to tensorrt error about ultralytics

[github-actions]

👋 Hello @stupidme123, 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.

[glenn-jocher]

@stupidme123 hi there,

Thank you for reporting this issue and providing detailed information about your environment. It looks like you're encountering a dimension mismatch error when running inference with a TensorRT model.

To help us investigate and resolve this issue, could you please provide a minimal reproducible example? This will allow us to reproduce the bug on our end. You can find guidelines for creating a minimal reproducible example here. This step is crucial for us to understand the context and specifics of the problem.

Additionally, please ensure that you are using the latest versions of both torch and ultralytics. You can update them using the following commands:

pip install --upgrade torch ultralytics

From the error message, it seems that the input dimensions for the TensorRT model are not matching the expected dimensions. Specifically, the model expects dimensions within the range of [1, 3, 224, 224], but you are providing [1, 3, 640, 640]. To resolve this, you can try setting the imgsz parameter to 224 during both the export and inference stages.

Here’s an example of how to export the model with the correct image size and then run inference:

from ultralytics import YOLO

# Load the YOLOv8 model
model = YOLO("yolov8n.pt")

# Export the model to TensorRT format with the correct image size
model.export(format="engine", imgsz=224)  # creates 'yolov8n.engine'

# Load the exported TensorRT model
tensorrt_model = YOLO("yolov8n.engine")

# Run inference with the correct image size
results = tensorrt_model("https://ultralytics.com/images/bus.jpg", imgsz=224)

If you continue to experience issues, please share the minimal reproducible example, and we will be happy to assist further.