def main(args):
config = load_config(args.config)
check_classes(config)
index = [
i for i in (list(range(len(config["classes"]))))
if config["classes"][i]["title"] == args.type
]
if not index:
sys.exit(
"ERROR: Requested type {} not found among classes title in the config file."
.format(args.type))
print("RoboSat.pink - vectorize {} from {}".format(args.type, args.masks))
with open(args.out, "w", encoding="utf-8") as out:
first = True
out.write('{"type":"FeatureCollection","features":[')
for tile, path in tqdm(list(tiles_from_slippy_map(args.masks)),
ascii=True,
unit="mask"):
try:
features = (np.array(Image.open(path).convert("P"),
dtype=np.uint8) == index).astype(np.uint8)
try:
C, W, H = features.shape
except:
W, H = features.shape
transform = rasterio.transform.from_bounds(
(*mercantile.bounds(tile.x, tile.y, tile.z)), W, H)
for shape, value in rasterio.features.shapes(
features, transform=transform):
prop = '"properties":{{"x":{},"y":{},"z":{}}}'.format(
int(tile.x), int(tile.y), int(tile.z))
geom = '"geometry":{{"type": "Polygon", "coordinates":{}}}'.format(
json.dumps(shape["coordinates"]))
out.write('{}{{"type":"Feature",{},{}}}'.format(
"," if not first else "", geom, prop))
first = False
except:
sys.exit("ERROR: Unable to vectorize tile {}.".format(
str(tile)))
out.write("]}")
def main(args):
if not args.workers:
args.workers = max(1, math.floor(os.cpu_count() * 0.5))
if args.label:
config = load_config(args.config)
check_classes(config)
colors = [classe["color"] for classe in config["classes"]]
palette = make_palette(*colors)
splits_path = os.path.join(os.path.expanduser(args.out), ".splits")
tiles_map = {}
print("RoboSat.pink - tile on CPU, with {} workers".format(args.workers))
bands = -1
for path in args.rasters:
try:
raster = rasterio_open(path)
w, s, e, n = transform_bounds(raster.crs, "EPSG:4326", *raster.bounds)
except:
sys.exit("Error: Unable to load raster {} or deal with it's projection".format(args.raster))
if bands != -1:
assert bands == len(raster.indexes), "Coverage must be bands consistent"
bands = len(raster.indexes)
tiles = [mercantile.Tile(x=x, y=y, z=z) for x, y, z in mercantile.tiles(w, s, e, n, args.zoom)]
for tile in tiles:
tile_key = (str(tile.x), str(tile.y), str(tile.z))
if tile_key not in tiles_map.keys():
tiles_map[tile_key] = []
tiles_map[tile_key].append(path)
if args.label:
ext = "png"
bands = 1
if not args.label:
if bands == 1:
ext = "png"
if bands == 3:
ext = "webp"
if bands > 3:
ext = "tiff"
tiles = []
progress = tqdm(total=len(tiles_map), ascii=True, unit="tile")
# Begin to tile plain tiles
with futures.ThreadPoolExecutor(args.workers) as executor:
def worker(path):
raster = rasterio_open(path)
w, s, e, n = transform_bounds(raster.crs, "EPSG:4326", *raster.bounds)
transform, _, _ = calculate_default_transform(raster.crs, "EPSG:3857", raster.width, raster.height, w, s, e, n)
tiles = [mercantile.Tile(x=x, y=y, z=z) for x, y, z in mercantile.tiles(w, s, e, n, args.zoom)]
tiled = []
for tile in tiles:
try:
w, s, e, n = mercantile.xy_bounds(tile)
# inspired by rio-tiler, cf: https://github.com/mapbox/rio-tiler/pull/45
warp_vrt = WarpedVRT(
raster,
crs="epsg:3857",
resampling=Resampling.bilinear,
add_alpha=False,
transform=from_bounds(w, s, e, n, args.ts, args.ts),
width=math.ceil((e - w) / transform.a),
height=math.ceil((s - n) / transform.e),
)
data = warp_vrt.read(
out_shape=(len(raster.indexes), args.ts, args.ts), window=warp_vrt.window(w, s, e, n)
)
image = np.moveaxis(data, 0, 2) # C,H,W -> H,W,C
except:
sys.exit("Error: Unable to tile {} from raster {}.".format(str(tile), raster))
tile_key = (str(tile.x), str(tile.y), str(tile.z))
if not args.label and len(tiles_map[tile_key]) == 1 and is_border(image):
progress.update()
continue
if len(tiles_map[tile_key]) > 1:
out = os.path.join(splits_path, str(tiles_map[tile_key].index(path)))
else:
out = args.out
x, y, z = map(int, tile)
if not args.label:
ret = tile_image_to_file(out, mercantile.Tile(x=x, y=y, z=z), image)
if args.label:
ret = tile_label_to_file(out, mercantile.Tile(x=x, y=y, z=z), palette, image)
if not ret:
sys.exit("Error: Unable to write tile {} from raster {}.".format(str(tile), raster))
if len(tiles_map[tile_key]) == 1:
progress.update()
tiled.append(mercantile.Tile(x=x, y=y, z=z))
return tiled
for tiled in executor.map(worker, args.rasters):
if tiled is not None:
tiles.extend(tiled)
