huhu
huhu
hi, i change the input size to 1/2 of original,but ir occur the error when tranning ![企业微信截图_15964342956364](https://user-images.githubusercontent.com/12590457/89150823-07249180-d592-11ea-98de-195b03c83f32.png) thanks so much
hi, the SINet.pth you give work normal. but when i train the sinet using myown data , use my pth, but it occured ![image](https://user-images.githubusercontent.com/12590457/93455617-2e9ba780-f90f-11ea-929f-e8e6d1e8fbcd.png) the layer name in my pth...
i train the v3 with my own data that with lables 0:backgrounbd and 1:portrait, just two classes ,so the n_classes=1 , but you masks labels are 1-255 , and my...
hi,hellochick: i use the code you release severel days ago , i use my data in two class(background,foreground) to train from strach 1. the input i set 512*512 2, class_num=2,(8bit...
PDM 模型
作者您好 看到研究退化的工作很开心,您是否可以将单独的pdm的训练模型放出来, 并给个大图入, lr小图出的demo? 谢谢 祝好
hi how to train my own data? my img data is detected and 15% padded. all the data in dir named 0-80 . for axample: all 0 year img in...
hi,the paper has recived by NeurIPS 2022, so when will release the trainning code, wait in hope.