STANet
STANet copied to clipboard
official implementation of the spatial-temporal attention neural network (STANet) for remote sensing image change detection
epoch:1 后报 IndexError: boolean index did not match indexed array along dimension 0; dimension is 4194304 but corresponding boolean dimension is 65536 的错误
tcmalloc: large alloc 2147483648 bytes == 0x55577043e000 @ 0x7ff56448eb6b 0x7ff5644ae379 0x7ff463c93cde 0x7ff463c95452 0x7ff4b5cbccf3 0x7ff4b5d44158 0x7ff4b641b49f 0x7ff4b63fb870 0x7ff4b61e648a 0x7ff4b5d3529d 0x7ff4b6514aca 0x7ff4b63f770e 0x7ff4b5fbcd17 0x7ff4b791f7c4 0x7ff4b791fc8d 0x7ff4b60326e8 0x7ff4b5d333d5 0x7ff4b659b970 0x7ff4b62e8069 0x7ff55f0f42c3 0x7ff55f24e04e 0x5557057cf4b0...
'CDSA' object has no attribute 'module' 
Hello author, thank you very much for disclosing the code of this paper. However, I encountered a small problem when implementing it, and I hope to get your reply. The...
我首先运行代码中的python demo.py ,然后报标题的错误。 自己的也分段查看涉及的代码模块,打印从模型输出的图像张量:print(pred) = [1,64,256,256,],请问最后代码中的result结果的图像是256*256*3。我不知道这个demo.py中最后保存的64chanel,如何变成3的?谢谢
Thanks for sharing your code with us, I have a question for you: (1) The parameter of epoch was originally set to 200. Now I want to modify the parameter...
关于损失函数
您好~十分感谢您的工作,我有一个比较细节的问题,在损失函数的代码loss.py中,将未变化区域label值设为1,变化区域的label值为-1,与论文中loss函数部分所说的 “0,1表示未变化和变化区域”略有不同,感觉用“0,1”同样可以实现BCL损失函数,请问具体实现中改成“1,-1”这样做有什么特殊的意义吗?谢谢~
Dear Sir, Thank you for sharing such a remarkable job. can you please upload pam_net_F.pth as the baidu link you mentioned, is not available now. thanks
运行train.py时出现这个错误AssertionError: ./LEVIR-CD\A is not a valid directory