feat: sync integration updates across app and ML pipeline

feat: UI nav, onboarding, L2CS weights path + torch.load; trim dev files

Integrate L2CS-Net gaze estimation

change test params and files

Merge feature/clearml-thresholds

Sorry the previous commit came from feature/ui-fix not feature/integration-cleaned xD

MERGE EVERYTHING from feature/integration-cleaned :((((((((((((((((((((((((((((((((((((((((((((((( so tired

Merge prepare_dataset.py from feature/ui-fix

Merge all other things coming from feature/integration

Merge testing scripts from feauture/intergration

Start merging everything before 17/03/26

evaluation: channel ablation script + feature importance LOPO

refactor: single checkpoints/ dir, fix uvicorn cmd and hybrid config path

chore: MLP pipeline, evaluation updates, feature importance, confusion matrices

chore: integration cleanup — remove eye CNN, add threshold justification, fix pipeline

add api test

Merge branch 'feature/integration' of https://github.kcl.ac.uk/k23172173/GAP_Large_project into feature/integration

Update .gitignore

update params

Combine all updated main code together, forming new main.py

Fix open-cv GPU support problem (opencv library changed)

Combined main.py and main_yolo.py to create main_combined.py, where main.py came from Mohamad and main_yolo.py came from UI team. (To be tested)

Merge UI Manually (expect main)

Put all the models together (expect UI)

integrated open/closed eye cnn in script

Merge pull request #7 from k23172173/dev

Merge pull request #6 from k23172173/main

Replace CNN_MODEL submodule with actual files

Add CNN model

Add ClearML for mlp

remove old duplicate folders

reorg folders, add MLP demo

feat: data collection script, explorer notebook, sample sessions

feat: add optional eye model (YOLO/MobileNet) alongside geometry

feat: stage 2 head pose, eye behaviour, MAR/yawn, tighter focus; add torch deps

chore: add template layout and stage 1 face mesh demo

Merge pull request #3 from k23172173/template-branch

set up template with folder structure and training script

first commit