ultralytics / xview-docker

xView 2018 Object Detection Challenge: Docker container submission code

Introduction 👋

Welcome to the Ultralytics software directory! Our codebase is open-source and 🔓 distributed under the AGPL-3.0 license. Explore more about Ultralytics and our cutting-edge projects at our website.

Project Overview 📄

This repository, located at https://github.com/ultralytics/xview-docker, is designed to help you dockerize and deploy machine learning models for the xView detection challenge 🔍. It should be used in combination with the trained models from our xView YOLOv3 repository.

Prerequisites 📑

To get started, you need Docker and Python 3.6 (or newer). Ensure that you have all the required packages by installing them via pip:

pip3 install -U -r requirements.txt

You should have the following packages:

• numpy for numerical operations,
• scipy for scientific computations,
• torch as the deep learning framework, and
• opencv-python for computer vision tasks.

Dockerization Steps 🐳

Below are the steps to containerize this repository for the xView challenge using run.sh.

Step 1: Copy Best Model Checkpoint

Get the best performing checkpoint from our xView YOLOv3 model:

mkdir xview-docker/checkpoints
cp xview-yolov3/checkpoints/best.pt xview-docker/checkpoints

Step 2: Build and Tag The Docker Container

Here's how to remove older images, set the right permissions for the script, build the image, and tag it appropriately (e.g., ultralytics/xview:v30):

sudo docker image prune -a
cd xview-docker && chmod +x run.sh
sudo docker build -t friendlyhello .
sudo docker tag friendlyhello ultralytics/xview:v30

Step 3: Run Container on Example Image

Test the container with the example image while specifying CPU and memory usage:

time sudo docker run -it --memory=8g --cpus=1 ultralytics/xview:v30 bash -c './run.sh /1047.tif /tmp && cat /tmp/1047.tif.txt'

Here's a sample output:

Step 4: Push to Docker Hub

Finally, upload the container to Docker Hub ready for challenge submission:

sudo docker push ultralytics/xview:v30

You can find the container now hosted at Docker Hub, prepared for the challenge 🚀.

🤝 Contribute

We welcome contributions from the community! Whether you're fixing bugs, adding new features, or improving documentation, your input is invaluable. Take a look at our Contributing Guide to get started. Also, we'd love to hear about your experience with Ultralytics products. Please consider filling out our Survey. A huge 🙏 and thank you to all of our contributors!

©️ License

Ultralytics is excited to offer two different licensing options to meet your needs:

• AGPL-3.0 License: Perfect for students and hobbyists, this OSI-approved open-source license encourages collaborative learning and knowledge sharing. Please refer to the LICENSE file for detailed terms.
• Enterprise License: Ideal for commercial use, this license allows for the integration of Ultralytics software and AI models into commercial products without the open-source requirements of AGPL-3.0. For use cases that involve commercial applications, please contact us via Ultralytics Licensing.

📬 Contact Us

For bug reports, feature requests, and contributions, head to GitHub Issues. For questions and discussions about this project and other Ultralytics endeavors, join us on Discord!