# 🚗 MareArts Road Objects Detection
[](https://badge.fury.io/py/marearts-road-objects)
[](https://pepy.tech/project/marearts-road-objects)
[](https://www.python.org/downloads/)
[](LICENSE)
[](https://www.microsoft.com/windows)
[](https://www.linux.org/)
[](https://www.apple.com/macos/)
A high-performance Python package for road object detection. Detect persons, 4-wheeled vehicles, and 2-wheeled vehicles in images with advanced YOLO-based neural networks.
## ✨ Features
- 🚗 **Multi-class Detection**: Detects persons, cars/trucks, and motorcycles/bicycles
- ⚡ **GPU Acceleration**: NVIDIA CUDA, TensorRT, and DirectML support
- 🛠️ **CLI Interface**: Easy command-line tools (`marearts-robj` or `marearts-road-objects`)
- 📦 **Multiple Model Sizes**: Small (50MB), medium (100MB), large (200MB)
- 🌐 **Cross-platform**: Windows, macOS, and Linux support
- 🔑 **Unified License**: Same license works for both [MareArts-ANPR](https://github.com/MareArts/MareArts-ANPR) and Road Objects
## 🚀 Quick Start
### Installation
```bash
# Basic installation (CPU)
pip install marearts-road-objects
# With GPU acceleration (recommended)
pip install marearts-road-objects[gpu] # NVIDIA
pip install marearts-road-objects[directml] # Windows GPU
pip install marearts-road-objects[all-gpu] # All GPU support
```
### Get Your License
**Subscribe**: [MareArts ANPR/LPR Solution](https://study.marearts.com/p/anpr-lpr-solution.html)
**Note**: One license works for both ANPR and Road Objects packages!
### Configure License
```bash
# Interactive setup (recommended)
marearts-robj config
# Or set environment variables
export MAREARTS_ANPR_USERNAME="your-email@domain.com"
export MAREARTS_ANPR_SERIAL_KEY="your-serial-key"
```
### Basic Usage
```bash
# Detect objects in an image
marearts-robj detect traffic.jpg
# Use larger model with custom settings
marearts-robj detect highway.jpg --model large --confidence 0.7 --output result.jpg
# Check GPU acceleration
marearts-robj gpu-info
```
## 🐍 Python API
### Simple Detection
```python
import cv2
from marearts_road_objects import create_detector, download_model
# License credentials
username = "your-email@domain.com"
serial_key = "your-serial-key"
# Download and initialize detector
model_path = download_model("medium", username, serial_key)
detector = create_detector(model_path, username, serial_key, model_size="medium")
# Detect objects
image = cv2.imread("traffic_scene.jpg")
result = detector.detect(image)
# Print results
print(f"Processing time: {result['processing_time_ms']}ms")
print(f"Total objects: {result['total_objects']}")
for detection in result['detections']:
print(f"{detection['id']}. {detection['class']} ({detection['subclass']})")
print(f" Confidence: {detection['confidence']}")
print(f" Bounding box: {detection['bbox']}")
```
### Combined with ANPR
```python
# Same license works for both packages!
from marearts_road_objects import create_detector, download_model
from marearts_anpr import ma_anpr_detector, ma_anpr_ocr, marearts_anpr_from_cv2
username = "your-email@domain.com"
serial_key = "your-serial-key" # Same key for both!
