BlueBlueFF
BlueBlueFF
> @BlueBlueFF No. You can try it by yourself, but I think data augmentation is important on PASCAL VOC because the number of images is small. ok, I will try...
> @BlueBlueFF It will be very nice if you can post your results here. And recently i have tested fcos on other tasks such as face detection and i find...
> @BlueBlueFF I am not sure. But slightly tuning the hyper-parameters such as `object_sizes_of_interest` might be helpful. From my perspective, the anchor-free detector should at least yield _no worse_ performance...
> @BlueBlueFF Feel free to post your results here if you have some questions. In my test, fcos get 66.2 map (backbone resnet18) and 74.8 map(backbone resnet50) in voc 2007...
> @BlueBlueFF I am not sure. But have you used data augmentation, which is crucial on PASCAL VOC? I used data augmentation like ssd.
> @BlueBlueFF How about the training settings such as batch size? BatchSize is 64, and I do some new test such as not frozen the first stage in resnet and...
> @BlueBlueFF Great! If you like, you can pull request your code and models to our repository. I think it will be very useful to others. Actually my experiments are...
> > > I do the related experiments , I make FCOS as RPN in faster-rcnn ,I only get mAP 34~ when res50 as backbone, It may not work as...
> @yiyexy 感谢你。现在正在做微调阶段。也许我会尝试转换为 chatml 格式，看看会发生什么，希望得到你的结果。 so are you use qwen-chat to llava sft?
> RuntimeError: still have inflight param Do you fix this error? RuntimeError: still have inflight param