How to hide warning log "potential out-of-memory errors..." about ultralytics HOT 6 OPEN

👋 Hello @SimplyOliv3r, 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! To suppress the mentioned warning while using stream=False in your tracking setup, an option is to temporarily redirect standard output, which captures these warnings. Here's a quick way to achieve this in Python:

import sys
import os

# Suppress warnings
sys.stderr = open(os.devnull, 'w')

# Your tracking code
model.track(source=videoPath, verbose=False, stream=False)

# Re-enable warnings
sys.stderr = sys.__stderr__

This code essentially diverts the stderr stream (where warnings are typically output) to os.devnull, effectively "muting" them. After running your tracking code, it's good practice to revert stderr back to its original setting to avoid missing out on other important warnings or errors.

Keep experimenting and happy coding! 😊

from ultralytics.

I do not know if I am doing something wrong, but I am using the exact code you provided and I still see the warning... I did try to catch error, redirect stderr, redirect stdout but nothing works for me. Any other suggestions?

from ultralytics.

@SimplyOliv3r hi there!

It sounds like you've tried quite a few methods to suppress the warning. Another approach could be to use the Python warnings module to filter out specific warnings. Here's a quick example of how you can do that:

import warnings

warnings.filterwarnings("ignore", message="inference results will accumulate in RAM unless `stream=True` is passed")
# Your tracking code
model.track(source=videoPath, verbose=False, stream=False)

This code snippet tells Python to ignore warnings that specifically match the provided message. Please try this out and see if it resolves your issue! 😊

from ultralytics.

That is what I have mentioned in my last response. Saying "I did try to catch error" I ment I did the exact same thing you just wrote and it did not stop warning from displaying. Im using anaconda prompt where I am running my program as python main.py. I am using python 3.11 if it helps you.

from ultralytics.

Hello @SimplyOliv3r,

Thank you for the clarification and additional details about your environment. Given the persistence of the warning even after using the warnings module, it appears that the warning might be output by the underlying system or library in a manner that bypasses standard Python warning controls.

As an alternative solution, could you try adjusting the environment variable for Python logging to suppress warnings? Here’s a quick snippet:

import os
import logging

os.environ['PYTHONWARNINGS'] = 'ignore'
logging.getLogger('py.warnings').setLevel(logging.ERROR)

# Your tracking code
model.track(source=videoPath, verbose=False, stream=False)

This code attempts to configure the logging level directly as well as the environment settings to ignore Python warnings. Let's see if this method works in your case.

from ultralytics.