# Initialize road objects detector
road_model = download_model("medium", username, serial_key)
road_detector = create_detector(road_model, username, serial_key, "medium")
# Initialize ANPR detector and OCR
anpr_detector = ma_anpr_detector("v11_middle", username, serial_key)
anpr_ocr = ma_anpr_ocr("v11_euplus", username, serial_key)
# Analyze traffic scene
image = cv2.imread("traffic.jpg")
vehicles = road_detector.detect(image) # Detect vehicles/persons
plates = marearts_anpr_from_cv2(anpr_detector, anpr_ocr, image) # Detect and OCR license plates
print(f"Found {vehicles['total_objects']} road objects, {len(plates)} license plates")
```
## 📊 Output Format
The detection results come in a clean, structured JSON format:
```python
{
"processing_time_ms": 45.2, # Processing time in milliseconds
"total_objects": 3, # Number of detected objects
"detections": [ # List of detected objects
{
"id": 1, # Sequential object ID
"class": "person", # Main class (person, 4-wheels, 2-wheels)
"subclass": "pedestrian", # Specific subclass (pedestrian, car, truck, bike)
"confidence": 0.89, # Detection confidence (0.0 - 1.0)
"bbox": [120, 150, 180, 280] # Bounding box [x1, y1, x2, y2]
},
{
"id": 2,
"class": "4-wheels",
"subclass": "car",
"confidence": 0.76,
"bbox": [300, 200, 450, 320]
}
]
}
```
## 🎯 Model Information
| Model | Speed | Accuracy | Size | Use Case |
|-------|-------|----------|------|----------|
| Small | Fastest | Good | 50MB | Real-time, mobile |
| Medium | Balanced | Better | 100MB | General purpose |
| Large | Slower | Best | 200MB | High accuracy needs |
**Detection Classes & Subclasses:**
- **person** (Pedestrians and people) → **pedestrian**
- **4-wheels** (Cars, trucks, buses, vans) → **car** (small) or **truck** (large)
- **2-wheels** (Motorcycles, bicycles, scooters) → **bike**
## 🛠️ CLI Reference
### Available Commands
```bash
marearts-robj config # Configure license
marearts-robj gpu-info # Check GPU support
marearts-robj detect IMAGE # Detect objects
marearts-robj download # Download models
marearts-robj validate # Validate license
```
### Detection Examples
```bash
# Basic detection
marearts-robj detect image.jpg
# Advanced options
marearts-robj detect highway.jpg \
--model large \
--confidence 0.8 \
--output detected_highway.jpg
# Batch processing
for img in *.jpg; do
marearts-robj detect "$img" --output "detected_$img"
done
```
### Model Management
```bash
# Download specific models
marearts-robj download --model small
marearts-robj download --model large
# Check what's available
python -c "from marearts_road_objects import get_available_models; print(get_available_models())"
```
## ⚡ GPU Acceleration
### Check GPU Support
```bash
marearts-robj gpu-info
```
**Expected output with GPU:**
```
🚀 CUDAExecutionProvider (GPU)
⚡ CPUExecutionProvider
GPU Acceleration: ENABLED
```
### Performance Comparison
| Configuration | Small Model | Medium Model | Large Model |
|---------------|-------------|--------------|-------------|
| CPU (Intel i7) | ~100ms | ~200ms | ~400ms |
| NVIDIA RTX 3080 | ~15ms | ~25ms | ~45ms |
| DirectML (Windows) | ~30ms | ~60ms | ~120ms |
### GPU Requirements
**NVIDIA**: CUDA 11.8+ and cuDNN 8.6+
**Windows DirectML**: Windows 10 v1903+ with compatible GPU
**Memory**: 4GB+ GPU memory recommended for large models
## 💡 Code Examples
Ready-to-run examples are available in the [`examples/`](examples/) directory:
- **`basic_detection.py`** - Simple image detection
- **`combined_anpr_robj.py`** - Use both ANPR and Road Objects
- **`webcam_detection.py`** - Real-time webcam processing
- **`batch_processing.py`** - Process multiple images
- **`cli_examples.sh`** - Complete CLI usage guide
```bash
