PyPI - lazylabel-gui - Versions diffs - 1.3.5__tar.gz → 1.3.6__tar.gz - Mend

lazylabel-gui 1.3.5tar.gz → 1.3.6tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (61) hide show

{lazylabel_gui-1.3.5/src/lazylabel_gui.egg-info → lazylabel_gui-1.3.6}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lazylabel-gui
-Version: 1.3.5
+Version: 1.3.6
 Summary: An image segmentation GUI for generating ML ready mask tensors and annotations.
 Author-email: "Deniz N. Cakan" <deniz.n.cakan@gmail.com>
 License: MIT License
@@ -53,17 +53,24 @@ Requires-Dist: pytest-qt>=4.2.0; extra == "dev"
 Requires-Dist: ruff>=0.8.0; extra == "dev"
 Dynamic: license-file
-# <img src="https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/logo2.png" alt="LazyLabel Logo" style="height:60px; vertical-align:middle;" /> <img src="https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/logo_black.png" alt="LazyLabel Cursive" style="height:60px; vertical-align:middle;" />
+# LazyLabel
-**AI-Assisted Image Segmentation Made Simple**
+<div align="center">
+  <img src="https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/logo2.png" alt="LazyLabel Logo" style="height:60px; vertical-align:middle;" />
+  <img src="https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/logo_black.png" alt="LazyLabel Cursive" style="height:60px; vertical-align:middle;" />
+</div>
-LazyLabel combines Meta's Segment Anything Model (SAM) with intuitive editing tools for fast, precise image labeling. Perfect for machine learning datasets and computer vision research.
+**AI-Assisted Image Segmentation for Machine Learning Applications**
-![LazyLabel Screenshot](https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/gui.PNG)
+LazyLabel integrates Meta's Segment Anything Model (SAM) with advanced editing capabilities to enable efficient, high-precision image annotation. Designed for computer vision research and machine learning dataset preparation.
+<div align="center">
+  <img src="https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/gui.PNG" alt="LazyLabel Screenshot" width="800"/>
+</div>
 ---
-## 🚀 Quick Start
+## Quick Start
 ### Installation
 ```bash
@@ -71,38 +78,38 @@ pip install lazylabel-gui
 lazylabel-gui
 ```
-### Optional: SAM-2 Support
-For advanced SAM-2 models, install manually:
+### Optional: SAM 2.1 Support
+For enhanced performance with SAM 2.1 models:
 ```bash
 pip install git+https://github.com/facebookresearch/sam2.git
 ```
-*Note: SAM-2 is optional - LazyLabel works with SAM 1.0 models by default*
+**Note:** SAM 2.1 is optional - LazyLabel downloads SAM 1.0 models by default.
 ### Usage
-1. **Open Folder** → Select your image directory
-2. **Click on image** → AI generates instant masks
-3. **Fine-tune** → Edit polygons, merge segments
-4. **Export** → Clean `.npz` files ready for ML training
+1. **Open Folder** - Select your image directory
+2. **AI Segmentation** - Click on objects for automatic mask generation
+3. **Manual Refinement** - Edit polygons, merge segments, adjust classifications
+4. **Export** - Generate `.npz` files with one-hot encoded masks for ML training
 ---
-## ✨ Key Features
+## Key Features
-- **🧠 One-click AI segmentation** with Meta's SAM and SAM2 models
-- **🎨 Manual polygon drawing** with full vertex control
-- **⚡ Smart editing tools** - merge segments, adjust class names, and class order
-- **📊 ML-ready exports** - One-hot encoded `.npz` format and `.json` for YOLO format
-- **🔧 Image enhancement** - brightness, contrast, gamma adjustment
-- **🔍 Image viewer** - zoom, pan, brightness, contrast, and gamma adjustment
-- **✂️ Edge cropping** - define custom crop areas to focus on specific regions
-- **🔄 Undo/Redo** - full history of all actions
-- **💾 Auto-saving** - Automatic saving of your labels when navigating between images
-- **🎛️ Advanced filtering** - FFT thresholding and color channel thresholding
-- **⌨️ Customizable hotkeys** for all functions
+- **One-click AI segmentation** with Meta's SAM and SAM 2.1 models
