duduzai20192019
duduzai20192019
你好，上面的问题，如果在deeplab v3+，把train.py把input_shape = [512, 512]改成input_shape = [920, 720]，还会自动被reszie小吗
好难过呀，用eiseg标了好多天,然后发现它的json和labelme的不一样！！！，求解决，急，在线等！！！
> 自己写个转的方法不就行了 你好，可以参考一下你的转换代码吗，我用eiseg标注生成的json格式和labelme的json格式不一样，搞了好几天都训练不了 谢谢 邮箱：[email protected]
> 您好，是否可以提供一下EPSANet-50的预训练权重？ 你好，你找到EPSANet-50了吗？可以发我一份不
hi, how to slove it?
> Hi, > > i have tried to load_state_dict from eca_resnet50_k3557.pth.tar file and has already rename the keys, but meets a RuntimeError: Error(s) in loading state_dict for ResNet: size mismatch...
> > hi, how can i use eca_resnet50_k3557.pth.tar in the windows? .tar file cannot be decompressed! > > You don't need to decompress it. Use it directly! thanks!
> Hi, > > i have tried to open eca_resnet50_k3557.pth.tar file in linux but i am unable to open it, it seems this file is corrupted. can you please check...
> Hello！Can I directly use the pre training parameters of resnet50 instead of the pre training parameters you provide? The same ask