I setup a DetrForObjectDetection fine-tuning run with a custom dataset. The model loss bottomed out around 2.0 and predicts zero boxes when applied to even training images. To debug what I’d done, I stepped through the Object Detection demonstration in the documentation here: Object detection Run…

Example DeTr Object Detectors not predicting after fine tuning

huggingEars October 5, 2023, 6:52pm 3

Here is the run in Google Colab:

Topic		Replies	Views
Unable to finetune DETR 🤗Transformers	0	475	April 4, 2023
Some bug in object detect when train in macbook Beginners	1	27	August 28, 2024
Potential bug in the rt-detr v2 fine tune script 🤗Transformers	5	302	July 29, 2025
CUDA Out Of Memory when training a DETR Object detection model with compute_metrics 🤗Transformers	3	115	July 17, 2025
Inaccurate bboxes after finetuning DETR Beginners	9	430	October 6, 2024