Non-local_pytorch
Non-local_pytorch copied to clipboard
implement in other network
SO if I want to add nonblock into my own experiment I can only add NONLocalBlock2D() into somewhere of the network ? and I did't need to change other params ?
Yes, but the size of feature map should not be too small, such as 1x1, 2x2.
Yes, but the size of feature map should not be too small, such as 1x1, 2x2.
感谢提供的代码!想请教一个问题,我在孪生神经网络两个分支分别加了Non-local模块,其中一个分支的feature map 大小是55512,只要在这个后面加Non-local模块,效果就非常差,另外一个分支是2121512,就没有问题,是因为尺寸太小了吗?请问为什么尺寸小效果会不好呢?