Learn to implement a top 5 Kaggle solution for detecting facial keypoints using deep learning in this comprehensive tutorial video. Explore the competition details, understand the data and task at hand, and delve into the metric used for evaluation. Gain insights into the solution steps, including code implementation for configuration, dataset handling, data splitting, and submission format. Follow along with the main training file, troubleshoot errors, and discover ways to improve your score. Conclude with valuable tips and reflections on participating in Kaggle competitions.
Detecting Facial Keypoints with Deep Learning
Overview
Syllabus
- Introduction to competition
- Why?
- The data and the task
- Metric used
- A more in depth look at the data
- The steps of the solution
- Code: config
- Code: dataset
- Code: split_data
- Understanding submission format
- Code: utils
- Code: train/main file
- Fixing a small error
- Checking the score of submission
- How to improve it further?
- My 2 things to try for improving the score
- Ending & my thoughts on Kaggle
Taught by
Aladdin Persson
Related Courses
-
How to Solve Santander Kaggle Transaction Competition - Top 1% Solution, No Ensemble
-
Deep Learning for Computer Vision with TensorFlow – Complete Course
-
Bengali.AI- Handwritten Grapheme Classification Using PyTorch
-
Build a Deep Iris Detection Model Using Python and Tensorflow - Keypoint Detection
-
Pytorch Seq2Seq Tutorial for Machine Translation
-
Instrumenting Weights & Biases for PII Data Detection - ML Pipeline Tutorial