+- **Manual polygon drawing** with full vertex control
+- **Smart editing tools** - merge segments, adjust class names, and class order
+- **ML-ready exports** - One-hot encoded `.npz` format and `.json` for YOLO format
+- **Image enhancement** - brightness, contrast, gamma adjustment
+- **Advanced image viewer** - zoom, pan, and real-time adjustments
+- **Edge cropping** - define custom crop areas to focus on specific regions
+- **Undo/Redo system** - full history of all actions
+- **Auto-saving** - automatic saving of labels when navigating between images
+- **Advanced filtering** - FFT thresholding and color channel thresholding
+- **Customizable hotkeys** for all functions
 ---
-## ⌨️ Essential Hotkeys
+## Essential Hotkeys
 | Action | Key | Description |
 |--------|-----|-------------|
@@ -115,13 +122,13 @@ pip install git+https://github.com/facebookresearch/sam2.git
 | **Positive Point** | `Left Click` | Add to segment |
 | **Negative Point** | `Right Click` | Remove from segment |
-💡 **All hotkeys customizable** - Click "Hotkeys" button to personalize
+**Note:** All hotkeys are fully customizable - Click "Hotkeys" button to personalize your workflow.
 ---
-## 📦 Output Format
+## Output Format
-Perfect for ML training - clean, structured data:
+LazyLabel exports data in standardized formats optimized for machine learning workflows:
 ```python
 import numpy as np
@@ -145,10 +152,9 @@ class_2_mask = mask[:, :, 2]  # Object type 2
 ---
-## 🛠️ Development
+## Development
-**Requirements:** Python 3.10+
-**2.5GB** disk space for SAM model (auto-downloaded)
+**Requirements:** Python 3.10+, ~2.5GB disk space for SAM models (auto-downloaded)
 ### Installation from Source
 ```bash
@@ -160,35 +166,32 @@ lazylabel-gui
 ### Testing & Quality
 ```bash
-# Run full test suite
-python -m pytest --cov=lazylabel --cov-report=html
+# Run test suite (272 tests)
+pytest --tb=short
-# Code formatting & linting
-ruff check . && ruff format .
+# Code quality checks
+ruff check --fix src/
 ```
 ### Architecture
 - **Modular design** with clean component separation
-- **Signal-based communication** between UI elements
-- **Extensible model system** for new SAM variants
-- **Comprehensive test suite** (150+ tests, 60%+ coverage)
+- **Signal-based communication** between UI elements
+- **Extensible model system** for SAM 1.0 and SAM 2.1 variants
+- **Comprehensive test suite** (272 tests with extensive coverage)
+- **Multi-view support** for simultaneous image processing
 ---
-## 🤝 Contributing
+## Contributing
-LazyLabel welcomes contributions! Check out:
-- [Architecture Guide](src/lazylabel/ARCHITECTURE.md) for technical details
-- [Hotkey System](src/lazylabel/HOTKEY_FEATURE.md) for customization
-- Issues page for feature requests and bug reports
+LazyLabel welcomes contributions! Please review:
+- [Usage Manual](src/lazylabel/USAGE_MANUAL.md) for comprehensive user documentation
+- [Architecture Guide](src/lazylabel/ARCHITECTURE.md) for technical implementation details
+- [Issues page](https://github.com/dnzckn/LazyLabel/issues) for feature requests and bug reports
 ---
-## 🙏 Acknowledgments
+## Acknowledgments
 - [LabelMe](https://github.com/wkentaro/labelme)
 - [Segment-Anything-UI](https://github.com/branislavhesko/segment-anything-ui)
----
-**Made with ❤️ for the computer vision community**

lazylabel_gui-1.3.6/README.md ADDED Viewed

@@ -0,0 +1,142 @@
+# LazyLabel
+<div align="center">
+  <img src="https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/logo2.png" alt="LazyLabel Logo" style="height:60px; vertical-align:middle;" />
+  <img src="https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/logo_black.png" alt="LazyLabel Cursive" style="height:60px; vertical-align:middle;" />
+</div>
+**AI-Assisted Image Segmentation for Machine Learning Applications**
+LazyLabel integrates Meta's Segment Anything Model (SAM) with advanced editing capabilities to enable efficient, high-precision image annotation. Designed for computer vision research and machine learning dataset preparation.
