Intermediate level · Module 6 of 6 · 17 guided hours
Intermediate Deep Learning Project
Deliver the medicine package recognition project from data to a recommended, mobile-ready model.
Learning objectives
- Plan a deep learning project with deployment targets
- Build, train and compare models with reproducible code
- Evaluate, document and present the results
Topics
- requirements and targets
- data set documentation
- training and comparison
- field evaluation
- recommendations
- presentation
Lessons
-
Lesson 1 Targets and Data
Agree accuracy, size and speed targets and finalise the documented data set.
deployment targetsdata cardcoverageknown gaps
-
Lesson 2 Training and Comparison
Train candidate models with the project's training code and compare them against the targets.
reproducible runscomparison tabletarget checkselection
-
Lesson 3 Evaluation and Presentation
Evaluate the chosen model on the field test, analyse errors and present recommendations.
field test resultserror categorieslimitspresentation and demonstration
Practical activity
Deliver the level project through three reviewed stages: targets and data, training and comparison, evaluation and presentation.
Expected outcomes
- A complete deep learning project
- Experience balancing accuracy and deployment constraints
Assessment
The level project assessed against its criteria with a presentation and a live prediction demonstration.
Taught live by an instructor — online or in person. Free course lessons are for self-study and do not lead to a certificate — see registration options.