feat: Add surface generation and media handling

- Implemented surface generation functionality in `surface.py`, including geometry estimation and texture writing.
- Introduced media input handling in `input.py`, supporting image and video frame extraction.
- Added model management for geometry adapters in `models/__init__.py`.
- Created BEN2 and DA3 model inference logic in `ben2.py` and `da3.py`, respectively.
- Developed ONNX model inference utilities for BEN2 and DA3 in `onnx_ben2.py` and `onnx_da3.py`.
- Added support for MoGe-2 model inference in `moge2.py` with necessary ONNX utilities.
- Implemented output handling for depth and surface data in `depth.py` and `surface.py`.
- Created debug output utilities for DA3 and MoGe-2 predictions in `debug_da3.py` and `debug_moge2.py`.
- Enhanced ONNX runtime session management in `onnx_runtime.py`.
- Updated `__init__.py` files to include new modules and functions for better organization.

tests/test_server.py

@@ -113,13 +113,13 @@ class ServerTest(unittest.TestCase):
     def test_ben2_model_is_reused_for_matching_runtime_key(self):
         loads = []
 
-        ben2 = ModuleType("server.onnx_ben2")
+        ben2 = ModuleType("server.models.onnx_ben2")
         ben2.create_session = lambda model_dir, device: (
             loads.append((model_dir, device)) or object()
         )
         cache = self.create_cache()
         device = SimpleNamespace(type="cuda")
-        with patch.dict(sys.modules, {"server.onnx_ben2": ben2}):
+        with patch.dict(sys.modules, {"server.models.onnx_ben2": ben2}):
             first, _load_ms = cache.get_ben2("model", device)
             second, cached_load_ms = cache.get_ben2("model", device)
 
@@ -131,7 +131,7 @@ class ServerTest(unittest.TestCase):
     def test_da3_model_is_reused_for_matching_runtime_key(self):
         loads = []
 
-        da3 = ModuleType("server.onnx_da3")
+        da3 = ModuleType("server.models.onnx_da3")
         da3.create_session = lambda model_dir, device: (
             loads.append((model_dir, device)) or object()
         )
@@ -140,7 +140,7 @@ class ServerTest(unittest.TestCase):
         with patch.dict(
             sys.modules,
             {
-                "server.onnx_da3": da3,
+                "server.models.onnx_da3": da3,
             },
         ):
             first = cache.get_da3("model", device)
@@ -172,9 +172,9 @@ class ServerTest(unittest.TestCase):
 
         moge = object()
 
-        fake_moge = ModuleType("server.onnx_moge2")
+        fake_moge = ModuleType("server.models.onnx_moge2")
         fake_moge.create_session = lambda _model_dir, _device: moge
-        with patch.dict(sys.modules, {"server.onnx_moge2": fake_moge}):
+        with patch.dict(sys.modules, {"server.models.onnx_moge2": fake_moge}):
             self.assertIs(cache.get_moge2("moge", "cuda"), moge)
 
         self.assertIsNone(cache.da3_model)
@@ -217,10 +217,8 @@ class ServerTest(unittest.TestCase):
                 "download-required-models",
                 "remove-background",
                 "extract-frames",
-                "generate-da3-depth",
-                "generate-moge2-depth",
-                "generate-da3-surface",
-                "generate-moge2-surface",
+                "generate-depth",
+                "generate-surface",
                 "debug-da3",
                 "debug-moge2",
                 "debug-ben2",
@@ -265,7 +263,17 @@ class ServerTest(unittest.TestCase):
             self.server_module, "ModelManager", return_value=fake_models
         ):
             server = self.create_server()
-        context = server.submit("remove-background", {}, job_id="job")
+        started = threading.Event()
+
+        @server.job("cancellable")
+        def cancellable(context, _parameters):
+            started.set()
+            while not context._is_cancelled():
+                time.sleep(0.001)
+            context.check_cancelled()
+
+        context = server.submit("cancellable", {}, job_id="job")
+        self.assertTrue(started.wait(1.0))
         self.assertIsNotNone(server.cancel("job"))
         self.assertTrue(context._is_cancelled())
         status = self.wait_for_job(context)