+<div align="center">
+  <img src="https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/gui.PNG" alt="LazyLabel Screenshot" width="800"/>
+</div>
+---
+## Quick Start
+### Installation
+```bash
+pip install lazylabel-gui
+lazylabel-gui
+```
+### Optional: SAM 2.1 Support
+For enhanced performance with SAM 2.1 models:
+```bash
+pip install git+https://github.com/facebookresearch/sam2.git
+```
+**Note:** SAM 2.1 is optional - LazyLabel downloads SAM 1.0 models by default.
+### Usage
+1. **Open Folder** - Select your image directory
+2. **AI Segmentation** - Click on objects for automatic mask generation
+3. **Manual Refinement** - Edit polygons, merge segments, adjust classifications
+4. **Export** - Generate `.npz` files with one-hot encoded masks for ML training
+---
+## Key Features
+- **One-click AI segmentation** with Meta's SAM and SAM 2.1 models
+- **Manual polygon drawing** with full vertex control
+- **Smart editing tools** - merge segments, adjust class names, and class order
+- **ML-ready exports** - One-hot encoded `.npz` format and `.json` for YOLO format
+- **Image enhancement** - brightness, contrast, gamma adjustment
+- **Advanced image viewer** - zoom, pan, and real-time adjustments
+- **Edge cropping** - define custom crop areas to focus on specific regions
+- **Undo/Redo system** - full history of all actions
+- **Auto-saving** - automatic saving of labels when navigating between images
+- **Advanced filtering** - FFT thresholding and color channel thresholding
+- **Customizable hotkeys** for all functions
+---
+## Essential Hotkeys
+| Action | Key | Description |
+|--------|-----|-------------|
+| **AI Mode** | `1` | Point-click segmentation |
+| **Draw Mode** | `2` | Manual polygon drawing |
+| **Edit Mode** | `E` | Select and modify shapes |
+| **Save Segment** | `Space` | Confirm current mask |
+| **Merge** | `M` | Combine selected segments |
+| **Pan** | `Q` + drag | Navigate large images |
+| **Positive Point** | `Left Click` | Add to segment |
+| **Negative Point** | `Right Click` | Remove from segment |
+**Note:** All hotkeys are fully customizable - Click "Hotkeys" button to personalize your workflow.
+---
+## Output Format
+LazyLabel exports data in standardized formats optimized for machine learning workflows:
+```python
+import numpy as np
+# Load your labeled data
+data = np.load('your_image.npz')
+mask = data['mask']  # Shape: (height, width, num_classes)
+# Each channel is a binary mask for one class
+class_0_mask = mask[:, :, 0]  # Background
+class_1_mask = mask[:, :, 1]  # Object type 1
+class_2_mask = mask[:, :, 2]  # Object type 2
+```
+**Ideal for:**
+- Semantic segmentation datasets
+- Instance segmentation training
+- Computer vision research
+- Automated annotation pipelines
+---
+## Development
+**Requirements:** Python 3.10+, ~2.5GB disk space for SAM models (auto-downloaded)
+### Installation from Source
+```bash
+git clone https://github.com/dnzckn/LazyLabel.git
+cd LazyLabel
+pip install -e .
