STANet icon indicating copy to clipboard operation
STANet copied to clipboard

使用demo时,出现下面的错误

Open linglangqiuxun opened this issue 1 year ago • 6 comments

in fromarray mode, rawmode = _fromarray_typemap[typekey] KeyError: ((1, 1, 64), '|u1')

linglangqiuxun avatar Mar 11 '23 12:03 linglangqiuxun

同样的错误

WesternTrail avatar Mar 17 '23 11:03 WesternTrail

修改CDFA_model中代码 self.dist = F.pairwise_distance(self.feat_A, self.feat_B, keepdim=True) # 特征距离 为 self.feat_A = self.feat_A.permute(0, 2, 3, 1) self.feat_B = self.feat_B.permute(0, 2, 3, 1) self.dist = F.pairwise_distance(self.feat_A, self.feat_B, keepdim=True) # 特征距离 self.dist = self.dist.permute(0,3, 1, 2)

mhdwhx avatar Mar 17 '23 11:03 mhdwhx

感谢,我降低torch版本可行。发自我的华为手机-------- 原始邮件 --------发件人: mhdkssygit @.>日期: 2023年3月17日周五 晚上7:42收件人: justchenhao/STANet @.>抄送: 陈铭 @.>, Comment @.>主 题: Re: [justchenhao/STANet] 使用demo时,出现下面的错误 (Issue #99) 修改CDFA_model中代码 self.dist = F.pairwise_distance(self.feat_A, self.feat_B, keepdim=True) # 特征距离 为 self.feat_A = self.feat_A.permute(0, 2, 3, 1) self.feat_B = self.feat_B.permute(0, 2, 3, 1) self.dist = F.pairwise_distance(self.feat_A, self.feat_B, keepdim=True) # 特征距离 self.dist = self.dist.permute(0,3, 1, 2)

—Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you commented.Message ID: @.***>

WesternTrail avatar Mar 19 '23 03:03 WesternTrail

self.feat_A = self.feat_A.permute(0, 2, 3, 1) self.feat_B = self.feat_B.permute(0, 2, 3, 1) self.dist = F.pairwise_distance(self.feat_A, self.feat_B, keepdim=True) # 特征距离 self.dist = self.dist.permute(0,3, 1, 2)

That is very useful for me. Thank you very much!!!

TingFinn avatar Mar 20 '23 07:03 TingFinn

修改CDFA_model中代码 self.dist = F.pairwise_distance(self.feat_A, self.feat_B, keepdim=True) # 特征距离 为 self.feat_A = self.feat_A.permute(0, 2, 3, 1) self.feat_B = self.feat_B.permute(0, 2, 3, 1) self.dist = F.pairwise_distance(self.feat_A, self.feat_B, keepdim=True) # 特征距离 self.dist = self.dist.permute(0,3, 1, 2)

It works, thanks.

1596892709 avatar Oct 12 '23 06:10 1596892709

感谢,我降低torch版本可行。发自我的华为手机-------- 原始邮件 --------发件人: mhdkssygit @.>日期: 2023年3月17日周五 晚上7:42收件人: justchenhao/STANet _@**._>抄送: 陈铭 _@.>, Comment @._>主 题: Re: [justchenhao/STANet] 使用demo时,出现下面的错误 (Issue #99) 修改CDFA_model中代码 self.dist = F.pairwise_distance(self.feat_A, self.feat_B, keepdim=True) # 特征距离 为 self.feat_A = self.feat_A.permute(0, 2, 3, 1) self.feat_B = self.feat_B.permute(0, 2, 3, 1) self.dist = F.pairwise_distance(self.feat_A, self.feat_B, keepdim=True) # 特征距离 self.dist = self.dist.permute(0,3, 1, 2) —Reply to this email directly, view it on GitHub, or unsubscribe.You are receiving this because you commented.Message ID: _@_.*>

请问一下你用预训练权重跑的 demo的结果怎么样我跑的结果很零碎

hellohandsome avatar Mar 06 '24 12:03 hellohandsome