Autoplay
Autocomplete
Previous Lesson
Complete and Continue
Deploying Machine Learning Models with Vapor and Core ML
Welcome
Introduction (2:06)
Prerequisites (1:34)
Getting Started
Understanding Different Packages (2:32)
Machine Learning Flow (3:10)
Downloading Car Prices Dataset from Kaggle (7:27)
Downloading Miniconda (2:59)
Setting Up the Environment (12:59)
Cleaning and Preprocessing Data
Loading Carvana CSV Using Pandas (11:00)
Fixing the Year Column (4:31)
Standardization of the Miles Column (10:48)
Encoding the Name Column (7:16)
Regression Algorithms and Encodings
Understanding Regression and Common Algorithms (6:19)
Linear Regression (5:33)
RandomForest (4:07)
One-Hot Encoding (6:48)
Label Encoding (2:52)
Training and Exporting the Models
Training the Model Using RandomForestRegressor (18:03)
Converting Model to ML Model Using coremltools (9:16)
Create Car Names JSON File (13:09)
Integrating Core ML Model into an iOS App
Creating the User Interface (11:48)
Integrating Core ML Model (10:54)
Standardization and Predicting Prices (8:38)
Hosting Core ML Model Using Vapor
Running your first Vapor Project (10:43)
Integrating Core ML Model Part 1 (10:22)
Integrating Core ML Model Part 2 (4:38)
Predicting Prices (23:05)
Integrating Model with iOS App (10:50)
Deploying Vapor Server Locally and Exposing JSON API Publicly Using ngrok (6:50)
Conclusion
Next Steps
Resource: Deployment Using MacStadium
Resource: Deployment Using ngrok
Bonus
Teach online with
Deploying Vapor Server Locally and Exposing JSON API Publicly Using ngrok
Lesson content locked
If you're already enrolled,
you'll need to login
.
Enroll in Course to Unlock