Freeze detection on training

[Porweks]

Search before asking

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

Question

How can i freeze detection? Currently detection is great, but classification can be better. Does exist any way to train only classification part of YOLOv5 without changes in detection part?

Additional

No response

[github-actions]

👋 Hello @Porweks, 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>=3.8.0 with all requirements.txt installed including PyTorch>=1.8. 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! 😊

To train only the classification part of YOLOv5 without altering the detection components, you can freeze the layers responsible for detection before starting your training. This can be done by setting the requires_grad attribute to False for the layers you wish to freeze.

Here's a general approach:

1. Load your model and identify which layers or parameters are dedicated to detection.
2. Set requires_grad to False for those layers to freeze them.
3. Proceed with training, this will only update the weights of the unfrozen layers.

Example to freeze layers up to a certain layer index (e.g., 10):

model = torch.load('yolov5s.pt')  # Load your model
for i, (name, param) in enumerate(model.named_parameters()):
    if i < 10:  # Change the 10 to your specific layer cutoff
        param.requires_grad = False

Make sure to carefully select which layers to freeze based on your model's architecture. Happy training! 🚀