Guillaume Fourret

Results 6 comments of Guillaume Fourret

Hi, just for your information: the new DINOv3 release includes a model pretrained on large-scale Remote Sensing / Satellite imagery (a dataset of 493 million images). Since RF-DETR was originally...

Hi, I tried adding LoRA layers to the detection head for fine-tuning. Although the LoRA weights appeared to learn during training, the results were worse (with a drop of about...

Hi, I believe it shouldn't be a problem to adapt YOLO11 for p2 and p6, similar to what was done in YOLOv8. You likely just need to modify the .yaml...

You can find the yaml file for p2 and p6 in #16558

I don't get where you see the 128 ch in layer 2 ? Also, what I mentioned earlier was just a quick guess on how to implement it, but I...

One thing that enhanced my attention maps was to check and reinstall the xformers library with the correct version. Didn't fix everything, but still was notably better.