+lazylabel-gui
+```
+### Testing & Quality
+```bash
+# Run test suite (272 tests)
+pytest --tb=short
+# Code quality checks
+ruff check --fix src/
+```
+### Architecture
+- **Modular design** with clean component separation
+- **Signal-based communication** between UI elements
+- **Extensible model system** for SAM 1.0 and SAM 2.1 variants
+- **Comprehensive test suite** (272 tests with extensive coverage)
+- **Multi-view support** for simultaneous image processing
+---
+## Contributing
+LazyLabel welcomes contributions! Please review:
+- [Usage Manual](src/lazylabel/USAGE_MANUAL.md) for comprehensive user documentation
+- [Architecture Guide](src/lazylabel/ARCHITECTURE.md) for technical implementation details
+- [Issues page](https://github.com/dnzckn/LazyLabel/issues) for feature requests and bug reports
+---
+## Acknowledgments
+- [LabelMe](https://github.com/wkentaro/labelme)
+- [Segment-Anything-UI](https://github.com/branislavhesko/segment-anything-ui)

{lazylabel_gui-1.3.5 → lazylabel_gui-1.3.6}/pyproject.toml RENAMED Viewed

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 [project]
 name = "lazylabel-gui"
-version = "1.3.5"
+version = "1.3.6"
 authors = [
   { name="Deniz N. Cakan", email="deniz.n.cakan@gmail.com" },
 ]

{lazylabel_gui-1.3.5 → lazylabel_gui-1.3.6}/src/lazylabel/ui/widgets/channel_threshold_widget.py RENAMED Viewed

@@ -372,6 +372,7 @@ class ChannelThresholdWidget(QWidget):
         super().__init__(parent)
         self.current_image_channels = 0  # 0 = no image, 1 = grayscale, 3 = RGB
         self.sliders = {}  # Dictionary of channel name -> slider
+        self.is_dragging = False  # Track if any slider is being dragged
         self.setupUI()
@@ -434,10 +435,8 @@ class ChannelThresholdWidget(QWidget):
         for channel_name in channel_names:
             slider_widget = ChannelSliderWidget(channel_name, self)
             slider_widget.valueChanged.connect(self._on_slider_changed)
-            slider_widget.dragStarted.connect(
-                self.dragStarted.emit
-            )  # Forward drag signals
-            slider_widget.dragFinished.connect(self.dragFinished.emit)
+            slider_widget.dragStarted.connect(self._on_drag_started)
+            slider_widget.dragFinished.connect(self._on_drag_finished)
             self.sliders[channel_name] = slider_widget
             self.sliders_layout.addWidget(slider_widget)
@@ -450,6 +449,21 @@ class ChannelThresholdWidget(QWidget):
     def _on_slider_changed(self):
         """Handle slider value change."""
+        # Only emit thresholdChanged if not currently dragging
+        # This prevents expensive calculations during drag operations
+        if not self.is_dragging:
+            self.thresholdChanged.emit()
+    def _on_drag_started(self):
+        """Handle drag start - suppress expensive calculations during drag."""
+        self.is_dragging = True
+        self.dragStarted.emit()
+    def _on_drag_finished(self):
+        """Handle drag finish - perform final calculation."""
+        self.is_dragging = False
+        self.dragFinished.emit()
+        # Emit threshold changed now that dragging is complete
         self.thresholdChanged.emit()
     def get_threshold_settings(self):

{lazylabel_gui-1.3.5 → lazylabel_gui-1.3.6/src/lazylabel_gui.egg-info}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lazylabel-gui
-Version: 1.3.5
+Version: 1.3.6
 Summary: An image segmentation GUI for generating ML ready mask tensors and annotations.