# Aggregate remaining tiles splits
with futures.ThreadPoolExecutor(args.workers) as executor:
def worker(tile_key):
if len(tiles_map[tile_key]) == 1:
return
image = np.zeros((args.ts, args.ts, bands), np.uint8)
x, y, z = map(int, tile_key)
for i in range(len(tiles_map[tile_key])):
root = os.path.join(splits_path, str(i))
_, path = tile_from_slippy_map(root, x, y, z)
if not args.label:
split = tile_image_from_file(path)
if args.label:
split = tile_label_from_file(path)
split = split.reshape((args.ts, args.ts, 1)) # H,W -> H,W,C
assert image.shape == split.shape
image[:, :, :] += split[:, :, :]
if not args.label and is_border(image):
progress.update()
return
tile = mercantile.Tile(x=x, y=y, z=z)
if not args.label:
ret = tile_image_to_file(args.out, tile, image)
if args.label:
ret = tile_label_to_file(args.out, tile, palette, image)
if not ret:
sys.exit("Error: Unable to write tile {}.".format(str(tile_key)))
progress.update()
return tile
for tiled in executor.map(worker, tiles_map.keys()):
if tiled is not None:
tiles.append(tiled)
if splits_path and os.path.isdir(splits_path):
shutil.rmtree(splits_path) # Delete suffixes dir if any
if not args.no_web_ui:
template = "leaflet.html" if not args.web_ui_template else args.web_ui_template
base_url = args.web_ui_base_url if args.web_ui_base_url else "./"
web_ui(args.out, base_url, tiles, tiles, ext, template)
def main(args):
if (args.geojson and args.postgis) or (not args.geojson
and not args.postgis):
sys.exit(
"ERROR: Input features to rasterize must be either GeoJSON or PostGIS"
)
if args.postgis and not args.pg_dsn:
sys.exit(
"ERROR: With PostGIS input features, --pg_dsn must be provided")
config = load_config(args.config)
check_classes(config)
palette = make_palette(*[classe["color"] for classe in config["classes"]],
complementary=True)
burn_value = 1
args.out = os.path.expanduser(args.out)
os.makedirs(args.out, exist_ok=True)
log = Logs(os.path.join(args.out, "log"), out=sys.stderr)
def geojson_parse_polygon(zoom, srid, feature_map, polygon, i):
try:
if srid != 4326:
polygon = [
xy for xy in geojson_reproject(
{
"type": "feature",
"geometry": polygon
}, srid, 4326)
][0]
for i, ring in enumerate(
polygon["coordinates"]
): # GeoJSON coordinates could be N dimensionals
polygon["coordinates"][i] = [[
x, y
] for point in ring for x, y in zip([point[0]], [point[1]])]
if polygon["coordinates"]:
for tile in burntiles.burn([{
"type": "feature",
"geometry": polygon
}],
zoom=zoom):
feature_map[mercantile.Tile(*tile)].append({
"type":
"feature",
"geometry":
polygon
})
except ValueError:
log.log("Warning: invalid feature {}, skipping".format(i))
return feature_map
def geojson_parse_geometry(zoom, srid, feature_map, geometry, i):
if geometry["type"] == "Polygon":
feature_map = geojson_parse_polygon(zoom, srid, feature_map,
geometry, i)
elif geometry["type"] == "MultiPolygon":
for polygon in geometry["coordinates"]:
feature_map = geojson_parse_polygon(zoom, srid, feature_map, {
"type": "Polygon",
"coordinates": polygon
}, i)
else:
log.log(
"Notice: {} is a non surfacic geometry type, skipping feature {}"
.format(geometry["type"], i))
return feature_map
if args.geojson:
try:
tiles = [
tile for tile in tiles_from_csv(os.path.expanduser(args.cover))
]
zoom = tiles[0].z
assert not [tile for tile in tiles if tile.z != zoom]
except:
sys.exit("ERROR: Inconsistent cover {}".format(args.cover))
feature_map = collections.defaultdict(list)
log.log("RoboSat.pink - rasterize - Compute spatial index")
for geojson_file in args.geojson:
with open(os.path.expanduser(geojson_file)) as geojson:
try:
feature_collection = json.load(geojson)
except:
sys.exit("ERROR: {} is not a valid JSON file.".format(
geojson_file))
try:
crs_mapping = {"CRS84": "4326", "900913": "3857"}
srid = feature_collection["crs"]["properties"][
"name"].split(":")[-1]
srid = int(srid) if srid not in crs_mapping else int(
crs_mapping[srid])
except:
srid = int(4326)
for i, feature in enumerate(
tqdm(feature_collection["features"],
ascii=True,
unit="feature")):
try:
if feature["geometry"]["type"] == "GeometryCollection":
for geometry in feature["geometry"]["geometries"]:
feature_map = geojson_parse_geometry(
zoom, srid, feature_map, geometry, i)
else:
feature_map = geojson_parse_geometry(
zoom, srid, feature_map, feature["geometry"],
i)
except:
sys.exit(
"ERROR: Unable to parse {} file. Seems not a valid GEOJSON file."
