Export tensorrt to infer an error when specifying the image size about ultralytics HOT 1 OPEN

Hello! 😊 It looks like you're encountering an issue where the input size during the export doesn't match the model's maximum input size specified during the conversion process.

When exporting your model to TensorRT using a custom imgsz (image size), ensure that the exported model's inference input size matches the specified imgsz. The error you're encountering typically happens when there's a mismatch in the sizes expected by the model.

You can try specifying the imgsz during inference to match the size used during the export. Here's a snippet that might help:

# Assuming you've already exported your model as shown in your question...

# Load your TensorRT model
model_trt = YOLO('path_to_exported_engine_file.engine')

# Specify the same imgsz for inference
results = model_trt.predict('path_to_your_image_or_video', imgsz=2048)

This makes sure that both during export and inference, the model works with the same image dimensions, thus avoiding any size mismatch issues.

If you continue experiencing issues or have more questions, feel free to ask. Good luck! 🚀

from ultralytics.