 Author-email: "Deniz N. Cakan" <deniz.n.cakan@gmail.com>
 License: MIT License
@@ -53,17 +53,24 @@ Requires-Dist: pytest-qt>=4.2.0; extra == "dev"
 Requires-Dist: ruff>=0.8.0; extra == "dev"
 Dynamic: license-file
-# <img src="https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/logo2.png" alt="LazyLabel Logo" style="height:60px; vertical-align:middle;" /> <img src="https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/logo_black.png" alt="LazyLabel Cursive" style="height:60px; vertical-align:middle;" />
+# LazyLabel
-**AI-Assisted Image Segmentation Made Simple**
+<div align="center">
+  <img src="https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/logo2.png" alt="LazyLabel Logo" style="height:60px; vertical-align:middle;" />
+  <img src="https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/logo_black.png" alt="LazyLabel Cursive" style="height:60px; vertical-align:middle;" />
+</div>
-LazyLabel combines Meta's Segment Anything Model (SAM) with intuitive editing tools for fast, precise image labeling. Perfect for machine learning datasets and computer vision research.
+**AI-Assisted Image Segmentation for Machine Learning Applications**
-![LazyLabel Screenshot](https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/gui.PNG)
+LazyLabel integrates Meta's Segment Anything Model (SAM) with advanced editing capabilities to enable efficient, high-precision image annotation. Designed for computer vision research and machine learning dataset preparation.
+<div align="center">
+  <img src="https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/gui.PNG" alt="LazyLabel Screenshot" width="800"/>
+</div>
 ---
-## 🚀 Quick Start
+## Quick Start
 ### Installation
 ```bash
@@ -71,38 +78,38 @@ pip install lazylabel-gui
 lazylabel-gui
 ```
-### Optional: SAM-2 Support
-For advanced SAM-2 models, install manually:
+### Optional: SAM 2.1 Support
+For enhanced performance with SAM 2.1 models:
 ```bash
 pip install git+https://github.com/facebookresearch/sam2.git
 ```
-*Note: SAM-2 is optional - LazyLabel works with SAM 1.0 models by default*
+**Note:** SAM 2.1 is optional - LazyLabel downloads SAM 1.0 models by default.
 ### Usage
-1. **Open Folder** → Select your image directory
-2. **Click on image** → AI generates instant masks
-3. **Fine-tune** → Edit polygons, merge segments
-4. **Export** → Clean `.npz` files ready for ML training
+1. **Open Folder** - Select your image directory
+2. **AI Segmentation** - Click on objects for automatic mask generation
+3. **Manual Refinement** - Edit polygons, merge segments, adjust classifications
+4. **Export** - Generate `.npz` files with one-hot encoded masks for ML training
 ---
-## ✨ Key Features
+## Key Features
-- **🧠 One-click AI segmentation** with Meta's SAM and SAM2 models
-- **🎨 Manual polygon drawing** with full vertex control
-- **⚡ Smart editing tools** - merge segments, adjust class names, and class order
-- **📊 ML-ready exports** - One-hot encoded `.npz` format and `.json` for YOLO format
-- **🔧 Image enhancement** - brightness, contrast, gamma adjustment
-- **🔍 Image viewer** - zoom, pan, brightness, contrast, and gamma adjustment
-- **✂️ Edge cropping** - define custom crop areas to focus on specific regions
-- **🔄 Undo/Redo** - full history of all actions
-- **💾 Auto-saving** - Automatic saving of your labels when navigating between images
-- **🎛️ Advanced filtering** - FFT thresholding and color channel thresholding
-- **⌨️ Customizable hotkeys** for all functions
+- **One-click AI segmentation** with Meta's SAM and SAM 2.1 models
+- **Manual polygon drawing** with full vertex control
+- **Smart editing tools** - merge segments, adjust class names, and class order
+- **ML-ready exports** - One-hot encoded `.npz` format and `.json` for YOLO format
+- **Image enhancement** - brightness, contrast, gamma adjustment
+- **Advanced image viewer** - zoom, pan, and real-time adjustments
+- **Edge cropping** - define custom crop areas to focus on specific regions
+- **Undo/Redo system** - full history of all actions
+- **Auto-saving** - automatic saving of labels when navigating between images
+- **Advanced filtering** - FFT thresholding and color channel thresholding
+- **Customizable hotkeys** for all functions
 ---
-## ⌨️ Essential Hotkeys
+## Essential Hotkeys
 | Action | Key | Description |
 |--------|-----|-------------|
@@ -115,13 +122,13 @@ pip install git+https://github.com/facebookresearch/sam2.git
 | **Positive Point** | `Left Click` | Add to segment |
 | **Negative Point** | `Right Click` | Remove from segment |
-💡 **All hotkeys customizable** - Click "Hotkeys" button to personalize
+**Note:** All hotkeys are fully customizable - Click "Hotkeys" button to personalize your workflow.
