Remove obsolete implementation and simplify project structure

src/anyimage/server/models/da3.py

@@ -0,0 +1,94 @@
+from ..geometry import unproject_camera_depth
+from ..geometry import GeometryFrame
+
+
+def merge_frame_predictions(predictions):
+    import numpy as np
+
+    if not predictions:
+        raise ValueError("DA3 returned no frame predictions")
+    merged = predictions[0]
+    for name in (
+        "depth",
+        "conf",
+        "extrinsics",
+        "intrinsics",
+        "processed_images",
+    ):
+        setattr(
+            merged,
+            name,
+            np.concatenate(
+                [getattr(prediction, name) for prediction in predictions],
+                axis=0,
+            ),
+        )
+    return merged
+
+
+def infer(
+    model_manager,
+    parameters,
+    images,
+    *,
+    progress_callback=None,
+    cancel_check=None,
+):
+    from .onnx_da3 import infer as infer_onnx
+    from .onnx_runtime import provider_label
+
+    model_directory = model_manager.directory(parameters["model"])
+    device = parameters["device"]
+    model = model_manager.get_da3(model_directory, device)
+    options = {
+        "process_res": parameters["process_res"],
+        "process_res_method": parameters["process_res_method"],
+        "ref_view_strategy": parameters["ref_view_strategy"],
+    }
+
+    def run(paths):
+        try:
+            return infer_onnx(model, paths, **options)
+        except UnicodeDecodeError as error:
+            if provider_label(model) == "DirectML":
+                raise RuntimeError(
+                    "DA3 inference failed on DirectML. Switch the device to "
+                    "CPU in AnyImage Preferences and retry. "
+                    f"Original error: {error}"
+                ) from error
+            raise
+
+    if parameters.get("inference_mode", "joint") != "per_frame":
+        return run([str(path) for path in images])
+
+    predictions = []
+    for index, image in enumerate(images):
+        if cancel_check is not None:
+            cancel_check()
+        if progress_callback is not None:
+            progress_callback(index, len(images))
+        predictions.append(run([str(image)]))
+    return merge_frame_predictions(predictions)
+
+
+def surface_frame(prediction):
+    import numpy as np
+
+    depth = np.asarray(prediction.depth, dtype=np.float32)
+    confidence = np.asarray(prediction.conf, dtype=np.float32)
+    intrinsics = np.asarray(prediction.intrinsics, dtype=np.float32)
+    if depth.shape[0] != 1:
+        raise ValueError("Convert to Surface currently supports one image")
+    points = unproject_camera_depth(depth[0], intrinsics[0])
+    valid = (
+        np.isfinite(depth[0])
+        & (depth[0] > 0.0)
+        & np.isfinite(points).all(axis=-1)
+    )
+    return GeometryFrame(
+        depth=depth[0],
+        points=points,
+        intrinsics=intrinsics[0],
+        valid_mask=valid,
+        confidence=confidence[0],
+    )