alessandro trinca tornidor
[chore] sync with samgis-be (pyproject.toml, PageLisaMap.vue), update HF space card title
5350122
raw
history blame
2.51 kB
from samgis import app_logger
from samgis.io.geo_helpers import get_vectorized_raster_as_geojson
from samgis.io.tms2geotiff import download_extent
from samgis.prediction_api.global_models import models_dict
from samgis.utilities.constants import DEFAULT_URL_TILES
from samgis_core.utilities.type_hints import llist_float, list_dict, dict_str_int
from lisa_on_cuda.utils import app_helpers
def lisa_predict(
bbox: llist_float,
prompt: str,
zoom: float,
inference_function_name_key: str = "lisa",
source: str = DEFAULT_URL_TILES
) -> dict_str_int:
"""
Return predictions as a geojson from a geo-referenced image using the given input prompt.
1. if necessary instantiate a segment anything machine learning instance model
2. download a geo-referenced raster image delimited by the coordinates bounding box (bbox)
3. get a prediction image from the segment anything instance model using the input prompt
4. get a geo-referenced geojson from the prediction image
Args:
bbox: coordinates bounding box
prompt: machine learning input prompt
zoom: Level of detail
inference_function_name_key: machine learning model name
source: xyz
Returns:
Affine transform
"""
app_logger.info("start lisa inference...")
if models_dict[inference_function_name_key]["inference"] is None:
app_logger.info(f"missing inference function {inference_function_name_key}, instantiating it now!")
parsed_args = app_helpers.parse_args([])
inference_fn = app_helpers.get_inference_model_by_args(parsed_args)
models_dict[inference_function_name_key]["inference"] = inference_fn
app_logger.debug(f"using a {inference_function_name_key} instance model...")
inference_fn = models_dict[inference_function_name_key]["inference"]
pt0, pt1 = bbox
app_logger.info(f"tile_source: {source}: downloading geo-referenced raster with bbox {bbox}, zoom {zoom}.")
img, transform = download_extent(w=pt1[1], s=pt1[0], e=pt0[1], n=pt0[0], zoom=zoom, source=source)
app_logger.info(
f"img type {type(img)} with shape/size:{img.size}, transform type: {type(transform)}, transform:{transform}.")
_, mask, output_string = inference_fn(prompt, img)
# app_logger.info(f"created {n_predictions} masks, preparing conversion to geojson...")
return {
"output_string": output_string,
**get_vectorized_raster_as_geojson(mask, transform)
}