 ---
-## 📦 Output Format
+## Output Format
-Perfect for ML training - clean, structured data:
+LazyLabel exports data in standardized formats optimized for machine learning workflows:
 ```python
 import numpy as np
@@ -145,10 +152,9 @@ class_2_mask = mask[:, :, 2]  # Object type 2
 ---
-## 🛠️ Development
+## Development
-**Requirements:** Python 3.10+
-**2.5GB** disk space for SAM model (auto-downloaded)
+**Requirements:** Python 3.10+, ~2.5GB disk space for SAM models (auto-downloaded)
 ### Installation from Source
 ```bash
@@ -160,35 +166,32 @@ lazylabel-gui
 ### Testing & Quality
 ```bash
-# Run full test suite
-python -m pytest --cov=lazylabel --cov-report=html
+# Run test suite (272 tests)
+pytest --tb=short
-# Code formatting & linting
-ruff check . && ruff format .
+# Code quality checks
+ruff check --fix src/
 ```
 ### Architecture
 - **Modular design** with clean component separation
-- **Signal-based communication** between UI elements
-- **Extensible model system** for new SAM variants
-- **Comprehensive test suite** (150+ tests, 60%+ coverage)
+- **Signal-based communication** between UI elements
+- **Extensible model system** for SAM 1.0 and SAM 2.1 variants
+- **Comprehensive test suite** (272 tests with extensive coverage)
+- **Multi-view support** for simultaneous image processing
 ---
-## 🤝 Contributing
+## Contributing
-LazyLabel welcomes contributions! Check out:
-- [Architecture Guide](src/lazylabel/ARCHITECTURE.md) for technical details
-- [Hotkey System](src/lazylabel/HOTKEY_FEATURE.md) for customization
-- Issues page for feature requests and bug reports
+LazyLabel welcomes contributions! Please review:
+- [Usage Manual](src/lazylabel/USAGE_MANUAL.md) for comprehensive user documentation
+- [Architecture Guide](src/lazylabel/ARCHITECTURE.md) for technical implementation details
+- [Issues page](https://github.com/dnzckn/LazyLabel/issues) for feature requests and bug reports
 ---
-## 🙏 Acknowledgments
+## Acknowledgments
 - [LabelMe](https://github.com/wkentaro/labelme)
 - [Segment-Anything-UI](https://github.com/branislavhesko/segment-anything-ui)
----
-**Made with ❤️ for the computer vision community**

lazylabel_gui-1.3.5/README.md DELETED Viewed

@@ -1,139 +0,0 @@
-# <img src="https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/logo2.png" alt="LazyLabel Logo" style="height:60px; vertical-align:middle;" /> <img src="https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/logo_black.png" alt="LazyLabel Cursive" style="height:60px; vertical-align:middle;" />
-**AI-Assisted Image Segmentation Made Simple**
-LazyLabel combines Meta's Segment Anything Model (SAM) with intuitive editing tools for fast, precise image labeling. Perfect for machine learning datasets and computer vision research.
