HRNet-Semantic-Segmentation Do anyone reproduce the result on LIP dataset?

I use the environment that the author suggested, but I can not reproduce the result. Have anyone done? I run the code three times, but every time the result is :50.76? Why?

Nov 04 '20 05:11 tjpulkl

I use this pretrained model when I trained on LIP dataset.

Nov 04 '20 05:11 tjpulkl

@tjpulkl Any luck on this?

Jun 09 '21 19:06 shambhavi-ml

No, do you have any suggestions to me?

Jun 10 '21 01:06 tjpulkl

50.76 is the results with the config FLIP=False paper's results is FLIP=True But I can't get the same Mean_Acc as author by testing the lip model released

Sep 07 '21 08:09 Margrate

could you give me your result on lip validation dataset?

Sep 07 '21 09:09 tjpulkl

train on val(sample 2000 images) mIoU=50.93 testval(10000 images). mIoU:0.5544, Pixel_Acc:0.8807, Mean_Acc:0.6617

add My Wechat: 13713916489 加我微信，交流一下HRNet

------------------ 原始邮件 ------------------ 发件人: "HRNet/HRNet-Semantic-Segmentation" @.>; 发送时间: 2021年9月7日(星期二) 下午5:47 @.>; @.@.>; 主题: Re: [HRNet/HRNet-Semantic-Segmentation] Do anyone reproduce the result on LIP dataset? (#198)

could you give me your result on lip validation dataset?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.

Sep 07 '21 12:09 Margrate