def main():
ap = argparse.ArgumentParser(description='run model on tileset')
ap.add_argument('model', help='path to model checkpoint')
ap.add_argument('config', help='path to model config')
ap.add_argument('tiles', help='path to XYZ tile folder')
ap.add_argument('outputdir', help='name for tile output')
ap.add_argument('--aws_profile',
help='AWS Profile Name',
default='default')
args = ap.parse_args()
config = load_config(args.config)
tiles = S3SlippyMapTiles(args.tiles,
mode='multibands',
aws_profile=args.aws_profile)
net = model(config, args.model)
loader = DataLoader(tiles,
batch_size=config['model']['batch_size'],
shuffle=True,
num_workers=1)
palette = make_palette(config["classes"][0]["color"])
fs = s3fs.S3FileSystem(session=boto3.Session(profile_name='esip'))
outputdir = args.outputdir[5:] + '/' + os.path.basename(args.tiles)
print("Saving predictions to {}.".format(outputdir))
predict(net, loader, outputdir, palette, fs)
def write_tile(root, tile, colors, out):
""" """
out_path = os.path.join(root, str(tile.z), str(tile.x))
os.makedirs(out_path, exist_ok=True)
out = Image.fromarray(out, mode="P")
out.putpalette(complementary_palette(make_palette(colors[0], colors[1])))
out.save(os.path.join(out_path, "{}.png".format(tile.y)), optimize=True)
def main(args):
config = load_config(args.config)
num_classes = len(config["classes"])
batch_size = args.batch_size if args.batch_size else config["model"][
"batch_size"]
tile_size = args.tile_size if args.tile_size else config["model"][
"tile_size"]
if torch.cuda.is_available():
device = torch.device("cuda")
torch.backends.cudnn.benchmark = True
else:
device = torch.device("cpu")
def map_location(storage, _):
return storage.cuda() if torch.cuda.is_available() else storage.cpu()
# https://github.com/pytorch/pytorch/issues/7178
chkpt = torch.load(args.checkpoint, map_location=map_location)
models = [
name for _, name, _ in pkgutil.iter_modules(
[os.path.dirname(robosat_pink.models.__file__)])
]
if config["model"]["name"] not in [model for model in models]:
sys.exit("Unknown model, thoses available are {}".format(
[model for model in models]))
std = []
mean = []
num_channels = 0
for channel in config["channels"]:
std.extend(channel["std"])
mean.extend(channel["mean"])
num_channels += len(channel["bands"])
encoder = config["model"]["encoder"]
pretrained = config["model"]["pretrained"]
model_module = import_module("robosat_pink.models.{}".format(
config["model"]["name"]))
net = getattr(model_module, "{}".format(config["model"]["name"].title()))(
num_classes=num_classes,
num_channels=num_channels,
encoder=encoder,
pretrained=pretrained).to(device)
net = torch.nn.DataParallel(net)
net.load_state_dict(chkpt["state_dict"])
net.eval()
transform = Compose([ImageToTensor(), Normalize(mean=mean, std=std)])
directory = BufferedSlippyMapTiles(args.tiles,
transform=transform,
size=tile_size,
overlap=args.overlap)
loader = DataLoader(directory,
batch_size=batch_size,
num_workers=args.workers)
palette = make_palette(config["classes"][0]["color"],
config["classes"][1]["color"])
# don't track tensors with autograd during prediction
with torch.no_grad():
for images, tiles in tqdm(loader,
desc="Eval",
unit="batch",
ascii=True):
images = images.to(device)
outputs = net(images)
# manually compute segmentation mask class probabilities per pixel
probs = torch.nn.functional.softmax(outputs,
dim=1).data.cpu().numpy()
for tile, prob in zip(tiles, probs):
x, y, z = list(map(int, tile))
# we predicted on buffered tiles; now get back probs for original image
prob = directory.unbuffer(prob)
assert prob.shape[
0] == 2, "single channel requires binary model"
assert np.allclose(
np.sum(prob, axis=0), 1.0
), "single channel requires probabilities to sum up to one"
image = np.around(prob[1:, :, :]).astype(np.uint8).squeeze()
out = Image.fromarray(image, mode="P")
out.putpalette(palette)
os.makedirs(os.path.join(args.probs, str(z), str(x)),
exist_ok=True)
path = os.path.join(args.probs, str(z), str(x),
str(y) + ".png")
out.save(path, optimize=True)
if args.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.tiles)]
web_ui(args.probs, base_url, tiles, tiles, "png", template)
def main(args):
config = load_config(args.config)
num_classes = len(config["classes"])
batch_size = args.batch_size if args.batch_size else config["model"][
"batch_size"]