.format(geojson_file))
log.log(
"RoboSat.pink - rasterize - rasterizing tiles from {} on cover {}".
format(args.geojson, args.cover))
with open(os.path.join(os.path.expanduser(args.out),
"instances.cover"),
mode="w") as cover:
for tile in tqdm(list(
tiles_from_csv(os.path.expanduser(args.cover))),
ascii=True,
unit="tile"):
try:
if tile in feature_map:
cover.write("{},{},{} {}{}".format(
tile.x, tile.y, tile.z, len(feature_map[tile]),
os.linesep))
out = geojson_tile_burn(tile, feature_map[tile], 4326,
args.ts, burn_value)
else:
cover.write("{},{},{} {}{}".format(
tile.x, tile.y, tile.z, 0, os.linesep))
out = np.zeros(shape=(args.ts, args.ts),
dtype=np.uint8)
tile_label_to_file(args.out, tile, palette, out)
except:
log.log("Warning: Unable to rasterize tile. Skipping {}".
format(str(tile)))
if args.postgis:
try:
pg_conn = psycopg2.connect(args.pg_dsn)
pg = pg_conn.cursor()
except Exception:
sys.exit("Unable to connect PostgreSQL: {}".format(args.pg_dsn))
log.log(
"RoboSat.pink - rasterize - rasterizing tiles from PostGIS on cover {}"
.format(args.cover))
log.log(" SQL {}".format(args.postgis))
try:
pg.execute(
"SELECT ST_Srid(geom) AS srid FROM ({} LIMIT 1) AS sub".format(
args.postgis))
srid = pg.fetchone()[0]
except Exception:
sys.exit("Unable to retrieve geometry SRID.")
for tile in tqdm(list(tiles_from_csv(args.cover)),
ascii=True,
unit="tile"):
s, w, e, n = mercantile.bounds(tile)
raster = np.zeros((args.ts, args.ts))
query = """
WITH
bbox AS (SELECT ST_Transform(ST_MakeEnvelope({},{},{},{}, 4326), {} ) AS bbox),
bbox_merc AS (SELECT ST_Transform(ST_MakeEnvelope({},{},{},{}, 4326), 3857) AS bbox),
rast_a AS (SELECT ST_AddBand(
ST_SetSRID(
ST_MakeEmptyRaster({}, {}, ST_Xmin(bbox), ST_Ymax(bbox), (ST_YMax(bbox) - ST_YMin(bbox)) / {}),
3857),
'8BUI'::text, 0) AS rast
FROM bbox_merc),
features AS (SELECT ST_Union(ST_Transform(ST_Force2D(geom), 3857)) AS geom
FROM ({}) AS sub, bbox
WHERE ST_Intersects(geom, bbox)),
rast_b AS (SELECT ST_AsRaster(geom, rast, '8BUI', {}) AS rast
FROM features, rast_a
WHERE NOT ST_IsEmpty(geom))
SELECT ST_AsBinary(ST_MapAlgebra(rast_a.rast, rast_b.rast, '{}', NULL, 'FIRST')) AS wkb FROM rast_a, rast_b
""".format(s, w, e, n, srid, s, w, e, n, args.ts, args.ts, args.ts,
args.postgis, burn_value, burn_value)
try:
pg.execute(query)
row = pg.fetchone()
if row:
raster = np.squeeze(wkb_to_numpy(io.BytesIO(row[0])),
axis=2)
except Exception:
log.log(
"Warning: Invalid geometries, skipping {}".format(tile))
pg_conn = psycopg2.connect(args.pg_dsn)
pg = pg_conn.cursor()
try:
tile_label_to_file(args.out, tile, palette, raster)
except:
log.log(
"Warning: Unable to rasterize tile. Skipping {}".format(
str(tile)))
if not args.no_web_ui:
template = "leaflet.html" if not args.web_ui_template else args.web_ui_template
base_url = args.web_ui_base_url if args.web_ui_base_url else "./"
tiles = [tile for tile in tiles_from_csv(args.cover)]
