refactor(pipeline): integrate SAM segmentation and modularize model loading

mini-nav/tests/test_compressors.py

@@ -2,6 +2,7 @@
 
 import pytest
 import torch
+from unittest.mock import Mock, patch
 from compressors import (
     BinarySign,
     HashCompressor,
@@ -205,18 +206,54 @@ class TestVideoPositiveMask:
 class TestHashPipeline:
     """Test suite for HashPipeline."""
 
-    def test_pipeline_init(self):
+    @patch("compressors.pipeline.load_sam_model")
+    @patch("compressors.pipeline.AutoModel.from_pretrained")
+    @patch("compressors.pipeline.AutoImageProcessor.from_pretrained")
+    def test_pipeline_init(
+        self,
+        mock_processor_from_pretrained,
+        mock_model_from_pretrained,
+        mock_load_sam_model,
+    ):
         """Verify pipeline initializes all components."""
+        mock_processor_from_pretrained.return_value = Mock()
+
+        mock_model = Mock()
+        mock_model.to.return_value = mock_model
+        mock_model.eval.return_value = None
+        mock_model_from_pretrained.return_value = mock_model
+
+        mock_load_sam_model.return_value = (Mock(), Mock())
+
         pipeline = HashPipeline(
             dino_model="facebook/dinov2-large",
             hash_bits=512,
         )
 
         assert pipeline.dino_model == "facebook/dinov2-large"
+        assert pipeline.sam_model_name == "facebook/sam2.1-hiera-large"
         assert pipeline.dino_dim == 1024
+        mock_load_sam_model.assert_called_once()
 
-    def test_pipeline_hash_bits(self):
+    @patch("compressors.pipeline.load_sam_model")
+    @patch("compressors.pipeline.AutoModel.from_pretrained")
+    @patch("compressors.pipeline.AutoImageProcessor.from_pretrained")
+    def test_pipeline_hash_bits(
+        self,
+        mock_processor_from_pretrained,
+        mock_model_from_pretrained,
+        mock_load_sam_model,
+    ):
         """Verify pipeline uses correct hash bits."""
+        mock_processor_from_pretrained.return_value = Mock()
+
+        mock_model = Mock()
+        mock_model.to.return_value = mock_model
+        mock_model.eval.return_value = None
+        mock_model_from_pretrained.return_value = mock_model
+
+        mock_load_sam_model.return_value = (Mock(), Mock())
+
         pipeline = HashPipeline(hash_bits=256)
         assert pipeline.hash_bits == 256
 
@@ -228,14 +265,33 @@ class TestHashPipeline:
 class TestConfigIntegration:
     """Test suite for config integration with pipeline."""
 
-    def test_create_pipeline_from_config(self):
+    @patch("compressors.pipeline.load_sam_model")
+    @patch("compressors.pipeline.AutoModel.from_pretrained")
+    @patch("compressors.pipeline.AutoImageProcessor.from_pretrained")
+    def test_create_pipeline_from_config(
+        self,
+        mock_processor_from_pretrained,
+        mock_model_from_pretrained,
+        mock_load_sam_model,
+    ):
         """Verify pipeline can be created from config."""
+        mock_processor_from_pretrained.return_value = Mock()
+
+        mock_model = Mock()
+        mock_model.to.return_value = mock_model
+        mock_model.eval.return_value = None
+        mock_model_from_pretrained.return_value = mock_model
+
+        mock_load_sam_model.return_value = (Mock(), Mock())
+
         config = cfg_manager.load()
 
         pipeline = create_pipeline_from_config(config)
 
         assert isinstance(pipeline, HashPipeline)
         assert pipeline.hash_bits == config.model.compression_dim
+        assert pipeline.sam_max_masks == config.model.sam_max_masks
+        assert pipeline.sam_min_mask_area == config.model.sam_min_mask_area
 
     def test_config_settings(self):
         """Verify config contains required settings."""

mini-nav/tests/test_sam.py

@@ -97,9 +97,21 @@ class TestSAMSegmentation:
         from utils.sam import segment_image
 
         # Create masks with known areas (unordered)
-        mask1 = {"segment": np.ones((5, 5), dtype=bool), "area": 25, "bbox": [0, 0, 5, 5]}
-        mask2 = {"segment": np.ones((10, 10), dtype=bool), "area": 100, "bbox": [0, 0, 10, 10]}
-        mask3 = {"segment": np.ones((3, 3), dtype=bool), "area": 9, "bbox": [0, 0, 3, 3]}
+        mask1 = {
+            "segment": np.ones((5, 5), dtype=bool),
+            "area": 25,
+            "bbox": [0, 0, 5, 5],
+        }
+        mask2 = {
+            "segment": np.ones((10, 10), dtype=bool),
+            "area": 100,
+            "bbox": [0, 0, 10, 10],
+        }
+        mask3 = {
+            "segment": np.ones((3, 3), dtype=bool),
+            "area": 9,
+            "bbox": [0, 0, 3, 3],
+        }
 
         mock_generator = Mock()
         mock_generator.generate.return_value = [mask1, mask2, mask3]
@@ -117,6 +129,31 @@ class TestSAMSegmentation:
         assert result[2]["area"] == 9
 
 
+class TestSAMLoading:
+    @patch("utils.sam.pipeline")
+    def test_load_sam_model_uses_transformers_pipeline(self, mock_pipeline):
+        from utils.sam import Sam2MaskGenerator, load_sam_model
+
+        mock_pipe_obj = Mock()
+        mock_pipe_obj.model = Mock()
+        mock_pipeline.return_value = mock_pipe_obj
+
+        sam_model, mask_generator = load_sam_model(
+            model_name="facebook/sam2.1-hiera-large",
+            device="cpu",
+            points_per_batch=16,
+        )
+
+        assert sam_model is mock_pipe_obj.model
+        assert isinstance(mask_generator, Sam2MaskGenerator)
+        assert mask_generator.points_per_batch == 16
+
+        _, kwargs = mock_pipeline.call_args
+        assert kwargs["task"] == "mask-generation"
+        assert kwargs["model"] == "facebook/sam2.1-hiera-large"
+        assert kwargs["device"] == -1
+
+
 class TestExtractMaskedRegion:
     """Test suite for extracting masked regions from images."""