Unable to train model on VisDrone about yolov5

[github-actions]

👋 Hello @InderSethi, 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,

Thank you for reporting this issue with training on the VisDrone dataset. From the error message, it appears that the dataset download failed because the environment was not online. This could be due to a temporary network issue or a problem with the dataset URL.

Please ensure that your internet connection is stable and try downloading the dataset manually from the provided URL to verify its availability. If the issue persists, it might be helpful to check if the dataset URL has changed or if there are any restrictions on downloading files in your current environment (such as firewall settings).

If you continue to face difficulties, please provide any additional details or changes in your setup since the last successful training. This will help us better understand and address the problem.

Thank you for your cooperation and patience.

[InderSethi]

Hi Glenn, This issue has been occurring for the last two days. I can assure you that my internet is stable and working fine. I tried other models and they were also working fine. I tried downloading the data manually and found that there is a period (.) in the end which makes it return 404 once I removed that period it started downloading files. *Error: * ``` File "/home/iiitd/Documents/inder/venv/lib/python3.12/site-packages/ultralytics/engine/trainer.py", line 521, in get_dataset raise RuntimeError(emojis(f"Dataset '{clean_url(self.args.data)}' error ❌ {e}")) from e RuntimeError: Dataset 'VisDrone.yaml' error ❌ ❌ Download failure for https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-dev.zip. Environment is not online.``` This works fine manually: https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-dev.zip (removed .) Regards

…

On Fri, May 31, 2024 at 12:12 AM Glenn Jocher ***@***.***> wrote: Hello, Thank you for reporting this issue with training on the VisDrone dataset. From the error message, it appears that the dataset download failed because the environment was not online. This could be due to a temporary network issue or a problem with the dataset URL. Please ensure that your internet connection is stable and try downloading the dataset manually from the provided URL to verify its availability. If the issue persists, it might be helpful to check if the dataset URL has changed or if there are any restrictions on downloading files in your current environment (such as firewall settings). If you continue to face difficulties, please provide any additional details or changes in your setup since the last successful training. This will help us better understand and address the problem. Thank you for your cooperation and patience. — Reply to this email directly, view it on GitHub <#13054 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AGH57YVRYSMVWGELMFCTUPDZE5XJ7AVCNFSM6AAAAABIRAZ3HGVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCNBQGYZTSMRVHA> . You are receiving this because you were mentioned.Message ID: ***@***.***>

-- Inder Sethi

[glenn-jocher]

@InderSethi hi Inder,

Thank you for the update and for pinpointing the issue with the URL. It seems like the extra period was indeed causing the download to fail. I appreciate your diligence in troubleshooting this problem.

We will review the dataset URLs in our documentation and scripts to ensure they are correct and prevent similar issues in the future. Meanwhile, your manual fix to remove the period and successfully download the dataset is a good interim solution.

If you encounter any further issues or have additional insights to share, please feel free to reach out.

[InderSethi]

Hi Glenn, Thanks for your quick response, However, I'm unsure how to use the offline dataset with the Yolo Hub Code. Can you do a quick fix or let me know how to use the offline dataset with the Yolo Hub code? Regards

…

On Fri, May 31, 2024 at 5:39 PM Glenn Jocher ***@***.***> wrote: @InderSethi <https://github.com/InderSethi> hi Inder, Thank you for the update and for pinpointing the issue with the URL. It seems like the extra period was indeed causing the download to fail. I appreciate your diligence in troubleshooting this problem. We will review the dataset URLs in our documentation and scripts to ensure they are correct and prevent similar issues in the future. Meanwhile, your manual fix to remove the period and successfully download the dataset is a good interim solution. If you encounter any further issues or have additional insights to share, please feel free to reach out. — Reply to this email directly, view it on GitHub <#13054 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AGH57YTEPZAXCLFUW222P33ZFBR6VAVCNFSM6AAAAABIRAZ3HGVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCNBRHEZDOMRWG4> . You are receiving this because you were mentioned.Message ID: ***@***.***>

-- Inder Sethi

[glenn-jocher]

Hi Inder,

To use an offline dataset with the YOLOv5 code from YOLO Hub, you can specify the path to your local dataset in the dataset configuration file (usually a YAML file). Here’s a quick guide:

1. Ensure your dataset is structured correctly (images and labels in expected directories).
2. Modify the dataset YAML file:
   • Replace the path value with the local path to your dataset.
   • Ensure train, val, and test paths are correctly set relative to the new path.
3. Use this YAML file path when initializing your model training in the YOLO Hub code.

This should allow the model to train using your locally stored dataset. If you need further assistance, please let me know!