Model Training

Train custom YOLO models using the Stanford Cars dataset

Dataset Status
Stanford Cars Dataset

Not Found Directory

Not Found Annotations File

YOLO Model Status

No custom YOLO model available

Use the training form below to train a custom model

Current Training Status
Error
Started: 2025-03-24T10:58:31.603585+00:00
0%
Error: Failed to train YOLO model
Mode
Detection
Epochs
30
Image Size
640px
Batch Size
16
Start Training
Detection Mode
Car Detection

Train model to detect cars in images (single class)

Good for identifying where cars are located in images

Classification Mode
Car Classification

Train model to identify car make/model/year (multi-class)

Requires more data, but provides detailed car identification

Choose whether to train for detection or classification
More epochs = better results but longer training
Larger = better detection but slower
Depends on your system memory
About Training
What is YOLO?

YOLO (You Only Look Once) is a state-of-the-art object detection algorithm that can identify multiple objects in an image in real-time.

It works by dividing the image into a grid and predicting bounding boxes and class probabilities for each grid cell.

Stanford Cars Dataset

The Stanford Cars dataset contains 16,185 images of 196 classes of cars. Classes are typically at the level of Make, Model, Year (e.g. 2012 Tesla Model S).

This dataset provides high-quality annotations for training accurate car detection and classification models.

Training may take several hours depending on your system's capabilities and the parameters you choose. The process will continue in the background even if you navigate away from this page.