yolov5 Docker & Self-Hosted Deployment

GitHub

Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.

57,796 stars Python Python 1 file · ~24,246 tokens #computer-vision#coreml#deep-learning#image-classification#inference#instance-segmentation#model-export#model-training
1. Pull Image (DOCKERHUB) docker pull ultralytics/yolov5:latest
2. Docker Run (1-Click Launch) docker run -d --name yolov5 --restart always ultralytics/yolov5:latest
3. Podman Run podman run -d --name yolov5 --restart always ultralytics/yolov5:latest
4. Skopeo Inspect (Zero-Pull Manifest) skopeo inspect docker://docker.io/ultralytics/yolov5:latest
5. ORAS Pull (OCI Artifact) oras pull ultralytics/yolov5:latest
utils/docker/Dockerfile 
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license

# Builds ultralytics/yolov5:latest image on DockerHub https://hub.docker.com/r/ultralytics/yolov5
# Image is CUDA-optimized for YOLOv5 single/multi-GPU training and inference

# Start FROM PyTorch image https://hub.docker.com/r/pytorch/pytorch
FROM pytorch/pytorch:2.14.1-cuda13.2-cudnn9-runtime

# Downloads to user config dir
ADD https://ultralytics.com/assets/Arial.ttf https://ultralytics.com/assets/Arial.Unicode.ttf /root/.config/Ultralytics/

# Install linux packages
ENV DEBIAN_FRONTEND=noninteractive \
    PIP_BREAK_SYSTEM_PACKAGES=1 \
    UV_BREAK_SYSTEM_PACKAGES=1
RUN apt update
RUN TZ=Etc/UTC apt install -y tzdata
RUN apt install --no-install-recommends -y gcc git zip curl htop libgl1 libglib2.0-0 libpython3-dev gnupg

# Create working directory
RUN rm -rf /usr/src/app && mkdir -p /usr/src/app
WORKDIR /usr/src/app

# Copy contents
COPY . /usr/src/app

# Install pip packages
COPY requirements.txt .
RUN uv pip install --system --no-cache -r requirements.txt albumentations comet_ml gsutil notebook \
    coremltools onnx onnxslim onnxruntime 'openvino>=2024.0.0'

# Set environment variables
ENV OMP_NUM_THREADS=1

# Cleanup
ENV DEBIAN_FRONTEND=teletype


# Usage Examples -------------------------------------------------------------------------------------------------------

# Build and Push
# t=ultralytics/yolov5:latest && sudo docker build -f utils/docker/Dockerfile -t $t . && sudo docker push $t

# Pull and Run
# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all $t

# Pull and Run with local directory access
# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all -v "$(pwd)"/datasets:/usr/src/datasets $t

# Kill all
# sudo docker kill $(sudo docker ps -q)

# Kill all image-based
# sudo docker kill $(sudo docker ps -qa --filter ancestor=ultralytics/yolov5:latest)

# Clean up
# sudo docker system prune -a --volumes

# DDP test
# python -m torch.distributed.run --nproc_per_node 2 --master_port 1 train.py --epochs 3

# GCP VM from Image
# docker.io/ultralytics/yolov5:latest