web_ui(args.out, base_url, tiles, tiles, "png", template)
def main(args):
config = load_config(args.config)
args.out = os.path.expanduser(args.out)
args.workers = torch.cuda.device_count() * 2 if torch.device(
"cuda") and not args.workers else args.workers
config["model"][
"loader"] = args.loader if args.loader else config["model"]["loader"]
config["model"]["bs"] = args.bs if args.bs else config["model"]["bs"]
config["model"]["lr"] = args.lr if args.lr else config["model"]["lr"]
config["model"]["ts"] = args.ts if args.ts else config["model"]["ts"]
config["model"]["nn"] = args.nn if args.nn else config["model"]["nn"]
config["model"][
"loss"] = args.loss if args.loss else config["model"]["loss"]
config["model"]["da"] = args.da if args.da else config["model"]["da"]
config["model"]["dap"] = args.dap if args.dap else config["model"]["dap"]
check_classes(config)
check_channels(config)
check_model(config)
if not os.path.isdir(os.path.expanduser(args.dataset)):
sys.exit("ERROR: dataset {} is not a directory".format(args.dataset))
log = Logs(os.path.join(args.out, "log"))
if torch.cuda.is_available():
log.log("RoboSat.pink - training on {} GPUs, with {} workers".format(
torch.cuda.device_count(), args.workers))
log.log("(Torch:{} Cuda:{} CudNN:{})".format(
torch.__version__, torch.version.cuda,
torch.backends.cudnn.version()))
device = torch.device("cuda")
torch.backends.cudnn.benchmark = True
else:
log.log("RoboSat.pink - training on CPU, with {} workers - (Torch:{})".
format(args.workers, torch.__version__))
log.log(
"WARNING: Are you really sure sure about not training on GPU ?")
device = torch.device("cpu")
try:
loader = import_module("robosat_pink.loaders.{}".format(
config["model"]["loader"].lower()))
loader_train = getattr(loader, config["model"]["loader"])(
config, config["model"]["ts"],
os.path.join(args.dataset, "training"), "train")
loader_val = getattr(loader, config["model"]["loader"])(
config, config["model"]["ts"],
os.path.join(args.dataset, "validation"), "train")
except:
sys.exit("ERROR: Unable to load data loaders")
try:
model_module = import_module("robosat_pink.models.{}".format(
config["model"]["nn"].lower()))
except:
sys.exit("ERROR: Unable to load {} model".format(
config["model"]["nn"]))
nn = getattr(model_module, config["model"]["nn"])(
loader_train.shape_in, loader_train.shape_out,
config["model"]["pretrained"]).to(device)
nn = torch.nn.DataParallel(nn)
optimizer = Adam(nn.parameters(), lr=config["model"]["lr"])
resume = 0
if args.checkpoint:
try:
chkpt = torch.load(os.path.expanduser(args.checkpoint),
map_location=device)
nn.load_state_dict(chkpt["state_dict"])
log.log("Using checkpoint: {}".format(args.checkpoint))
except:
sys.exit("ERROR: Unable to load {} checkpoint".format(
args.checkpoint))
if args.resume:
optimizer.load_state_dict(chkpt["optimizer"])
resume = chkpt["epoch"]
if resume >= args.epochs:
sys.exit(
"ERROR: Epoch {} already reached by the given checkpoint".
