Add Mermaid architecture diagrams
Full encoder-decoder-with-attention flow diagram for the trained depth=2
config, plus block-level internals for Conv3DBlock, SE channel attention,
and the attention gate used on decoder skip connections.
Update all wiki pages to reflect 8-class segmentation model
- Model-Architecture.md: num_classes 4→8, full 8-class listing with WHO categories,
updated parameter table (CPU=2.2M), updated class weights
- Training-Guide.md: --num-classes default 8, training output format for all 7 classes,
test-set evaluation output, updated hardware table with actual timing
- Evaluation-Results.md: dataset size 8,673/1,858/1,860, config table updated
(2.2M params, depth=2, ~15min/epoch), per-class metrics table ready for results
- Dataset-Setup.md: actual folder names (Gliomas/, Meningothelial Tumors/, etc.),
class mapping table with all 7 WHO categories + pseudo-label explanation
Add Dataset Setup, Model Architecture, Training Guide, Evaluation Results pages; fix Home link