A complete 22-week pathway for learners who want to become capable computer vision builders, starting from foundations and progressing to deployed, evaluation-backed CV systems and capstone defense.
Students learn to design and ship systems that combine detection, segmentation, tracking, and deployment workflows.
You leave with project repositories, metrics summaries, deployment demos, and a final architecture presentation.
This path exists so learners do not skip core engineering foundations before entering advanced CV specialization.
Core stack covered across foundations, deployment, and specialization:
NumPy, Pandas, scikit-learn
PyTorch, CNNs, transfer learning
Detection, segmentation, tracking, generative models
FastAPI, Docker, Streamlit, deployment packaging
Use this section to self-select before applying so you choose the right path for your current level.
If you are already prepared in Python/ML/DL, the shorter advanced CV specialization track may be more efficient.
Clear architecture so applicants choose by readiness, not by guesswork.
Presented in three layers for clarity: top-level overview, phase summaries, then grouped week-level structure.
A 22-week diploma that moves from core engineering fundamentals into production computer vision specialization.
It prevents learners from jumping into advanced CV topics before they can code, evaluate, debug, and deploy reliably.
Design and deliver practical CV pipelines with measurable outcomes and production-ready packaging.
Programming fundamentals, data handling basics, EDA, and visualization discipline.
Output: foundational mini-projects and structured notebooks.
Model workflow discipline, evaluation logic, regression/classification diagnostics, and comparisons.
Output: model recommendation memos and evidence-based analysis.
Neural network mechanics, PyTorch workflow, and transfer learning orientation.
Output: diagnostic DL mini-project with comparative reasoning.
Serving vision inference, API design, containerization, and deployment packaging.
Output: deployment-ready CV mini-service.
Advanced computer vision modules across preprocessing, recognition, detection, segmentation, tracking, and generative vision.
Output: practical specialization artifacts with evaluation summaries.
Integration sprint, model refinement, deployment polish, presentation, and architecture defense.
Output: interview-ready capstone package and live defense.
From coding fundamentals to practical data workflows.
Modeling discipline and evaluation-driven decision making.
Transition from classical ML to modern deep learning workflows.
Production exposure before entering advanced CV specialization.
Core specialization modules across modern computer vision tasks.
Integrate all major pieces into one interview-ready system.
You can speak to admissions to confirm whether the full diploma or the shorter advanced CV track better matches your background.
Admissions support helps with pathway alignment and readiness review. It is not a hiring guarantee.
Graduation is based on evidence: reproducible implementation, measurable quality, and clear communication of design decisions.
Graduate transformation: from learner to practitioner who can build, evaluate, package, and present end-to-end computer vision systems.