# Run an example
python examples/basic_detection.py
```
## 🆘 Support
- **License**: [Get your subscription](https://study.marearts.com/p/anpr-lpr-solution.html)
- **Issues**: [GitHub Issues](https://github.com/MareArts/MareArts-Road-Objects/issues)
- **Email**: hello@marearts.com
## 🔗 Related Packages
**MareArts AI Ecosystem** (same license for all):
- **[marearts-anpr](https://pypi.org/project/marearts-anpr/)** - License plate recognition
- **[marearts-crystal](https://pypi.org/project/marearts-crystal/)** - Licensing framework
- **[marearts-xcolor](https://pypi.org/project/marearts-xcolor/)** - Color space conversions
---
**© 2024 MareArts. All rights reserved.**
*Get started with road object detection in minutes. One license, multiple AI packages, endless possibilities.*
Raw data
{
"_id": null,
"home_page": null,
"name": "marearts-road-objects",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.9",
"maintainer_email": null,
"keywords": "computer-vision, object-detection, road-safety, onnx, yolo",
"author": null,
"author_email": "MareArts <contact@marearts.com>",
"download_url": null,
"platform": null,
"description": "# \ud83d\ude97 MareArts Road Objects Detection\n\n[](https://badge.fury.io/py/marearts-road-objects)\n[](https://pepy.tech/project/marearts-road-objects)\n[](https://www.python.org/downloads/)\n[](LICENSE)\n[](https://www.microsoft.com/windows)\n[](https://www.linux.org/)\n[](https://www.apple.com/macos/)\n\nA high-performance Python package for road object detection. Detect persons, 4-wheeled vehicles, and 2-wheeled vehicles in images with advanced YOLO-based neural networks.\n\n## \u2728 Features\n\n- \ud83d\ude97 **Multi-class Detection**: Detects persons, cars/trucks, and motorcycles/bicycles\n- \u26a1 **GPU Acceleration**: NVIDIA CUDA, TensorRT, and DirectML support\n- \ud83d\udee0\ufe0f **CLI Interface**: Easy command-line tools (`marearts-robj` or `marearts-road-objects`)\n- \ud83d\udce6 **Multiple Model Sizes**: Small (50MB), medium (100MB), large (200MB)\n- \ud83c\udf10 **Cross-platform**: Windows, macOS, and Linux support\n- \ud83d\udd11 **Unified License**: Same license works for both [MareArts-ANPR](https://github.com/MareArts/MareArts-ANPR) and Road Objects\n\n## \ud83d\ude80 Quick Start\n\n### Installation\n\n```bash\n# Basic installation (CPU)\npip install marearts-road-objects\n\n# With GPU acceleration (recommended)\npip install marearts-road-objects[gpu] # NVIDIA\npip install marearts-road-objects[directml] # Windows GPU\npip install marearts-road-objects[all-gpu] # All GPU support\n```\n\n### Get Your License\n\n**Subscribe**: [MareArts ANPR/LPR Solution](https://study.marearts.com/p/anpr-lpr-solution.html) \n**Note**: One license works for both ANPR and Road Objects packages!\n\n### Configure License\n\n```bash\n# Interactive setup (recommended)\nmarearts-robj config\n\n# Or set environment variables\nexport MAREARTS_ANPR_USERNAME=\"your-email@domain.com\"\nexport MAREARTS_ANPR_SERIAL_KEY=\"your-serial-key\"\n```\n\n### Basic Usage\n\n```bash\n# Detect objects in an image\nmarearts-robj detect traffic.jpg\n\n# Use larger model with custom settings\nmarearts-robj detect highway.jpg --model large --confidence 0.7 --output result.jpg\n\n# Check GPU acceleration\nmarearts-robj gpu-info\n```\n\n## \ud83d\udc0d Python API\n\n### Simple Detection\n\n```python\nimport cv2\nfrom marearts_road_objects import create_detector, download_model\n\n# License credentials\nusername = \"your-email@domain.com\"\nserial_key = \"your-serial-key\"\n\n# Download and initialize detector\nmodel_path = download_model(\"medium\", username, serial_key)\ndetector = create_detector(model_path, username, serial_key, model_size=\"medium\")\n\n# Detect objects\nimage = cv2.imread(\"traffic_scene.jpg\")\nresult = detector.detect(image)\n\n# Print results\nprint(f\"Processing time: {result['processing_time_ms']}ms\")\nprint(f\"Total objects: {result['total_objects']}\")\n\nfor detection in result['detections']:\n print(f\"{detection['id']}. {detection['class']} ({detection['subclass']})\")\n print(f\" Confidence: {detection['confidence']}\")\n print(f\" Bounding box: {detection['bbox']}\")\n```\n\n### Combined with ANPR\n\n```python\n# Same license works for both packages!\nfrom marearts_road_objects import create_detector, download_model\nfrom marearts_anpr import ma_anpr_detector, ma_anpr_ocr, marearts_anpr_from_cv2\n\nusername = \"your-email@domain.com\"\nserial_key = \"your-serial-key\" # Same key for both!\n\n# Initialize road objects detector\nroad_model = download_model(\"medium\", username, serial_key)\nroad_detector = create_detector(road_model, username, serial_key, \"medium\")\n\n# Initialize ANPR detector and OCR\nanpr_detector = ma_anpr_detector(\"v11_middle\", username, serial_key)\nanpr_ocr = ma_anpr_ocr(\"v11_euplus\", username, serial_key)\n\n# Analyze traffic scene\nimage = cv2.imread(\"traffic.jpg\")\nvehicles = road_detector.detect(image) # Detect vehicles/persons\nplates = marearts_anpr_from_cv2(anpr_detector, anpr_ocr, image) # Detect and OCR license plates\n\nprint(f\"Found {vehicles['total_objects']} road objects, {len(plates)} license plates\")\n```\n\n## \ud83d\udcca Output Format\n\nThe detection results come in a clean, structured JSON format:\n\n```python\n{\n \"processing_time_ms\": 45.2, # Processing time in milliseconds\n \"total_objects\": 3, # Number of detected objects\n \"detections\": [ # List of detected objects\n {\n \"id\": 1, # Sequential object ID\n \"class\": \"person\", # Main class (person, 4-wheels, 2-wheels)\n \"subclass\": \"pedestrian\", # Specific subclass (pedestrian, car, truck, bike)\n \"confidence\": 0.89, # Detection confidence (0.0 - 1.0)\n \"bbox\": [120, 150, 180, 280] # Bounding box [x1, y1, x2, y2]\n },\n {\n \"id\": 2,\n \"class\": \"4-wheels\", \n \"subclass\": \"car\",\n \"confidence\": 0.76,\n \"bbox\": [300, 200, 450, 320]\n }\n ]\n}\n```\n\n## \ud83c\udfaf Model Information\n\n| Model | Speed | Accuracy | Size | Use Case |\n|-------|-------|----------|------|----------|\n| Small | Fastest | Good | 50MB | Real-time, mobile |\n| Medium | Balanced | Better | 100MB | General purpose |\n| Large | Slower | Best | 200MB | High accuracy needs |\n\n**Detection Classes & Subclasses:**\n- **person** (Pedestrians and people) \u2192 **pedestrian**\n- **4-wheels** (Cars, trucks, buses, vans) \u2192 **car** (small) or **truck** (large)\n- **2-wheels** (Motorcycles, bicycles, scooters) \u2192 **bike**\n\n## \ud83d\udee0\ufe0f CLI Reference\n\n### Available Commands\n\n```bash\nmarearts-robj config # Configure license\nmarearts-robj gpu-info # Check GPU support\nmarearts-robj detect IMAGE # Detect objects\nmarearts-robj download # Download models\nmarearts-robj validate # Validate license\n```\n\n### Detection Examples\n\n```bash\n# Basic detection\nmarearts-robj detect image.jpg\n\n# Advanced options\nmarearts-robj detect highway.jpg \\\n --model large \\\n --confidence 0.8 \\\n --output detected_highway.jpg\n\n# Batch processing\nfor img in *.jpg; do\n marearts-robj detect \"$img\" --output \"detected_$img\"\ndone\n```\n\n### Model Management\n\n```bash\n# Download specific models\nmarearts-robj download --model small\nmarearts-robj download --model large\n\n# Check what's available\npython -c \"from marearts_road_objects import get_available_models; print(get_available_models())\"\n```\n\n## \u26a1 GPU Acceleration\n\n### Check GPU Support\n\n```bash\nmarearts-robj gpu-info\n```\n\n**Expected output with GPU:**\n```\n\ud83d\ude80 CUDAExecutionProvider (GPU)\n\u26a1 CPUExecutionProvider\nGPU Acceleration: ENABLED\n```\n\n### Performance Comparison\n\n| Configuration | Small Model | Medium Model | Large Model |\n|---------------|-------------|--------------|-------------|\n| CPU (Intel i7) | ~100ms | ~200ms | ~400ms |\n| NVIDIA RTX 3080 | ~15ms | ~25ms | ~45ms |\n| DirectML (Windows) | ~30ms | ~60ms | ~120ms |\n\n### GPU Requirements\n\n**NVIDIA**: CUDA 11.8+ and cuDNN 8.6+ \n**Windows DirectML**: Windows 10 v1903+ with compatible GPU \n**Memory**: 4GB+ GPU memory recommended for large models\n\n## \ud83d\udca1 Code Examples\n\nReady-to-run examples are available in the [`examples/`](examples/) directory:\n\n- **`basic_detection.py`** - Simple image detection\n- **`combined_anpr_robj.py`** - Use both ANPR and Road Objects\n- **`webcam_detection.py`** - Real-time webcam processing\n- **`batch_processing.py`** - Process multiple images\n- **`cli_examples.sh`** - Complete CLI usage guide\n\n```bash\n# Run an example\npython examples/basic_detection.py\n```\n\n## \ud83c\udd98 Support\n\n- **License**: [Get your subscription](https://study.marearts.com/p/anpr-lpr-solution.html)\n- **Issues**: [GitHub Issues](https://github.com/MareArts/MareArts-Road-Objects/issues)\n- **Email**: hello@marearts.com\n\n## \ud83d\udd17 Related Packages\n\n**MareArts AI Ecosystem** (same license for all):\n- **[marearts-anpr](https://pypi.org/project/marearts-anpr/)** - License plate recognition\n- **[marearts-crystal](https://pypi.org/project/marearts-crystal/)** - Licensing framework \n- **[marearts-xcolor](https://pypi.org/project/marearts-xcolor/)** - Color space conversions\n\n---\n\n**\u00a9 2024 MareArts. All rights reserved.**\n\n*Get started with road object detection in minutes. One license, multiple AI packages, endless possibilities.*\n",
"bugtrack_url": null,
"license": "Proprietary",
"summary": "High-performance road object detection for persons, vehicles, and 2-wheelers",
"version": "1.0.5",
"project_urls": {
"Documentation": "https://github.com/MareArts/MareArts-Road-Objects#readme",
"Homepage": "https://github.com/MareArts/MareArts-Road-Objects",
"Repository": "https://github.com/MareArts/MareArts-Road-Objects"
},
"split_keywords": [
"computer-vision",
" object-detection",
" road-safety",
" onnx",
" yolo"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "836ac773c5321c481e3000b1730ac649615a02b7beae4e839309f397b70f9cbf",
"md5": "a4e459fd051b24687f5efcd6d1222d73",
"sha256": "468b6ba28f861fb9b7bc8c6a8092d6a3bf696d459dfecae27ebcb9ef4006e031"
},
"downloads": -1,
"filename": "marearts_road_objects-1.0.5-cp310-cp310-macosx_10_9_universal2.whl",
"has_sig": false,
"md5_digest": "a4e459fd051b24687f5efcd6d1222d73",
"packagetype": "bdist_wheel",
"python_version": "cp310",
"requires_python": ">=3.9",
"size": 363610,
"upload_time": "2025-07-20T12:56:56",
"upload_time_iso_8601": "2025-07-20T12:56:56.672265Z",
"url": "https://files.pythonhosted.org/packages/83/6a/c773c5321c481e3000b1730ac649615a02b7beae4e839309f397b70f9cbf/marearts_road_objects-1.0.5-cp310-cp310-macosx_10_9_universal2.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "94b2cfe1530ea82c062fae127d6fa3d9e62e508a1ed0a67d908d2a92180085e4",
"md5": "a7f7c7edaf9e95679f9103809ffcda71",
"sha256": "0e7982da28297e52950423630dc4e1cffbcbb39b57910db29ab99290b1eaa6c8"
},
"downloads": -1,
"filename": "marearts_road_objects-1.0.5-cp310-cp310-win_amd64.whl",
"has_sig": false,
"md5_digest": "a7f7c7edaf9e95679f9103809ffcda71",
"packagetype": "bdist_wheel",
"python_version": "cp310",
"requires_python": ">=3.9",
"size": 173894,
"upload_time": "2025-07-20T12:56:57",
"upload_time_iso_8601": "2025-07-20T12:56:57.939398Z",
"url": "https://files.pythonhosted.org/packages/94/b2/cfe1530ea82c062fae127d6fa3d9e62e508a1ed0a67d908d2a92180085e4/marearts_road_objects-1.0.5-cp310-cp310-win_amd64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "f36e35c467173b92a4b56862fba4211054eaea065b3036f1e0255955ddfd7328",
"md5": "c98b89329f1d721f290d69e8ededfd2f",
"sha256": "6ae83832420edfd7cd0de4028451ff90c73e4e3150a32c0e5bd323204bfbf577"
},
"downloads": -1,
"filename": "marearts_road_objects-1.0.5-cp311-cp311-macosx_10_9_universal2.whl",
"has_sig": false,
"md5_digest": "c98b89329f1d721f290d69e8ededfd2f",
"packagetype": "bdist_wheel",
"python_version": "cp311",
"requires_python": ">=3.9",
"size": 366294,
"upload_time": "2025-07-20T12:56:59",
"upload_time_iso_8601": "2025-07-20T12:56:59.243261Z",
"url": "https://files.pythonhosted.org/packages/f3/6e/35c467173b92a4b56862fba4211054eaea065b3036f1e0255955ddfd7328/marearts_road_objects-1.0.5-cp311-cp311-macosx_10_9_universal2.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "2795fae9094c3a03ec2da71469f0bee9c4a26b4cf43e181fc29b77899b64932d",
"md5": "afae6254dfe6d72b6cc5a5cfe2f44d54",
"sha256": "d39d8f3a4e150f544ee32c6b5e62fed4eed778f8c9e11e205bcf70c8e70a78bb"
},
"downloads": -1,
"filename": "marearts_road_objects-1.0.5-cp311-cp311-win_amd64.whl",
"has_sig": false,
"md5_digest": "afae6254dfe6d72b6cc5a5cfe2f44d54",
"packagetype": "bdist_wheel",
"python_version": "cp311",
"requires_python": ">=3.9",
"size": 174662,
"upload_time": "2025-07-20T12:57:00",
"upload_time_iso_8601": "2025-07-20T12:57:00.691242Z",
"url": "https://files.pythonhosted.org/packages/27/95/fae9094c3a03ec2da71469f0bee9c4a26b4cf43e181fc29b77899b64932d/marearts_road_objects-1.0.5-cp311-cp311-win_amd64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "0f870ff2810a983336a0d46b978e421e143a5c4b445c4bebe291757715336237",
"md5": "af94a847f0e92a48b6b466c644615286",
"sha256": "f30d3fd4a5943f3bb6e517c8546a9a1f4199a792c00235b440a5870c9310b796"
},
"downloads": -1,
"filename": "marearts_road_objects-1.0.5-cp312-cp312-macosx_10_13_universal2.whl",
"has_sig": false,
"md5_digest": "af94a847f0e92a48b6b466c644615286",
"packagetype": "bdist_wheel",
"python_version": "cp312",
"requires_python": ">=3.9",
"size": 365245,
"upload_time": "2025-07-20T12:57:02",
"upload_time_iso_8601": "2025-07-20T12:57:02.222439Z",
"url": "https://files.pythonhosted.org/packages/0f/87/0ff2810a983336a0d46b978e421e143a5c4b445c4bebe291757715336237/marearts_road_objects-1.0.5-cp312-cp312-macosx_10_13_universal2.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "c4922072cfaef4075d1dfa6be3555b31b9b4e12c8a3f7f195a5f51e24939f74b",
"md5": "8853f1d0d32456a85beaeea80a12aee8",
"sha256": "0d209bfe0e967dac556be040d24d5de955c2164027abe84e6f09e85ce59cbedc"
},
"downloads": -1,
"filename": "marearts_road_objects-1.0.5-cp312-cp312-win_amd64.whl",
"has_sig": false,
"md5_digest": "8853f1d0d32456a85beaeea80a12aee8",
"packagetype": "bdist_wheel",
"python_version": "cp312",
"requires_python": ">=3.9",
"size": 173793,
"upload_time": "2025-07-20T12:57:03",
"upload_time_iso_8601": "2025-07-20T12:57:03.321235Z",
"url": "https://files.pythonhosted.org/packages/c4/92/2072cfaef4075d1dfa6be3555b31b9b4e12c8a3f7f195a5f51e24939f74b/marearts_road_objects-1.0.5-cp312-cp312-win_amd64.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-20 12:56:56",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "MareArts",
"github_project": "MareArts-Road-Objects#readme",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "marearts-road-objects"
}
JSON
