ultralytics/yolov5

Validating performance of a two-stage classifier using detect.py to crop results

anniexxsun opened this issue · 3 comments

anniexxsun commented

Search before asking

Question

Dear fellow githubbers,

I am un undergraduate uni student and I am considering using YOLOv5 and a second stage classifier model together as an ensemble model for a classification task.

After going through some of the threads, it seems that it is quite feasible to crop the detection results from the yolo model with save-crop, and feed this image into another classifier such as ResNet/EfficentNet. This classifier will have been custom trained on the same dataset already.

However, I am wondering how I would be able to evaluate the performance of this ensemble model altogether. I believe I can get metrics for the YOLO part alone, as well as metrics for the second stage classifier alone. However, how can I verify the results from the detect.py file, where the ensemble model is implemented together?

Or, would I need to run tests on this ensemble model instead? (a new file)??

Any help or ideas would be much appreciated. Thank you!

Additional

Related threads I have looked at:
#7429
#1033
#6585
#4785
#5329

github-actions commented

👋 Hello @anniehfwx, 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):

Status

YOLOv5 CI

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 commented

Hi @anniehfwx! That's a great question. To evaluate the performance of your ensemble model, you can calculate the precision, recall, and F1-score of your final output. You can do this by calculating the metrics of the yolo model separately and then calculating the metrics of the second classifier separately. Once you have done this, you can combine the metrics by taking the geometric mean or the harmonic mean. You can also choose to calculate the metrics for the ensemble model by running tests on a new file, but the results should be consistent with the individual results of the yolo model and second classifier. I hope this helps!

github-actions commented

👋 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:

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 ⭐