Fine tune a pre-trained model on Tobacco 800

I can see from your command that you train a new model based on Tobacco 800 data.

```
!python yolov5/train.py --img 640 --batch 16 --epochs 300 \
    --data tobacco_data.yaml --cfg models/yolov5x.yaml --name Tobacco-run
```
Just wonder why you didn't choose to fine tune a pre-trained Yolov5 model on Tobacco 800 data instead?