Build an AWS Machine Learning Pipeline for Object Detection

سرفصل های دوره

Use AWS Step Functions + Sagemaker to Build a Scalable Production Ready Machine Learning Pipeline for Plastic Detection

1. What we are Building

1. Lets look at our End Project

2. Getting Started with AWS and Getting our Dataset

1. Source Code for the Course.html

2. Setting up IAM User

3. Clarification about AWS S3

4. Getting Data for our Project

5. Getting dataset Part 1

6. Getting dataset Part 2

7. Getting dataset Part 3

8. Getting dataset Part 4

3. Setting up AWS SageMaker

1. Create SageMaker Domain

2. Create SageMaker Studio Notebook

3. Learning how to Stop and Start SageMaker Notebooks

4. Restarting our SageMaker Studio Notebook Kernel

5. Upload and Extract Data in SageMaker

6. Deleting Unused Files

4. Exploratory Data Analysis

1. Loading and Understanding our Data

2. Counting total Images and getting Image ids

3. Getting Classname Identifier

4. Looking at Random Samples from our Dataframe

5. Understanding Annotations

6. Visualize Random Images Part 1

7. Visualise Random Images Part 2

8. Matplotlib difference between plt.show() and plt.imshow().html

9. Visualising Multiples Images at Once

10. Correcting our Function.html

11. Visualising Bounding Boxes Part 1

12. Visualising Bounding Boxes Part 2 (Theory Lesson)

13. Visualising Random Images with Bounding Boxes Part 1

14. Wrong Print Statement.html

15. Visualising Random Images with Bounding Boxes Part 2

16. Read this Lesson if you have issues with Data Visualization.html

5. Cleaning and Splitting our Data

1. Clean our Train and Validation Dataframes

2. Split Dataframe into Test and Train

3. Get Images IDs

4. Splitting IDs Theory Lesson

5. Explanation Regarding Next video.html

6. Moving Images to Appropriate Folders

7. Count how many Train and Test Images we have

8. Verifying that our Images have been moved Properly Part 1

9. Verifying that our Images have been moved Properly Part 2

6. Date Engineering

1. Using Mxnet

2.1 RecordIO Reading.html

2. Additional Info regarding RecordIO format.html

3. Using Mxnet RecordIO

4. Correction Regarding Label width.html

5. Preparing Dataframes to RecordIO format Part 1

6.1 37 Getting df into correct format part2.mov

6. Preparing Dataframes to RecordIO format Part 2

7. Moving Images To Correct Directory

8. Explanation Regarding the Previous Video.html

9. Verifying that all Images have been Moved Properly

10. Read Before Proceeding to the next Lecture.html

11. Creating Production .lst files (Optional)

7. Data Augmentation

1. Data Augmentation Theory

2. Augmenting a Random Image

3. Moving Images to new Folder structure

4. Visualising Random Augmented Images Part 1

5. Visualising Random Augmented Images Part 2

6. Read this Lesson if you have issues visualising your images.html

7. Creating Data Augmentation Function Part 1

8. Creating Data Augmentation Function Part 2

9. Checking Image Counts Before running the Function

10. Correctional Video regarding our Function

11. Augmenting Test Dataset and Creating test .lst Files

12. Augmenting Train Dataset and Creating .lst File Part 1

13. Augmenting Train Dataset and Creating .lst File Part 2

14. Verifying that Data Augmentation has Worked

8. Setting up and Creating our Training Job

1. Increasing Service Quotas

2. Installing dependencies and Packages

3. Creating our RecordIO Files

4. Uploading our RecordIO data to our S3 bucket

5. Downloading Object Detection Algorithm from AWS ECR

6. Setting up our Estimator Object

7. Setting up Hyperparameters

8. Additional Information for Hyperparameter Tuning in AWS.html

9. Setting up Hyperparameter Ranges

10. Setting up Hyperparameter Tuner

11. Additional Information about mAP( mean average precision).html

12. Starting the Training Job Part 1

13. Starting the Training Job Part 2

14. More on mAP Scores.html

15. Monitoring the Training Job

16. Looking at our Finished Hyperparameter Tuning Job

9. Analysing Training Job Results

1. Deploying our Model in a Notebook

2. Creating Visualization Function for Inferences

3. Testing our Endpoint Part 1

4. Testing out Endpoint Part 2

5. Testing our Endpoint from Random Images from the Internet

10. Setting up Batch Transformation

1. Setting up Batch Transformation Job locally first

2. Starting our Batch Transformation Job

3. Analysing our Batch Transformation Job

4. Visualising Batch Transformation Results

5. Look at this lesson if you have trouble with the Visualisations.html

11. Setting Up Our Machine Learning Pipeline

1. Read this Before Watching the Next Lesson.html

2. Setting up AWS Step Function

3. Verify that CloudFormation has worked

4. Configure Batch Transform Lambda Part 1

5. Configure Batch Transform Lambda Part 2

6. Create Check Batch Transform Job Lambda

7. Fixing typos and Syntax Erros

8. JSON output Format

9. Creating Cleaning Batch output Lambda Function Part 1

10. Creating Cleaning Batch output Lambda Function Part 2

11. Configuring our Step Function Part 1

12. Configuring our Step Function Part 2

13. Configuring our Step Function Part 3

14. Upload Test Data to S3

15. Testing our Step Function

16. Fixing Errors

17. Testing our Step Function with the Corrections

18. Verifying that our Step Function Ran Successfully

19. Donwloading our JSON file from S3

20. Using Event Bridge to set up Cron Job for our Machine Learning Pipeline

21. Verify that the Cron Job works

22. Verifying that our Pipeline Ran Successfully

23. Setting up Production Notebook

24. Extending Our Machine Learning Pipeline

25. Coding our Process Job Notebook Part 1

26. Coding our Process Job Notebook Part 2

27. Coding our Process Job Notebook Part 3

28. Coding our Process Job Notebook Part 4

29. Verifying that the Images have been Saved Properly.html

30. Productionizing our Notebook Part 1

31.1 Link to the Trust Policy.html

31. Productionizing our Notebook Part 2

32. Verify that the Entire Machine Learning Pipeline works

33. Deleted Unused items from Sagemaker EFS

12. Creating our Web Application

1. Clone the Web Application from Github

2. Setup MongoDB

3. Connect to MongoDB and get AWS Credentials

4. Configuring Env file

5. Install Node modules

6.1 Article About Next.js proxy server.html

6. MERN app Walkthrough Part 1

7. MERN app Walkthrough Part 2

8. MERN app Walkthrough Part 3

9. Output Images Explanation.html

10. MERN app Walkthrough Part 4

11. MERN app Walkthrough Part 5

13. Outro

1. Clean Up Resources

2. Congratulations

45,900 تومان

خرید اشتراک افزودن به سبد خرید

خرید دانلودی فوری

در این روش نیاز به افزودن محصول به سبد خرید و تکمیل اطلاعات نیست و شما پس از وارد کردن ایمیل خود و طی کردن مراحل پرداخت لینک های دریافت محصولات را در ایمیل خود دریافت خواهید کرد.

تولید کننده: Udemy-Training