tile_size = args.tile_size if args.tile_size else config["model"][
"tile_size"]
if torch.cuda.is_available():
device = torch.device("cuda")
torch.backends.cudnn.benchmark = True
else:
device = torch.device("cpu")
def map_location(storage, _):
return storage.cuda() if torch.cuda.is_available() else storage.cpu()
# https://github.com/pytorch/pytorch/issues/7178
# chkpt = torch.load(args.checkpoint, map_location=map_location)
S3_CHECKPOINT = False
chkpt = args.checkpoint
if chkpt.startswith("s3://"):
S3_CHECKPOINT = True
# load from s3
chkpt = chkpt[5:]
models = [
name for _, name, _ in pkgutil.iter_modules(
[os.path.dirname(robosat_pink.models.__file__)])
]
if config["model"]["name"] not in [model for model in models]:
sys.exit("Unknown model, thoses available are {}".format(
[model for model in models]))
num_channels = 0
for channel in config["channels"]:
num_channels += len(channel["bands"])
pretrained = config["model"]["pretrained"]
encoder = config["model"]["encoder"]
model_module = import_module("robosat_pink.models.{}".format(
config["model"]["name"]))
net = getattr(model_module, "{}".format(config["model"]["name"].title()))(
num_classes=num_classes,
num_channels=num_channels,
encoder=encoder,
pretrained=pretrained).to(device)
net = torch.nn.DataParallel(net)
try:
if S3_CHECKPOINT:
sess = boto3.Session(profile_name=args.aws_profile)
fs = s3fs.S3FileSystem(session=sess)
with s3fs.S3File(fs, chkpt, 'rb') as C:
state = torch.load(io.BytesIO(C.read()),
map_location=map_location)
else:
state = torch.load(chkpt, map_location=map_location)
net.load_state_dict(state['state_dict'])
net.to(device)
except FileNotFoundError as f:
print("{} checkpoint not found.".format(CHECKPOINT))
net.eval()
#
# mean = np.array([[[8237.95084794]],
#
# [[6467.98702156]],
#
# [[6446.61743148]],
#
# [[4520.95360105]]])
# std = array([[[12067.03414753]],
#
# [[ 8810.00542703]],
#
# [[10710.64289882]],
#
# [[ 9024.92028515]]])
# #transform = Compose([ImageToTensor(), Normalize(mean=mean, std=std)])
# transform = A.Compose([
# A.Normalize(mean = mean, std = std, max_pixel_value = 1.0),
# A.ToFloat()
# ])
if args.tiles.startswith('s3://'):
directory = S3SlippyMapTiles(args.tiles,
mode='multibands',
transform=None,
aws_profile=args.aws_profile)
else:
directory = SlippyMapTiles(args.tiles,
mode="multibands",
transform=transform)
# directory = BufferedSlippyMapDirectory(args.tiles, transform=transform, size=tile_size, overlap=args.overlap)
loader = DataLoader(directory,
batch_size=batch_size,
num_workers=args.workers)
palette = make_palette(config["classes"][0]["color"])
# don't track tensors with autograd during prediction
with torch.no_grad():
for tiles, images in tqdm(loader,
desc="Eval",
unit="batch",
ascii=True):
tiles = list(zip(tiles[0], tiles[1], tiles[2]))
images = images.to(device)
outputs = net(images)
print(len(tiles), len(outputs))
for tile, prob in zip([tiles], outputs):
savedir = args.probs
x = tile[0].item()
y = tile[1].item()
z = tile[2].item()
# manually compute segmentation mask class probabilities per pixel
image = (prob > args.threshold).astype(np.uint8)
out = Image.fromarray(image, mode="P")
out.putpalette(palette)
os.makedirs(os.path.join(args.probs, str(z), str(x)),
exist_ok=True)
path = os.path.join(args.probs, str(z), str(x),
str(y) + ".png")
out.save(path, optimize=True)
if args.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.tiles)]
web_ui(args.probs, base_url, tiles, tiles, "png", template)
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):
config = load_config(args.config)
num_classes = len(config["classes"])
batch_size = args.batch_size if args.batch_size else config["model"]["batch_size"]
tile_size = config["model"]["tile_size"]
if torch.cuda.is_available():
device = torch.device("cuda")
torch.backends.cudnn.benchmark = True
else:
device = torch.device("cpu")
def map_location(storage, _):
return storage.cuda() if torch.cuda.is_available() else storage.cpu()
# check checkpoint situation + load if ncessary
chkpt = None # no checkpoint
if args.checkpoint: # command line checkpoint
chkpt = args.checkpoint
else:
try: # config file checkpoint
chkpt = config["checkpoint"]['path']
except:
# no checkpoint in config file
pass
S3_CHECKPOINT = False
if chkpt.startswith("s3://"):
S3_CHECKPOINT = True
# load from s3
chkpt = chkpt[5:]
