cannot set tensor for ultralytics/examples/YOLOv8-OpenCV-int8-tflite-Python /main.py about ultralytics HOT 4 CLOSED

👋 Hello @czy10383, 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.

@czy10383 hello! Thank you for the detailed report and the suggested fix for the ValueError you encountered with the YOLOv8 OpenCV-int8-tflite example. Your approach to adjust the data type to INT8 by scaling and adding the zero point is correct for handling quantized models.

We appreciate your contribution to improving the example code. If you're willing, you can directly contribute by submitting a pull request with your proposed changes. This would be a great help to the community, ensuring that others do not encounter the same issue.

If you prefer not to submit a PR, we'll review the issue internally and update the example accordingly.

Thank you again for your input and for using Ultralytics YOLOv8! 🚀

from ultralytics.

@glenn-jocher thank you for the confirmation. I have submitted a PR, thank you :)

from ultralytics.

@czy10383, thank you for submitting the PR! We appreciate your contribution to improving the project. The team will review it shortly. 😊🚀

from ultralytics.