dan326326

Hello, thank you for providing the exquisite code, can you upload the training function, thank you very much！

权重问题

1

你好，博主，请问我用你的train.py来训练HRnet模型（主要是我不会写基于keras的训练函数），在官网下了权重，格式为.pth，需要改格式嘛

Hello, thanks for your code! Could you please share the weight of keras version ( model.load_weights('seg_hrnet-08-4.2117-0.9428-0.4832.hdf5')) with me? Thank you very much

NaN

11

Thank you again for your answer. Now there is a new problem, Loss is NaN at the beginning of training. Do you know how to solve this problem？ Epoch: [1/200]...

dataset processing

1

Hello,Thank you for your wonderful code！I see COLUMB data set is used in the paper, may I ask how do you deal with the mask of this data set