Yi Jiang
how about the result?
> Dear All, > > This is more a feature request than a bug; anyway, can you test/utilize your method on the DF20 dataset? We include much more metadata within...
you should set BASE_LR as 0.000025 instead of 0.0025.
> When first running it, the learning rate is default, i.e.0.000025, got a lower AP than the author's log, then I changed the learning rate. maybe you need a small...
i also have the problem.... in addition,did you meet the problem that the loss is nan(loss_bbox is nan),from Iteration 45000??
@NimaBoscarino Hi, we are interested in adding the models and a web demo to Hugging Face. it will be great if you do this
> @iFighting Excellent! I can add the models to Hugging Face, and then I'll get started on pushing a web demo as well, starting with the SOT task. I might...
@yqy2001 Sorry，We're working on the code with the highest priority, and we'll be releasing it as soon as possible(in 24 hours)
> Jiawei-Yang @Jiawei-Yang thanks for your kindly attention, we will release the training code of VQVAE in several days
i have train the focal loss with doformable conv several times i found that the mAP is lower than the origin * lr = 0.0005，warmup_lr = 0.00005 * [email protected] =...