I RUN SAME CODE BUT I GET DIFFERENT ACCURACY

[Antoniodevy]

Search before asking

• I have searched the Roboflow Notebooks issues and found no similar bug report.

Notebook name

https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/train-rt-detr-on-custom-dataset-with-transformers.ipynb?ref=blog.roboflow.com#scrollTo=Fh5y-l8LJLIR

Bug

I RUN SAME CODE BUT I GET DIFFERENT ACCURACY

Environment

• Google Colab

Minimal Reproducible Example

No response

Additional

No response

Are you willing to submit a PR?

• Yes I'd like to help by submitting a PR!

[DolapoSalim]

Hello AntonioDevy,

During your training setup, try to set a random seed:

From Ulytralytics:
seed | int | default value is 0 | Sets the random seed for training, ensuring the reproducibility of results across runs with the same configurations.

e.g yolo detect train data=data.yaml model=yolov8n.pt epochs=100 imgsz=640 seed=42

With the seed value set at the same integer value, you can reproduce the same training result with the same code.
I hope this helps you.