How to improve model performance using additional data

[giho5374]

Search before asking

• I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

hello!
I trained using a pretrained model. We are in the process of learning with 10,000 pieces of data, and all previous learning is over.
Here, 10,000 additional pieces of data were collected, and there are a total of 20,000 pieces of data. I am wondering how to improve the performance of the model here.
Is there no other way than to train the newly collected 20,000 pieces of data from scratch without changing the class?
If the number of classes changes, do we have to train them all again?
Thank you for always.

Additional

No response

[github-actions]

👋 Hello @giho5374, thank you for your interest in YOLOv5 🚀! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide a minimum reproducible example to help us debug it.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset image examples and training logs, and verify you are following our Tips for Best Training Results.

Requirements

Python>=3.7.0 with all requirements.txt installed including PyTorch>=1.7. To get started:

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Notebooks with free GPU:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training, validation, inference, export and benchmarks on macOS, Windows, and Ubuntu every 24 hours and on every commit.

Introducing YOLOv8 🚀

We're excited to announce the launch of our latest state-of-the-art (SOTA) object detection model for 2023 - YOLOv8 🚀!

Designed to be fast, accurate, and easy to use, YOLOv8 is an ideal choice for a wide range of object detection, image segmentation and image classification tasks. With YOLOv8, you'll be able to quickly and accurately detect objects in real-time, streamline your workflows, and achieve new levels of accuracy in your projects.

Check out our YOLOv8 Docs for details and get started with:

pip install ultralytics

[glenn-jocher]

Hello @giho5374-AISchool, if you want to improve the performance of your pre-trained model with the additional 10,000 pieces of data, you have two options: 1) Fine-tuning the pre-trained model on the new data, or 2) Retraining the model on the entire 20,000 pieces of data.
If you want to change the number of classes, you will need to retrain the model from scratch as the output layer will need to be updated to match the new number of classes. However, if you just want to add new classes without changing the number of existing classes, you can fine-tune your pre-trained model on the new data without changing the output layer.
I hope this helps. Let me know if you have any further questions.

[SzaremehrjardiMT]

@glenn-jocher is there any guide to fine-tune the pre-trained yolov8 model? I need to enhance yolov8-seg model for one class of COCO (car). I already have the extra data (with the annotations) but it doesn't make sense to retrain yolov8 on COCO+the extra car dataset!

[github-actions]

👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.

For additional resources and information, please see the links below:

• Docs: https://docs.ultralytics.com
• HUB: https://hub.ultralytics.com
• Community: https://community.ultralytics.com

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLO 🚀 and Vision AI ⭐

[glenn-jocher]

Hello @SzaremehrjardiMT, you can refer to the Ultralytics Docs at https://docs.ultralytics.com/yolov5/ for a guide on fine-tuning the pre-trained YOLOv8 model. To enhance the YOLOv8-seg model for the "car" class, you can fine-tune the pre-trained model on your extra car dataset using transfer learning without retraining on the COCO dataset. This way, you can update the model specifically for the "car" class without starting from scratch. I hope this helps. Let me know if you have any further questions.