Data Science & Machine Learning Project – Part 5 Training a Model | Image Classification

Once we have X and y after applying feature engineering techniques, we can now create simple SVM model to get a feel of how it is going to perform on image classification. We will then use GridSearchCV and try different models with different hyper parameters to come up with a best model that can give us maximum accuracy. We will use sklearn classification_report to check the performance. Once we select best model based on GridSearchCV we can evaluate it on X_test and y_test to get a feel of how it is going to perform in production. Confusion matrix is used with seaborn visualization to get an understanding of classification errors for each of the classes. In the end we export the model to a file using joblib.

Code: https://github.com/codebasics/py/blob/master/DataScience/CelebrityFaceRecognition/model/sports_celebrity_classification.ipynb

Special thanks to,
Debjyoti Paul (Amazon Data Scientist): For help with entire project

Do you want to learn technology from me? Check https://resources.codebasics.io/W7e0fR/ for my affordable video courses.

Website: https://resources.codebasics.io/W7e0fR
Facebook: https://www.facebook.com/codebasicshub
Twitter: https://twitter.com/codebasicshub