format(config["model"]["epochs"]))
try:
loss_module = import_module("robosat_pink.losses.{}".format(
config["model"]["loss"].lower()))
criterion = getattr(loss_module, config["model"]["loss"])().to(device)
except:
sys.exit("ERROR: Unable to load {} loss".format(
config["model"]["loss"]))
bs = config["model"]["bs"]
train_loader = DataLoader(loader_train,
batch_size=bs,
shuffle=True,
drop_last=True,
num_workers=args.workers)
val_loader = DataLoader(loader_val,
batch_size=bs,
shuffle=False,
drop_last=True,
num_workers=args.workers)
log.log("--- Input tensor from Dataset: {} ---".format(args.dataset))
num_channel = 1 # 1-based numerotation
for channel in config["channels"]:
for band in channel["bands"]:
log.log("Channel {}:\t\t {}[band: {}]".format(
num_channel, channel["name"], band))
num_channel += 1
log.log("--- Hyper Parameters ---")
for hp in config["model"]:
log.log("{}{}".format(hp.ljust(25, " "), config["model"][hp]))
for epoch in range(resume, args.epochs):
UUID = uuid.uuid1()
log.log("---{}Epoch: {}/{} -- UUID: {}".format(os.linesep, epoch + 1,
args.epochs, UUID))
train(train_loader, config, log, device, nn, optimizer, criterion)
validate(val_loader, config, log, device, nn, criterion)
try: # https://github.com/pytorch/pytorch/issues/9176
nn_doc = nn.module.doc
nn_version = nn.module.version
except AttributeError:
nn_version = nn.version
nn_doc == nn.doc
states = {
"uuid": UUID,
"model_version": nn_version,
"producer_name": "RoboSat.pink",
"producer_version": "0.4.0",
"model_licence": "MIT",
"domain": "pink.RoboSat", # reverse-DNS
"doc_string": nn_doc,
"shape_in": loader_train.shape_in,
"shape_out": loader_train.shape_out,
"state_dict": nn.state_dict(),
"epoch": epoch + 1,
"nn": config["model"]["nn"],
"optimizer": optimizer.state_dict(),
"loader": config["model"]["loader"],
}
checkpoint_path = os.path.join(
args.out, "checkpoint-{:05d}.pth".format(epoch + 1))
try:
torch.save(states, checkpoint_path)
except:
sys.exit(
"ERROR: Unable to save checkpoint {}".format(checkpoint_path))
def main(args):
config = load_config(args.config)
check_channels(config)
check_classes(config)
args.workers = torch.cuda.device_count() * 2 if torch.device(
"cuda") and not args.workers else args.workers
log = Logs(os.path.join(args.out, "log"))
if torch.cuda.is_available():
log.log("RoboSat.pink - predict on {} GPUs, with {} workers".format(
torch.cuda.device_count(), args.workers))
log.log("(Torch:{} Cuda:{} CudNN:{})".format(
torch.__version__, torch.version.cuda,
torch.backends.cudnn.version()))
device = torch.device("cuda")
torch.backends.cudnn.benchmark = True
else:
log.log("RoboSat.pink - predict on CPU, with {} workers".format(
args.workers))
device = torch.device("cpu")
try:
chkpt = torch.load(args.checkpoint, map_location=device)
assert chkpt["producer_name"] == "RoboSat.pink"
model_module = import_module("robosat_pink.models.{}".format(
chkpt["nn"].lower()))
nn = getattr(model_module, chkpt["nn"])(chkpt["shape_in"],
chkpt["shape_out"]).to(device)
nn = torch.nn.DataParallel(nn)
nn.load_state_dict(chkpt["state_dict"])
nn.eval()
except:
sys.exit("ERROR: Unable to load {} checkpoint.".format(
args.checkpoint))
log.log("Model {} - UUID: {}".format(chkpt["nn"], chkpt["uuid"]))
try:
loader_module = import_module("robosat_pink.loaders.{}".format(
chkpt["loader"].lower()))
loader_predict = getattr(loader_module,
chkpt["loader"])(config,
chkpt["shape_in"][1:3],
args.tiles,
mode="predict")
except:
sys.exit("ERROR: Unable to load {} data loader.".format(
chkpt["loader"]))
loader = DataLoader(loader_predict,
batch_size=args.bs,
num_workers=args.workers)
palette = make_palette(config["classes"][0]["color"],
config["classes"][1]["color"])
with torch.no_grad(
): # don't track tensors with autograd during prediction
for images, tiles in tqdm(loader,
desc="Eval",
unit="batch",
ascii=True):
images = images.to(device)
try:
outputs = nn(images)
probs = torch.nn.functional.softmax(outputs,
dim=1).data.cpu().numpy()
except:
log.log("WARNING: Skipping batch:")
for tile, prob in zip(tiles, probs):
log.log(" - {}".format(str(tile)))
continue
for tile, prob in zip(tiles, probs):
try:
x, y, z = list(map(int, tile))
mask = np.around(prob[1:, :, :]).astype(np.uint8).squeeze()
tile_label_to_file(args.out, mercantile.Tile(x, y, z),
palette, mask)
except:
log.log("WARNING: Skipping tile {}".format(str(tile)))
if not args.no_web_ui:
template = "leaflet.html" if not args.web_ui_template else args.web_ui_template
base_url = args.web_ui_base_url if args.web_ui_base_url else "./"
tiles = [tile for tile, _ in tiles_from_slippy_map(args.out)]
web_ui(args.out, base_url, tiles, tiles, "png", template)