Repository navigation
Merged
Conversation
…xture, CI skeleton
…l-1 path and dead dependencies
…normalisation (A1, A10, A14)
…ibs.geo, narrow NaN warnings
…ice without smoothing (A2, A3, A4)
… 18 sites (A5, A6)
… AOI, strict split keys)
…nd memmap accumulator (A12)
…moke test, predictor close, parity on NaN pixels
…with prob and rank_score (A5, A7, A13)
… needs val composites, skip site eval during sanity check
…he API, MVT min_score, known-site seeding, PostGIS API tests (A8, A9)
…4 on untagged composites
… % coverage gate - Integration test: composite -> chips -> labels -> splits -> stats -> 2 CPU epochs -> LocalTorchPredictor -> evaluate on a composite 200 km east; recall@5 == 1.0. - Fix found by it: chip bboxes are in the raster CRS (UTM for Sentinel-2) but assign_splits read them as lon/lat, so every chip went to train. chip_raster now also emits bbox_4326 and assign_splits uses it. - tasks.py imports rasterio, sqlalchemy, the STAC client and torch-backed modules inside each task; importing the flows no longer loads torch (subprocess test). - Unit tests for the pipeline task bodies; coverage omits libs/stac/client.py (network) and services/api/* (PostGIS, api job); CI drops --cov-fail-under=0.
…, api coverage report, clear error on old manifests - fit: pl.seed_everything(cfg.seed, workers=True) before datasets and module are built (FitConfig.seed, default 0); replaces the late torch.manual_seed(0) that left model init unseeded. - Integration test: logged duration, generous 300 s bound instead of the 120 s assert. - assign_splits raises a clear ValueError on manifests without bbox_4326; dataset meta carries bbox_4326 when present. - Lazy-import test also checks pytorch_lightning and sqlalchemy. - api CI job reports services/api coverage (.coveragerc.api) and uploads coverage-api.xml. - Unit test for the evaluate CLI (fake predictor, README block update).
… runbook One default stats path (default_stats_path) for train_cli, evaluate and export_model; ingest --max-scenes passes through to ingest_aoi(limit=...); train_cli --precision. scripts/gpu_day.sh swaps in CUDA torch, passes the validation composites and uses the best checkpoint reported by training.
… and scanned area, fail-fast site validation, densified STAC bounds, lean deps
…ut AOIs fully held out, broadcast site metric, coverage gate on the api job
- /evidence/{id} no longer returns the server-side composite_path (shared
public_evidence helper in schemas)
- export_model ships the checkpoint's own stats, checked against a given
file via resolve_stats; --stats now defaults to None like evaluate
- detect flow defaults --stats to the local checkpoint's embedded stats and
loads channel_stats.json only for Triton (detect_stats_path)
- a truncated crop from an interrupted ingest is re-downloaded instead of
skipped on every run (reusable_crop)
- evaluate selects a split's composites by AOI (aoi_split), as the training
monitor does, instead of by stray chip labels; --manifest -> --aoi-config
- site circles are reprojected once per (sites, CRS) across all chips of an
AOI (lru_cache) instead of per chip
- memmap accumulator no longer writes 2 x H x W x 4 bytes of zeros eagerly
- web map draws the MVT polygon footprints at zoom >= 9
- synthetic planted-site generator moved to libs/synthetic so the benchmark
imports a packaged module
- README: how to upgrade a database created before v0.2 (idempotent schema)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
v0.2 makes the pipeline consistent from pixels to map and makes its evaluation honest.
BANDSPEC).channel_stats.json, computed on training-AOI composites only; the samenormalize()in training, evaluation, local inference and the ONNX export.evaluate.pyreports recall@{5,10,20}, FP per 1000 km² and reliability onprob, and can write the README results block; checkpoints are selected onval/site_recall@10.fit()training loop, one sliding window with aPredictor(local torch or Triton) and an optional memmap accumulator, a frozenDetectionwith separateprobandrank_score.?mode=rgb|nir), MVTmin_score, known-site seeding,probexposed next to the rank score.DualEncoderUNet, the async Triton client, dead dependencies.docs/hardware.md(incl. the issue Local pipeline is too slow on 8-CPU CPU-only setups #1 decision: remote GPU via Triton instead of tuning the CPU path), updated model and dataset cards,scripts/gpu_day.sh.The synthetic end-to-end test found and fixed a real bug: chip bboxes in UTM were read as lon/lat by the split assignment.
Tests
uv run pytest -q: 105 passed (unit + synthetic end-to-end on CPU, ~26 s); coverage 89.3 % against an 80 % gate.uv run pytest -m api -q: 8 passed on PostGIS; API coverage 89 % (reported by theapijob).lint-and-unit(ruff, pytest + coverage gate) andapi(PostGIS service container).What the GPU day adds
scripts/gpu_day.shingests the 17 AOIs (--max-scenes 20), trains on a GPU (--precision 16-mixed, monitor on the validation composites), runsevaluate.py --split val --split test --update-readme README.mdand exports ONNX for Triton. That fills the README results block with the first real-data numbers on the held-out sites.Test plan
pytest -q --cov(gate passes)pytest -m apiagainst local PostGISscripts/gpu_day.sh, commit README results andchannel_stats.jsonv0.2.0after merge