github-actions[bot]
commented
12 months ago 👋 Hello @sumanthvisionify, 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 # installEnvironments
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
Search before asking
YOLOv5 Component
Detection, Export, Other
Bug
I have trained YOLOv5 models and converted them to ONNX format. I am using Triton Server to serve these models for inference on a GPU with 12 GB . However, I've noticed that Triton Server is only utilizing around 2 GB of GPU memory, even when running multiple models(5) concurrently. This underutilization of GPU resources is impacting the overall inference performance and efficiency.
Triton docker logs
I1116 13:06:24.997288 1 server.cc:662] +--------------------------+---------+--------+ | Model | Version | Status | +--------------------------+---------+--------+ | model1 | 1 | READY | | model2 | 1 | READY | | model3 | 1 | READY | | model4 | 1 | READY | | model5 | 1 | READY | +--------------------------+---------+--------+
I1116 13:06:25.008435 1 metrics.cc:817] Collecting metrics for GPU 0: NVIDIA A10-12Q I1116 13:06:25.008586 1 metrics.cc:710] Collecting CPU metrics I1116 13:06:25.008858 1 tritonserver.cc:2458]
Triton Server is consistently utilizing only around 2 GB of GPU memory, regardless of the number of models running concurrently. This leads to underutilization of the GPU and suboptimal inference performance.
Note: This issue significantly impacts the inference performance of my application. I'm seeking assistance in resolving this problem to ensure efficient GPU resource utilization when serving multiple YOLOv5 models using Triton Server.
Environment
No response
Minimal Reproducible Example
No response
Additional
No response
Are you willing to submit a PR?