Skip to content

MOSIBIT/MOSIBIT-CLOUD-COMPUTING

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 

Repository files navigation

MOSIBIT-CLOUD-COMPUTING

Cloud Computing developmet for Mobile SIBI Translator Mobile App.

Deployment

Requirements:

  • Tensorflow 2.2.0
  • Numpy 1.20.3
  • Pandas 1.2.4
  • Flask 2.0.1

Cloud Computing path responsible for deploying the ML model. All the code and model are provided by Machine Learning Path.

Screenshot 2021-06-06 120655

We use 1 Virtual Machine to deployment, here are the spesification:

  • Name : test-deploy-sibi-translator
  • Machine type : n1-standard-1 (1 vCPU 3,75 GB RAM)
  • Image : Debian-10-buster-v20210512 (10 GB)
  • Network : default
  • Firewall rules : allw port 80 and 22

Our server is vulnerable because we only have 1 VM to serve the API. We planned to design a load balancer with 3 n1-standard-1 instances.

ML API

Plan_A_Prediction_Implementation

We use Flask as micro web framework. Flask written in Python. We use it because simple, extensible, and flexible. The API can be accessed through http://34.101.121.113:80/ . To perform prediction go to '/predict' route.

Mobile App will send json file consist of hand coordinate to API. The server will do the machine learning to predict the alphabet. The API will return hand coordinate and aplphabet prediction in json file.

Billing Report

final billing

Through this capstone project we used $20.84 GCP Billing. Most of it go to Compute Engine, and omly $0.01 go to Cloud Storage to store the dataset.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages