---
license: apache-2.0
extra_gated_prompt: >-
  ### VehicleNet-Y26 License & Usage Terms VehicleNet-Y26n is a vehicle
  detection model released under the Apache License, Version 2.0. By accessing,
  downloading, or using VehicleNet-Y26, you confirm that: 

  1. You meet the legal age requirements applicable in your country. 

  2. You have the authority to accept this agreement. 

  3. You agree to use the model in compliance with the Apache-2.0 license and
  all applicable laws and regulations.

  VehicleNet is provided as-is, without warranties of any kind, express or
  implied.  The authors make no guarantees regarding accuracy, reliability,
  fitness for a particular  purpose, or suitability for deployment in
  safety-critical or regulated environments.

  You are solely responsible for how the model and its outputs are used. Any
  misuse,  unlawful application, or deployment without proper validation is
  strictly discouraged.

  **Your access will be granted automatically upon submission.**
extra_gated_fields:
  First Name: text
  Last Name: text
  Country: country
  Job title:
    type: select
    options:
    - Undergraduate Student
    - Research Graduate
    - AI researcher
    - AI developer/engineer
    - Other
  geo: ip_location
  I acknowledge and accept these terms and conditions: checkbox
extra_gated_button_content: Get Access
datasets:
- iisc-aim/UVH-26
language:
- en
metrics:
- confusion_matrix
library_name: ultralytics
base_model:
- Ultralytics/YOLO26
pipeline_tag: object-detection
tags:
- indian-traffic
- inference-efficiency
- multi-vehicle-detection
- ultralytics
---

# VehicleNet-Y26n

**VehicleNet-Y26n** is a multi-class vehicle detection model designed for speed & efficiency for fine-grained vehicle type recognition in real-world traffic scenes. This model is trained on **`UVH-26-MV Dataset`** released by IISc Banaglore. The dataset is based on Indian traffic which is highly challenging, dense and heterogeneous. It contains 14 vehicle categories such as hatchback, sedan, SUV, MUV, two-wheelers, three-wheelers, buses, trucks, and commercial vehicles.

This model is finetuned on `YOLO26n`:[arXiv](https://arxiv.org/html/2509.25164v3)(model by **`Ultralytics`** using **`UVH-26-MV Dataset`**.

## Model Overview and Parameters
- Task: Multi-class vehicle detection
- Architecture: YOLO26n (Ultralytics)
- Number of Classes: 14
- Input Resolution: 640 × 640
- Training Epochs: 30/30
- Batch Size: 24
- Hardware: Dual NVIDIA Tesla T4 GPUs
- Framework: Ultralytics YOLO (PyTorch)

## Performance Summary
- `mAP@50`: 0.634
- `mAP@50:95`: 0.542
- `Precision`: 0.706
- `Recall`: 0.701


![image](https://cdn-uploads.huggingface.co/production/uploads/66c6048d0bf40704e4159a23/1goIQDKYndOSyDQuyRum7.png)

The model showed strong detection performance for structurally distinct vehicle categories such as two-wheelers, three-wheelers, buses, and trucks. Fine-grained car subclasses (hatchback, sedan, SUV, MUV) exhibit expected inter-class confusion/challenge due to visual similarity and viewpoint overlap, as reflected in the confusion matrix.

![image](https://cdn-uploads.huggingface.co/production/uploads/66c6048d0bf40704e4159a23/2olgSfmytUwGoGwUWBF8u.png)

## Intended Use

The model is suitable for:
- Edge device computation
- Traffic surveillance and analytics
- Academic research and benchmarking

## License

This model is released under the `Apache License 2.0`.