combine stac_model and pystac metadata

best-practices.md

@@ -2,6 +2,10 @@
 
 This document makes a number of recommendations for creating real world ML Model Extensions. None of them are required to meet the core specification, but following these practices will improve the documentation of your model and make life easier for client tooling and users. They come about from practical experience of implementors and introduce a bit more 'constraint' for those who are creating STAC objects representing their models or creating tools to work with STAC.
 
+## Using STAC Common Metadata Fields for the ML Model Extension
+
+We recommend using the `start_datetime` and `end_datetime`, `geometry`, and `bbox` to represent the recommended context of data the model was trained with and for which the model should have appropriate domain knowledge for inference. For example, we can consider a model which is trained on imagery from all over the world and is robust enough to be applied to any time period. In this case, the common metadata to use with the model would include the bbox of "the world" `[-90, -180, 90, 180]` and the start_datetime and end_datetime range could be generic values like `["1900-01-01", null]`.
+
 ## Recommended Extensions to Compose with the ML Model Extension
 
 ### Processing Extension

pyproject.toml

@@ -57,8 +57,7 @@ typer = {extras = ["all"], version = "^0.9.0"}
 rich = "^13.7.0"
 pydantic = "2.3" # bug in post 2.3 https://github.com/pydantic/pydantic/issues/7720
 pydantic-core = "^2"
-numpy = "^1.26.2"
-# fastapi="^0.108.0"
+pystac = "^1.9.0"
 
 
 [tool.poetry.group.dev.dependencies]

stac_model/examples.py

@@ -2,7 +2,7 @@
     Asset,
     ClassObject,
     InputArray,
-    MLModel,
+    MLModelExtension,
     ModelInput,
     ModelOutput,
     ResultArray,
@@ -112,7 +112,7 @@ def eurosat_resnet():
         output_shape=[-1, 10],
         result_array=[result_array],
     )
-    ml_model_meta = MLModel(
+    ml_model_meta = MLModelExtension(
         mlm_name="Resnet-18 Sentinel-2 ALL MOCO",
         mlm_task="classification",
         mlm_framework="pytorch",

stac_model/geometry_models.py

@@ -0,0 +1,39 @@
+from typing import List, Literal, Union
+
+from pydantic import (
+    BaseModel,
+)
+
+
+class Geometry(BaseModel):
+    type: str
+    coordinates: List
+
+
+class GeoJSONPoint(Geometry):
+    type: Literal["Point"]
+    coordinates: List[float]
+
+
+class GeoJSONMultiPoint(Geometry):
+    type: Literal["MultiPoint"]
+    coordinates: List[List[float]]
+
+
+class GeoJSONPolygon(Geometry):
+    type: Literal["Polygon"]
+    coordinates: List[List[List[float]]]
+
+
+class GeoJSONMultiPolygon(Geometry):
+    type: Literal["MultiPolygon"]
+    coordinates: List[List[List[List[float]]]]
+
+
+AnyGeometry = Union[
+    Geometry,
+    GeoJSONPoint,
+    GeoJSONMultiPoint,
+    GeoJSONPolygon,
+    GeoJSONMultiPolygon,
+]