models = [name for _, name, _ in pkgutil.iter_modules([os.path.dirname(robosat_pink.models.__file__)])]
if config["model"]["name"] not in [model for model in models]:
sys.exit("Unknown model, thoses available are {}".format([model for model in models]))
num_channels = 0
for channel in config["channels"]:
num_channels += len(channel["bands"])
pretrained = config["model"]["pretrained"]
encoder = config["model"]["encoder"]
model_module = import_module("robosat_pink.models.{}".format(config["model"]["name"]))
net = getattr(model_module, "{}".format(config["model"]["name"].title()))(
num_classes=num_classes, num_channels=num_channels, encoder=encoder, pretrained=pretrained
).to(device)
net = torch.nn.DataParallel(net)
try:
if S3_CHECKPOINT:
sess = boto3.Session(profile_name=args.aws_profile)
fs = s3fs.S3FileSystem(session=sess)
with s3fs.S3File(fs, chkpt, 'rb') as C:
state = torch.load(io.BytesIO(C.read()), map_location = map_location)
else:
state = torch.load(chkpt, map_location= map_location)
net.load_state_dict(state['state_dict'], strict=False)
net.to(device)
except FileNotFoundError as f:
print("{} checkpoint not found.".format(chkpt))
net.eval()
tile_ids_filter = None
if args.tile_ids is not None:
tile_ids_filter = pd.read_csv(args.tile_ids, names=['ids']).ids.values
## Construct torch Dataset, either from single directory (if args.tiles is given) or from config. Used --tile_ids argument
## to determine how to filter resulting tiles (e.g. to only run prediction on a test set)
if args.tiles is not None:
imagery_locs = [args.tiles]
# use tiledir provided
if args.tiles.startswith('s3://'):
allImageryDatasets = [S3SlippyMapTiles(args.tiles, mode='multibands', transform=None, aws_profile = args.aws_profile, ids = tile_ids_filter, buffered=args.buffer, buffered_overlap=args.buffer_overlap, tilesize=tile_size, bands=num_channels)]
else:
allImageryDatasets = [SlippyMapTiles(args.tiles, mode="multibands", transform = None)]
# directory = BufferedSlippyMapDirectory(args.tiles, transform=transform, size=tile_size,re overlap=args.overlap)
else: # use config to search for tiles
fs = s3fs.S3FileSystem(session = boto3.Session(profile_name = config['dataset']['aws_profile']))
p = pprint.PrettyPrinter()
imagery_searchpath = config['dataset']['image_bucket'] + '/' + config['dataset']['imagery_directory_regex']
print("Searching for imagery...({})".format(imagery_searchpath))
imagery_candidates = fs.ls(config['dataset']['image_bucket'])
print("candidates:")
p.pprint(imagery_candidates)
imagery_locs = [c for c in imagery_candidates if match(imagery_searchpath, c)]
print("result:")
p.pprint(imagery_locs)
allImageryDatasets = [
S3SlippyMapTiles("s3://" + loc, mode='multibands', transform=None, aws_profile=args.aws_profile, ids=tile_ids_filter)
for loc in imagery_locs
]
palette = make_palette(config["classes"][0]["color"])
# don't track tensors with autograd during prediction
with torch.no_grad():
for dataset, imageloc in zip(allImageryDatasets, imagery_locs):
print("Prediction: {}".format(imageloc))
imageloc_path = imageloc.replace("/", ":") # to not recreate directory structure when saving
loader = DataLoader(dataset, batch_size=batch_size, num_workers=args.workers)
for tiles, images in tqdm(loader, desc="Eval", unit="batch", ascii=True):
tiles = list(zip(tiles[0], tiles[1], tiles[2]))
images = images.to(device)
outputs = net(images)
for i, (tile, prob) in enumerate(zip(tiles, outputs)):
tile = Tile(tile[0].item(), tile[1].item(), tile[2].item())
savedir = args.preds
# manually compute segmentation mask class probabilities per pixel
image = (prob > args.threshold).cpu().numpy().astype(np.uint8)
if args.buffer:
image = allImageryDatasets[0].unbuffer(image)
image = image.squeeze()
_write_png(tile, image, os.path.join(savedir, imageloc_path), palette)
if(args.create_tif):
_write_tif(tile, image, os.path.join(savedir, imageloc_path))
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)
colors = [classe["color"] for classe in config["classes"]]
tile_size = args.tile_size
try:
raster = rasterio_open(args.raster)
w, s, e, n = bounds = transform_bounds(raster.crs, "EPSG:4326",
*raster.bounds)
transform, _, _ = calculate_default_transform(raster.crs, "EPSG:3857",
raster.width,
raster.height, *bounds)
except:
sys.exit("Error: Unable to load raster or deal with it's projection")
tiles = [
