kennen

I use cocostuff config on my own dataset， the pixel of my label image ：  0：background 1：human .   and self.maaping is 「0，1」 config.numclasses：2  but meaniu and bestiou always 0.5 发自我的iPhone...

Okay，I will try it. Thank u very much. best wishes 发自我的iPhone ------------------ Original ------------------ From: gulraizk94 ***@***.***> Date: Fri,Aug 20,2021 8:45 PM To: HRNet/HRNet-Semantic-Segmentation ***@***.***> Cc: Delete ***@***.***>, Author ***@***.***>...

anchor question: I use cityspaces with same configuration. I set config.TRAIN.BATCH_SIZE_GPU >1， config.TSET.BATCH_SIZE_GPU =1. train is normal, but the validate is error.  the validate only work in  config.TRAIN.BATCH_SIZE_GPU =1. it seems...

1.I have found that you use the train_batch_size_gpu in testloader in tools/train.py.  2.you resize image and label in function multi_scale_aug, but multi_scale is false in Test.  It leads to multi_sacle...

> I've discovered part of the problem but my attempt at fixing it still results in an error. The backbone layers we need to draw from in the Small model...

oh, thanks for your reply， I will study your paper. best wishes!  ------------------ 原始邮件 ------------------ 发件人: "xuebinqin/U-2-Net" ***@***.***>; 发送时间: 2021年8月17日(星期二) 下午4:37 ***@***.***>; 抄送: "Shente ***@***.******@***.***>; 主题: Re: [xuebinqin/U-2-Net] where is the val code in u2net_train?...

lkpt += kpt_loss_factor*((1 - torch.exp(-d/(s*(4*sigmas**2)+1e-9)))*kpt_mask).mean() its actually affect the offset of keypoint > @SashaAlderson There is no problem with the loss function. I have retrained the model and they are...

> ### Verify it's not a duplicate bug report > * [x] I searched for similar bugs reported on GitHub and nobody has reported a similar issue. [Search all issuees](https://github.com/ai-genie/vscode-chatgpt/issues?q=)....