Files
geointel/docs/PYTORCH_MODEL_PROGRAM.md
T
Jens 36aa3177e7
GeoIntel release gates / Compile, test, contracts and builds (push) Canceled after 0s
GeoIntel release gates / Python and npm vulnerability policy (push) Canceled after 0s
GeoIntel release gates / GIS image, SBOM and container scan (push) Canceled after 0s
feat: harden governed PyTorch training programme
2026-07-26 17:18:42 +02:00

53 lines
3.2 KiB
Markdown

# PyTorch model programme
## Principle
PyTorch is the governed CUDA runtime for trainable image models. It is not a
replacement for authoritative GIS processing. Terrain, flood depth, land-use
classes, road length, water area and vector/raster change remain deterministic
source-derived analyses.
## Capability matrix
| Capability | Method | Current state | Promotion requirement |
|---|---|---|---|
| Building localisation | YOLO detection on orthophoto | Operational for `building`; validated only in Mol/Kempen | geographically independent Belgian train/validation/test portfolio, including Flanders, Wallonia and Brussels |
| Building footprint | official GRB/PICC/URBIS geometry | Operational where the governed source covers the AOI | no neural model; source coverage and freshness gates |
| Roads and water | official vectors and thematic rasters | Operational by provider zone | no detector unless a separately justified imagery use case and reviewed labels exist |
| Land use / vegetation | official classified rasters | Operational where source coverage exists | no neural model; preserve official class semantics |
| Terrain / flood / bathymetry | numeric raster analysis | Operational or explicit `not_configured` per source | no neural model; source and CRS validation |
| Solar panels or other imagery objects | dedicated detector | Unvalidated local asset only | task-specific labels, negative corpus, independent hold-outs and promotion report |
| Segmentation | dedicated YOLO-seg/SAM model | `not_configured` | reviewed polygon/mask corpus and segmentation QA; detection boxes are not valid mask labels |
## Training rules
1. One model contract per task and canonical class set.
2. Training, validation and test samples are separated geographically; an AOI
or overlapping image tile may occur in only one split.
3. Reference labels identify authority, source, layer, observation/publication
date, CRS and checksum.
4. Production training requires NVIDIA CUDA and fails closed when unavailable.
5. Every challenger is evaluated on positive AOIs, pure-empty negatives and
difficult contextual negatives. Promotion is never based on training loss.
6. A model remains `not_configured` outside its independently proven geography
and classes.
## Executable waves
1. **Building Belgium corpus:** prepare spatially disjoint samples from GRB
(Flanders), PICC (Wallonia) and URBIS (Brussels) against temporally compatible
orthophotos. Keep complete municipalities outside training as test areas.
2. **Building challenger:** train on Tower using PyTorch CUDA, compare against
the active model at fixed thresholds and retain the current model unless all
promotion gates pass.
3. **Additional imagery task intake:** admit solar panels or another class only
after an explicit use case and reviewed labels exist. Never infer new classes
from the building corpus.
4. **Segmentation intake:** build a polygon/mask corpus and independent QA before
enabling YOLO-seg or SAM.
The tile exporter accepts explicit `--class-name`, `--reference-source` and
`--reference-layer` values and records them in dataset evidence. The production
training wrapper supports `TRAIN_REQUIRE_CUDA=true` and records CUDA and PyTorch
runtime evidence in every training summary.