# Шаблоны архитектурных диаграмм NADEZHDA

## Mermaid: Полная система Teacher-Student

````markdown
```mermaid
graph TB
    subgraph Training ["ОБУЧЕНИЕ (5 модальностей, облако)"]
        direction TB
        SAT_T[🛰 Satellite RGB] --> DINO[DINOv3-L<br/>~300M frozen, patch 16, RegTokens]
        DRONE_T[🚁 Drone RGB] --> DINO
        SV[📷 Street-View] --> DINO
        DEPTH[🗺 Depth Map<br/>DA V2] --> DINO
        TEXT[📝 Text<br/>MobileCLIP2] --> FILM[Multi-FiLM<br/>γ·F + β]
        FILM --> DINO

        DINO --> TFEAT[Teacher Features]
        TFEAT --> TDESC[Teacher Descriptor<br/>512-dim, L2-norm]
        TFEAT --> TSEG[OV-Seg Head]
    end

    subgraph Inference ["ИНФЕРЕНС (2 модальности, Jetson)"]
        direction TB
        SAT_S[🛰 Satellite RGB] --> FVIT[FastViT-T12<br/>8.5M, weight-shared]
        DRONE_S[🚁 Drone RGB] --> FVIT
        FVIT --> SFEAT[Student Features]
        SFEAT --> CVD[CVD Split]
        CVD --> SDESC[Student Descriptor<br/>512-dim, L2-norm]
    end

    TDESC -.->|L_LUPI: MSE| SDESC
    TFEAT -.->|L_feat: Conv1×1| SFEAT
    TDESC -.->|L_RKD: relational| SDESC
    TSEG -.->|L_seg: CE+KL| SFEAT

    style Training fill:#e8eaf6,stroke:#283593
    style Inference fill:#fff8e1,stroke:#f57f17
```
````

## Mermaid: Progressive Loss Staging

````markdown
```mermaid
gantt
    title Progressive Loss Staging (60 epochs)
    dateFormat X
    axisFormat %s

    section Losses
    L_task (InfoNCE)          :active, 0, 60
    L_feat (alignment)        :crit, 10, 60
    L_CRD (contrastive repr.) :crit, 10, 60
    L_LUPI (privileged MSE)   :done, 20, 60
    L_RKD (relational)        :done, 20, 60
    L_seg (segmentation)      :done, 20, 60
    L_CVD (disentanglement)   :done, 20, 60

    section Phases
    Warmup (L_task only)      :milestone, 0, 10
    Ramp-up (+L_feat, L_CRD)  :milestone, 10, 20
    Full (all 7 losses)       :milestone, 20, 60
```
````

## Mermaid: Student Backbone Stages

````markdown
```mermaid
graph LR
    IN["Input<br/>[B,3,256,256]"] --> S1["Stage 1<br/>[B,32,96,96]"]
    S1 --> S2["Stage 2<br/>[B,64,48,48]"]
    S2 --> BRIDGE["Conv1×1<br/>Bridge"]
    BRIDGE --> S3["Stage 3<br/>[B,128,24,24]"]
    S3 --> S4["Stage 4<br/>[B,256,12,12]"]
    S4 --> POOL["GGeM Pool"]
    POOL --> DESC["Descriptor<br/>[B,512]"]

    S1 ~~~ NOTE1["SOFIA<br/>(DCN blocks)"]
    S3 ~~~ NOTE2["MambaVision<br/>(SSM+ViT)"]

    style S1 fill:#fff3e0,stroke:#e65100
    style S2 fill:#fff3e0,stroke:#e65100
    style S3 fill:#e3f2fd,stroke:#1565c0
    style S4 fill:#e3f2fd,stroke:#1565c0
    style NOTE1 fill:#fff3e0,stroke:none,color:#e65100
    style NOTE2 fill:#e3f2fd,stroke:none,color:#1565c0
```
````

## Mermaid: Data Augmentation Pipeline

````markdown
```mermaid
graph LR
    RAW[Raw RGB<br/>512×512] --> RESIZE[Resize<br/>256×256]
    RESIZE --> DA["Depth Anything V2<br/>Large (335M)"]
    RESIZE --> DSINE["DSINE<br/>(30M)"]
    RESIZE --> SEG["SegFormer-B5<br/>(85M)"]

    DA --> D_OUT["depth.npy<br/>[1,256,256]"]
    DSINE --> N_OUT["normal.npy<br/>[3,256,256]"]
    SEG --> S_OUT["seg.npy<br/>[1,256,256]"]

    RESIZE --> RGB["RGB<br/>[3,256,256]"]
    RGB --> CONCAT["concat_8ch.npy<br/>[8,256,256]"]
    D_OUT --> CONCAT
    N_OUT --> CONCAT
    S_OUT --> CONCAT

    style DA fill:#e8f5e9,stroke:#2e7d32
    style DSINE fill:#fce4ec,stroke:#c62828
    style SEG fill:#e3f2fd,stroke:#1565c0
```
````