Fine tune a pre-trained model on Tobacco 800

amaljoseph / Signature-Verification_System_using_YOLOv5-and-CycleGAN

An end-to-end signature verification system to extract, clean and verify signatures in documents. Signatures are detected using YOLOv5. Noise is cleaned using a CycleGAN approach and verified. Keras / Tensorflow / PyTorch

147 stars 55 forks source link

Fine tune a pre-trained model on Tobacco 800 #11

Open htcml opened 1 year ago

htcml commented 1 year ago

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?