-
在哪可以设置只保存最终最优模型文件啊，就像yolov8只保存last.pt和best.pt，现在每epoch都会保存一个快700M的pth文件，epoch默认72，硬盘没那么大地方，作者能说说在哪设置不，我把配置文件里选项看完了，没发现。
-
Sorry to bother you, but how to set the file parameters when using two Gpus or one GPU? Is it set directly through the command? When I tried this method, I got an error as shown in the figure below:
…
-
As in the main DETR there is a way of using the models that were pretrained on coco by deleting the heads for use that on a specific dataset (custom), I tried to make the same here but it gives an err…
ver0z updated
2 years ago
-
论文中说不需要额外训练识别器，所以DiG模型的权重使用的是预训练权重而不是微调权重吗？
检测器使用的是微调权重？
-
Hi, guys,
I am learning about Deformable-DETR these days, and I am curious about the implementation of `HungarianMatcher`,
1. Why match the bboxes per batch, as [TORCH.CDIST](https://pytorch.org/do…
-
Is there a pre-training weight for the pytorch version of RTDETR?
-
this is my command:
python3 export_rtdetr_ultralytics.py -w rtdetr-l.pt --simplify --batch 4 -s 640
and got this error:
```
python3 export_rtdetr_ultralytics.py -w rtdetr-l.pt --simplify -…
-
-
Hi,
For object detection, I made below changes and training and inferencing was successful.
del checkpoint["model"]["class_embed.weight"]
del checkpoint["model"]["class_embed.bias"]
For Inst…
-
Hi, your work is great! But I am confused about the location tokens you used in Decoder, could you provide more details it?