Glenn Jocher

Hello, Thank you for reaching out and detailing your experience with the RT-DETR model. It's great to hear that you're exploring custom training! For the official hyperparameters, you can find...

Hello, Thank you for your follow-up and for clarifying your needs! For hyperparameters that closely match those used in the original RT-DETR paper, I recommend reviewing the configuration files and...

@lizheyong hello, Thank you for sharing your experience with training the RT-DETR model. It's great to hear that you've had success with YOLOv5, YOLOv6, and YOLOv8! To better assist you...

Hello @lizheyong, Thank you for providing additional details about your dataset and configuration. It’s helpful to know that you’re using the same format as previous YOLO versions and that the...

Hello, 1. Yes, `l1_loss` is equivalent to bbox loss. 2. Our pretrained RT-DETR models align with the original paper's settings. You can view these settings in the model configuration files....

Great to hear it's working now! If you have any more questions, feel free to ask.

@zhoujun0715 please ensure you're using the latest versions of ONNX and ONNX Runtime. If the issue persists, consider checking compatibility with your deployment environment or consult the [ONNX documentation](https://docs.ultralytics.com/integrations/onnx/) for...

Great, glad to hear it!

@jiance1 `ultralytics` 8.3.0+ has an updated head which is not the same as before. If you wish to use older YOLOv8 architecture, you can downgrade to 8.2.103

@saroshpatel the train set is used to fit the model, while the valid set evaluates its performance during training to prevent overfitting. The test set is for final evaluation after...