Francesco Oliva

Probably you have at least one image with a wrong xml annotation, you could use the ` __getitem__` function inside voc_dataset.py to look for it i.e. ``` if len(boxes) ==...

I had your same error, I completed the training using a lower learning rate i.e --lr 0.0001

Also I can see from your screenshot it looks like you are using mobilenet training parameters, or am I wrong? check in the Readme the Vgg model training instructions: `python...

Hi there, In my project I used a pre-trained RT-DETR from [ultralytics](https://docs.ultralytics.com/models/rtdetr/) so the network output layer might be different from your model. Also I used 640x640 hardcoded input, I...

Thanks all right, I'll take a look at it as soon as I can 👍

Yes is a completely different input/output format to the model I used for this project. 

Yes but not too soon, I have a full-time job so I can work on my GitHub projects only in my spare time.

Sorry a bit late :smile: , I currently wrote the code to infer this model [here](https://github.com/olibartfast/object-detection-inference/blob/master/detectors/src/RtDetr.cpp)

Hi, Unfortunately I never tested a device that supports ROCm, so this project doesn't support it. I think the best guess to use ROCm is to have Libtorch built with...

**Hi,** Thanks for the report. It seems there's a bug in the propagation of the `DEFAULT_BACKEND` argument from the root project to the subproject `inferenceengines`. I will try to fix...