Closed longmalongma closed 3 years ago
I cannot really solve your implementation problems for you... Some hints: https://github.com/hkchengrex/Mask-Propagation/blob/b5d8e61c87e1944426c3aed43685fd0eb336353a/model/network.py#L43 tells you how the tensor is arranged. Indexing in the time dimension gives you features for different frames.
tells you how the tensor is arranged. Indexing in the time dimension gives you features for different frames.
这里mk形状中,B是batch?CK是特征通道数?T是帧的数目?W,H分别为像素的宽和高,这样的理解对吗?
Yes.
Yes.
Ok, thanks!
您好,有个问题想请教下,
这是将所有内存帧和当前帧的内存读取操作,如果说只利用当前帧的前一帧进行匹配的话,如果去内存帧的最后保留的一帧,换句话说如何取前一帧?代码中如何实现?感谢。