Skip to content

The major focus of the project is to provide an optimal cloud service to classify images using a deployed deep learning image classification model. Used AWS EC2 instances to deploy a deep learning CNN model, AWS SQS to store requests, responses and terminate messages and AWS S3 to store image URL and its model prediction for future references. D…

Notifications You must be signed in to change notification settings

sourabhparvatikar/classifyCloud

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

classifyCloud

Setup:

  1. Set AWS access id and secret key environment variables on local machine.

  2. Create deep learning EC2 instance with ubuntu operating system and set .aws/credentials and .aws/config files. Below is the config file.

  3. Create a directory named proj1-worker in home directory.

  4. Copy classify_image.py, worker.sh, worker.py to the directory created from the above step.

  5. Copy the worker.service file to /etc/systemd/system directory and restart the systemd service.

  6. Register the AMI for the above instance and replace ami-id in the application.properties file with the created ami id.

  7. Create 3 Standard queues named as request, response and terminate queue.

  8. Create a S3 bucket named ccimagerecognition. Note: All the above AWS services should be created in us-west-1 region. Steps to run:

  9. Start the Apache tomcat server using the below command. mvn spring-boot:run

  10. Open browser.

  11. Make sure that tomcat server is running by entering the following url. http://localhost:50003

  12. Provide a image url by making GET request to the server as shown below. http://localhost:50003​/cloudimagerecognition.php?input=

  13. You should be able to see a key value pair as the output where key is image name and the value is the class of the image. It should take about a minute for the result to show up.

About

The major focus of the project is to provide an optimal cloud service to classify images using a deployed deep learning image classification model. Used AWS EC2 instances to deploy a deep learning CNN model, AWS SQS to store requests, responses and terminate messages and AWS S3 to store image URL and its model prediction for future references. D…

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published