No detections on custom data training

[Just1813]

Search before asking

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

Question

I'm trying to train yolov5 with custom data. I'm using very few images just to test everything. I have 2 classes and 6 images (3 images for each class), which I know is WAY too little, but as I said, it's only for testing purposes. So I trained the model with the data which worked fine, but when I try to detect one of the images that was used for training, it doesn't work. Shouldn't it be able to detect the images I trained with, even if there are so few?

Command for training:
python train.py --img 2048 --batch 16 --epochs 5 --data test.yaml --weights yolov5s.pt --nosave --cache

Command for testing:
python detect.py --weights runs/train/exp11/weights/last.pt --source data/cartes_mini/images/2-C_jpg.rf.3ad5f752441ac8389c42afec2b5ecc10.jpg

I've also tried with another dataset that contained 1 class and around 20 training images, but got the same result.

Thank you!

Additional

No response

[github-actions]

👋 Hello @Just1813, 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! Thanks for reaching out. 👋

Absolutely, even with a small dataset, you'd typically expect some detections from the training images. A few potential checkpoints:

1. Annotations Check: Ensure the annotations are correctly formatted and correspond accurately to your class labels in the images. Incorrect or misaligned annotations could result in no detections.

2. Image Path: Verify that the image paths specified in your data YAML and testing command are correct and accessible.

3. Experimentation: Try to lower the confidence threshold when running the detection command to see if the model is actually detecting anything but with low confidence:

python detect.py --weights runs/train/exp11/weights/last.pt --source data/cartes_mini/images/2-C_jpg.rf.3ad5f752441ac8389c42afec2b5ecc10.jpg --conf 0.25

4. Model Overfitting: With such a small dataset, the model might be underfitting. Consider using pre-trained weights and fine-tuning on your data for a better generalization over few epochs.

If you're persistently encountering issues, consider adjusting training parameters or increasing dataset size for effective training results. Happy coding! 😊