mercantile.Tile(x=x, y=y, z=z)
for x, y, z in mercantile.tiles(w, s, e, n, args.zoom)
]
tiles_nodata = []
for tile in tqdm(tiles, desc="Tiling", unit="tile", ascii=True):
w, s, e, n = tile_bounds = 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(*tile_bounds, args.size, args.size),
width=math.ceil((e - w) / transform.a),
height=math.ceil((s - n) / transform.e),
)
data = warp_vrt.read(out_shape=(len(raster.indexes), tile_size,
tile_size),
window=warp_vrt.window(w, s, e, n))
# If no_data is set, remove all tiles with at least one whole border filled only with no_data (on all bands)
if type(args.no_data) is not None and (
np.all(data[:, 0, :] == args.no_data)
or np.all(data[:, -1, :] == args.no_data)
or np.all(data[:, :, 0] == args.no_data)
or np.all(data[:, :, -1] == args.no_data)):
tiles_nodata.append(tile)
continue
C, W, H = data.shape
os.makedirs(os.path.join(args.out, str(args.zoom), str(tile.x)),
exist_ok=True)
path = os.path.join(args.out, str(args.zoom), str(tile.x), str(tile.y))
if args.type == "label":
assert C == 1, "Error: Label raster input should be 1 band"
ext = "png"
img = Image.fromarray(np.squeeze(data, axis=0), mode="P")
img.putpalette(make_palette(colors[0], colors[1]))
img.save("{}.{}".format(path, ext), optimize=True)
elif args.type == "image":
assert C == 1 or C == 3, "Error: Image raster input should be either 1 or 3 bands"
# GeoTiff could be 16 or 32bits
if data.dtype == "uint16":
data = np.uint8(data / 256)
elif data.dtype == "uint32":
data = np.uint8(data / (256 * 256))
if C == 1:
ext = "png"
Image.fromarray(np.squeeze(data, axis=0),
mode="L").save("{}.{}".format(path, ext),
optimize=True)
elif C == 3:
ext = "webp"
Image.fromarray(np.moveaxis(data, 0, 2),
mode="RGB").save("{}.{}".format(path, ext),
optimize=True)
if args.web_ui:
template = "leaflet.html" if not args.web_ui_template else args.web_ui_template
tiles = [tile for tile in tiles if tile not in tiles_nodata]
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):
config = load_config(args.config)
tile_size = args.tile_size if args.tile_size else config["model"]["tile_size"]
colors = [classe["color"] for classe in config["classes"]]
os.makedirs(args.out, exist_ok=True)
# We can only rasterize all tiles at a single zoom.
assert all(tile.z == args.zoom for tile in tiles_from_csv(args.cover))
# Find all tiles the features cover and make a map object for quick lookup.
feature_map = collections.defaultdict(list)
log = Logs(os.path.join(args.out, "log"), out=sys.stderr)
def parse_polygon(feature_map, polygon, i):
try:
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]])]
for tile in burntiles.burn([{"type": "feature", "geometry": polygon}], zoom=args.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 parse_geometry(feature_map, geometry, i):
if geometry["type"] == "Polygon":
feature_map = parse_polygon(feature_map, geometry, i)
elif geometry["type"] == "MultiPolygon":
for polygon in geometry["coordinates"]:
feature_map = parse_polygon(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
for feature in args.features:
with open(feature) as f:
fc = json.load(f)
for i, feature in enumerate(tqdm(fc["features"], ascii=True, unit="feature")):
if feature["geometry"]["type"] == "GeometryCollection":
for geometry in feature["geometry"]["geometries"]:
feature_map = parse_geometry(feature_map, geometry, i)
else:
feature_map = parse_geometry(feature_map, feature["geometry"], i)
# Burn features to tiles and write to a slippy map directory.
for tile in tqdm(list(tiles_from_csv(args.cover)), ascii=True, unit="tile"):
if tile in feature_map:
out = burn(tile, feature_map[tile], tile_size)
else:
out = np.zeros(shape=(tile_size, tile_size), dtype=np.uint8)
out_dir = os.path.join(args.out, str(tile.z), str(tile.x))
os.makedirs(out_dir, exist_ok=True)
out_path = os.path.join(out_dir, "{}.png".format(tile.y))
if os.path.exists(out_path):
prev = np.array(Image.open(out_path))
out = np.maximum(out, prev)
out = Image.fromarray(out, mode="P")
out_path = os.path.join(args.out, str(tile.z), str(tile.x))
os.makedirs(out_path, exist_ok=True)
out.putpalette(complementary_palette(make_palette(colors[0], colors[1])))
out.save(os.path.join(out_path, "{}.png".format(tile.y)), optimize=True)
if args.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)
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)