---
license: mit
library: ultralytics
tags:
- object-detection
- pytorch
- ultralytics
- roboflow-universe
- human-detection
- yolov8
---
# Human Detection using Thermal Camera

## Use Case

## Evaluation Metrics

__Weights & Biases__: [Run Details](https://wandb.ai/2wb2ndur/Human-Detection-Thermal-Camera/runs/5j95496q/overview?workspace=user-2wb2ndur)

### Training Graphs

![Training Graphs](./training_artifacts/results.png)

## Training Code

- Dataset Link: [Roboflow Universe](https://universe.roboflow.com/smart2/persondection-61bc2)

```python
from ultralytics import YOLO
import torch

# load model
model = YOLO("yolov8n.pt")

# hyper parameters
hyperparams = {
    "batch": 32,
    "epochs": 30,
    "imgsz": [640, 480],
    "optimizer": "AdamW",
    "cos_lr": True,
    "lr0": 3e-5,
    "warmup_epochs": 10
}

# start training
model.train(
    device = 'cuda' if torch.cuda.is_available() else 'cpu',
    data = "data.yaml",
    **hyperparams
)
```

- Click here for: [Training Arguments](./training_artifacts/args.yaml)

## Libraries

```yaml
python: 3.10.13
ultralytics: 8.0.206
torch: "2.1.0+cu118"
roboflow: 1.1.9
```