minds of ml + devops guys?

It will lead to automate everything ,there will not be any manual effort as soon as the ml code entered on github and then everything will be automate. So that there will not be any time delay and will be faster and accurate.

So here I have tried to do one task given by vimal sir to automate ml with devops with the help of Jenkins ,docker and git, github .

TASK DESCRIPTION

1. Create container image that’s has Python3 and Keras or numpy installed using dockerfile

2. When we launch this image, it should automatically starts train the model in the container.

3. Create a job chain of job1, job2, job3, job4 and job5 using build pipeline plugin in Jenkins

4. Job1 : Pull the Github repo automatically when some developers push repo to Github.

5. Job2 : By looking at the code or program file, Jenkins should automatically start the respective machine learning software installed interpreter install image container to deploy code and start training( eg. If code uses CNN, then Jenkins should start the container that has already installed all the softwares required for the cnn processing).

6. Job3 : Train your model and predict accuracy or metrics.

7. Job4 : if metrics accuracy is less than 80% , then tweak the machine learning model architecture.

8. Job5: Retrain the model or notify that the best model is being created

9. Create One extra job job6 for monitor : If container where app is running. fails due to any reason then this job should automatically start the container again from where the last trained model left.

AS ml guy we push the code to github 

->code were pushed on github

->creating dockerfile for docker image

*starting the docker and building the docker image with name cnn and version v1

->job 1

-> job 2

->job 3

-> job 4

->job 5

->job 6

->build pipeline showing all jobs connected with eachother

thank you vimal sir for such a great knowledge .