yolo_world about ultralytics HOT 2 OPEN

👋 Hello @FengJin-cv, thank you for your interest in Ultralytics YOLOv8 🚀! We recommend a visit to the Docs for new users where you can find many Python and CLI usage examples and where many of the most common questions may already be answered.

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.

Join the vibrant Ultralytics Discord 🎧 community for real-time conversations and collaborations. This platform offers a perfect space to inquire, showcase your work, and connect with fellow Ultralytics users.

Install

Pip install the ultralytics package including all requirements in a Python>=3.8 environment with PyTorch>=1.8.

pip install ultralytics

Environments

YOLOv8 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 Ultralytics CI tests are currently passing. CI tests verify correct operation of all YOLOv8 Modes and Tasks on macOS, Windows, and Ubuntu every 24 hours and on every commit.

from ultralytics.

Hello!

It sounds like you're encountering an issue where yolo_world is not detecting targets despite having 80 categories. This is likely related to the specifics of the image or model settings. Here are a few things you can check:

• Input Image: Ensure the input image is properly preprocessed and sized according to the model requirements.
• Model Weights: Make sure the model is loaded with the correct pretrained weights.
• Threshold Settings: Check if the confidence threshold and non-max suppression settings are appropriately configured.

You could try adjusting the confidence threshold with a simple code snippet if using the Python API:

from ultralytics import YOLO

# Load the model
model = YOLO('yolo_world.pt')

# Detect with a lower confidence threshold
results = model('path/to/image.jpg', conf=0.1)
results.show()

If you’re still facing issues, please provide some details about the implementation or errors for more specific guidance.

Best regards!

from ultralytics.