Open chrisliu54 opened 6 years ago
Hi, thanks for your great work! I was wondering why you chose [128, 128, 128] and [256, 256, 256] as mean and std for your dataset. What if we use those from ImageNet (ranging from 0 to 1)?
[128, 128, 128]
[256, 256, 256]
mean
std
https://github.com/namedBen/Convolutional-Pose-Machines-Pytorch/blob/540d16186cb477893dec490cec4dc9cff3ae4e9e/train_val/lsp_lspet_data.py#L120-L121
It depends on yourself .Actually,it's my personal habits when training(~.~)
Sure, thx : )
您好,请问您下载了pre-trained模型吗,作者之前的百度账号注销了,您如果下载了的话可否提供一下资源?
Hi, thanks for your great work! I was wondering why you chose
[128, 128, 128]
and[256, 256, 256]
asmean
andstd
for your dataset. What if we use those from ImageNet (ranging from 0 to 1)?https://github.com/namedBen/Convolutional-Pose-Machines-Pytorch/blob/540d16186cb477893dec490cec4dc9cff3ae4e9e/train_val/lsp_lspet_data.py#L120-L121