-![LazyLabel Screenshot](https://raw.githubusercontent.com/dnzckn/LazyLabel/main/src/lazylabel/demo_pictures/gui.PNG)
----
-## 🚀 Quick Start
-### Installation
-```bash
-pip install lazylabel-gui
-lazylabel-gui
-```
-### Optional: SAM-2 Support
-For advanced SAM-2 models, install manually:
-```bash
-pip install git+https://github.com/facebookresearch/sam2.git
-```
-*Note: SAM-2 is optional - LazyLabel works with SAM 1.0 models by default*
-### Usage
-1. **Open Folder** → Select your image directory
-2. **Click on image** → AI generates instant masks
-3. **Fine-tune** → Edit polygons, merge segments
-4. **Export** → Clean `.npz` files ready for ML training
----
-## ✨ Key Features
-- **🧠 One-click AI segmentation** with Meta's SAM and SAM2 models
-- **🎨 Manual polygon drawing** with full vertex control
-- **⚡ Smart editing tools** - merge segments, adjust class names, and class order
-- **📊 ML-ready exports** - One-hot encoded `.npz` format and `.json` for YOLO format
-- **🔧 Image enhancement** - brightness, contrast, gamma adjustment
-- **🔍 Image viewer** - zoom, pan, brightness, contrast, and gamma adjustment
-- **✂️ Edge cropping** - define custom crop areas to focus on specific regions
-- **🔄 Undo/Redo** - full history of all actions
-- **💾 Auto-saving** - Automatic saving of your labels when navigating between images
-- **🎛️ Advanced filtering** - FFT thresholding and color channel thresholding
-- **⌨️ Customizable hotkeys** for all functions
----
-## ⌨️ Essential Hotkeys
-| Action | Key | Description |
-|--------|-----|-------------|
-| **AI Mode** | `1` | Point-click segmentation |
-| **Draw Mode** | `2` | Manual polygon drawing |
-| **Edit Mode** | `E` | Select and modify shapes |
-| **Save Segment** | `Space` | Confirm current mask |
-| **Merge** | `M` | Combine selected segments |
-| **Pan** | `Q` + drag | Navigate large images |
-| **Positive Point** | `Left Click` | Add to segment |
-| **Negative Point** | `Right Click` | Remove from segment |
-💡 **All hotkeys customizable** - Click "Hotkeys" button to personalize
----
-## 📦 Output Format
-Perfect for ML training - clean, structured data:
-```python
-import numpy as np
-# Load your labeled data
-data = np.load('your_image.npz')
-mask = data['mask']  # Shape: (height, width, num_classes)
-# Each channel is a binary mask for one class
-class_0_mask = mask[:, :, 0]  # Background
-class_1_mask = mask[:, :, 1]  # Object type 1
-class_2_mask = mask[:, :, 2]  # Object type 2
-```
-**Ideal for:**
-- Semantic segmentation datasets
-- Instance segmentation training
-- Computer vision research
-- Automated annotation pipelines
----
-## 🛠️ Development
-**Requirements:** Python 3.10+
-**2.5GB** disk space for SAM model (auto-downloaded)
-### Installation from Source
-```bash
-git clone https://github.com/dnzckn/LazyLabel.git
-cd LazyLabel
-pip install -e .
-lazylabel-gui
-```
-### Testing & Quality
-```bash
-# Run full test suite
-python -m pytest --cov=lazylabel --cov-report=html
-# Code formatting & linting
-ruff check . && ruff format .
-```
-### Architecture
-- **Modular design** with clean component separation
-- **Signal-based communication** between UI elements
-- **Extensible model system** for new SAM variants
-- **Comprehensive test suite** (150+ tests, 60%+ coverage)
----
-## 🤝 Contributing
-LazyLabel welcomes contributions! Check out:
-- [Architecture Guide](src/lazylabel/ARCHITECTURE.md) for technical details
-- [Hotkey System](src/lazylabel/HOTKEY_FEATURE.md) for customization
-- Issues page for feature requests and bug reports
----
-## 🙏 Acknowledgments
-- [LabelMe](https://github.com/wkentaro/labelme)
-- [Segment-Anything-UI](https://github.com/branislavhesko/segment-anything-ui)
----
-**Made with ❤️ for the computer vision community**