FATAL ERROR! reclaim_blob_allocator get wild allocator in Jetson Nano with NCNN Inference about ultralytics HOT 2 OPEN

👋 Hello @VanillaMacchiato, 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.

@VanillaMacchiato hello,

Thank you for reporting this issue and for providing a detailed description along with your modifications. It's great to see your initiative in troubleshooting the problem! Let's address your concerns:

1. Reproducibility: Your steps to replicate the issue are clear and comprehensive. This will help us reproduce the bug on our end. Thank you for that!

2. Version Check: Please ensure you are using the latest versions of torch and ultralytics. You can upgrade them using:

   pip install --upgrade torch ultralytics

3. Code Modification: Regarding your modification to avoid using the with statement:

   ex = self.net.create_extractor()
   ex.input(self.net.input_names()[0], mat_in)
   y = [np.array(ex.extract(x)[1])[None] for x in sorted(self.net.output_names())]

   While this change seems to resolve the error, the with statement is generally used to ensure that resources are properly managed and released. Removing it might lead to resource leaks or other unintended side effects, especially in long-running applications.

4. Next Steps:

   • Testing: Continue monitoring the memory usage and performance over extended periods to ensure no resource leaks occur.
   • PR Submission: If you are confident in your changes and have thoroughly tested them, feel free to submit a Pull Request (PR). We appreciate contributions from the community!

If you encounter any further issues or have additional questions, please let us know. We're here to help!

from ultralytics.