Making it installabel package and switching to segmentation mode

ARCHITECTURE.md

@@ -2,11 +2,11 @@
 
 ## Project Overview
 
-A desktop application for detecting organelles and membrane branching structures in microscopy images using YOLOv8s, with comprehensive training, validation, and visualization capabilities.
+A desktop application for detecting and segmenting organelles and membrane branching structures in microscopy images using YOLOv8s-seg, with comprehensive training, validation, and visualization capabilities including pixel-accurate segmentation masks.
 
 ## Technology Stack
 
-- **ML Framework**: Ultralytics YOLOv8 (YOLOv8s.pt model)
+- **ML Framework**: Ultralytics YOLOv8 (YOLOv8s-seg.pt segmentation model)
 - **GUI Framework**: PySide6 (Qt6 for Python)
 - **Visualization**: pyqtgraph
 - **Database**: SQLite3
@@ -110,6 +110,7 @@ erDiagram
         float x_max
         float y_max
         float confidence
+        text segmentation_mask
         datetime detected_at
         json metadata
     }
@@ -122,6 +123,7 @@ erDiagram
         float y_min
         float x_max
         float y_max
+        text segmentation_mask
         string annotator
         datetime created_at
         boolean verified
@@ -139,7 +141,7 @@ Stores information about trained models and their versions.
 | model_name | TEXT | NOT NULL | User-friendly model name |
 | model_version | TEXT | NOT NULL | Version string (e.g., "v1.0") |
 | model_path | TEXT | NOT NULL | Path to model weights file |
-| base_model | TEXT | NOT NULL | Base model used (e.g., "yolov8s.pt") |
+| base_model | TEXT | NOT NULL | Base model used (e.g., "yolov8s-seg.pt") |
 | created_at | TIMESTAMP | DEFAULT CURRENT_TIMESTAMP | Model creation timestamp |
 | training_params | JSON | | Training hyperparameters |
 | metrics | JSON | | Validation metrics (mAP, precision, recall) |
@@ -159,7 +161,7 @@ Stores metadata about microscopy images.
 | checksum | TEXT | | MD5 hash for integrity verification |
 
 #### **detections** table
-Stores object detection results.
+Stores object detection results with optional segmentation masks.
 
 | Column | Type | Constraints | Description |
 |--------|------|-------------|-------------|
@@ -172,11 +174,12 @@ Stores object detection results.
 | x_max | REAL | NOT NULL | Bounding box right coordinate (normalized 0-1) |
 | y_max | REAL | NOT NULL | Bounding box bottom coordinate (normalized 0-1) |
 | confidence | REAL | NOT NULL | Detection confidence score (0-1) |
+| segmentation_mask | TEXT | | JSON array of polygon coordinates [[x1,y1], [x2,y2], ...] (normalized 0-1) |
 | detected_at | TIMESTAMP | DEFAULT CURRENT_TIMESTAMP | When detection was performed |
 | metadata | JSON | | Additional metadata (processing time, etc.) |
 
 #### **annotations** table
-Stores manual annotations for training data (future feature).
+Stores manual annotations for training data with optional segmentation masks (future feature).
 
 | Column | Type | Constraints | Description |
 |--------|------|-------------|-------------|
@@ -187,6 +190,7 @@ Stores manual annotations for training data (future feature).
 | y_min | REAL | NOT NULL | Bounding box top coordinate (normalized) |
 | x_max | REAL | NOT NULL | Bounding box right coordinate (normalized) |
 | y_max | REAL | NOT NULL | Bounding box bottom coordinate (normalized) |
+| segmentation_mask | TEXT | | JSON array of polygon coordinates [[x1,y1], [x2,y2], ...] (normalized 0-1) |
 | annotator | TEXT | | Name of person who created annotation |
 | created_at | TIMESTAMP | DEFAULT CURRENT_TIMESTAMP | Annotation timestamp |
 | verified | BOOLEAN | DEFAULT 0 | Whether annotation is verified |
@@ -245,8 +249,9 @@ graph TB
 ### Key Components
 
 #### 1. **YOLO Wrapper** ([`src/model/yolo_wrapper.py`](src/model/yolo_wrapper.py))
-Encapsulates YOLOv8 operations:
-- Load pre-trained YOLOv8s model
+Encapsulates YOLOv8-seg operations:
+- Load pre-trained YOLOv8s-seg segmentation model
+- Extract pixel-accurate segmentation masks
 - Fine-tune on custom microscopy dataset
 - Export trained models
 - Provide training progress callbacks
@@ -255,10 +260,10 @@ Encapsulates YOLOv8 operations:
 **Key Methods:**
 ```python
 class YOLOWrapper:
-    def __init__(self, model_path: str = "yolov8s.pt")
+    def __init__(self, model_path: str = "yolov8s-seg.pt")
     def train(self, data_yaml: str, epochs: int, callbacks: dict)
     def validate(self, data_yaml: str) -> dict
-    def predict(self, image_path: str, conf: float) -> list
+    def predict(self, image_path: str, conf: float) -> list  # Returns detections with segmentation masks
     def export_model(self, format: str, output_path: str)
 ```
 
@@ -435,7 +440,7 @@ image_repository:
   allowed_extensions: [".jpg", ".jpeg", ".png", ".tif", ".tiff"]
 
 models:
-  default_base_model: "yolov8s.pt"
+  default_base_model: "yolov8s-seg.pt"
   models_directory: "data/models"
 
 training: