cfzd / FcaNet

不是只要修改一行吗，怎么里面还要设置这么多参数

@XFR1998
开源代码和论文里的代码是完全等价的，只不过为了大家使用方便，同时兼容更多的实验，我们开源的时候做了很多封装和脚手架代码。你可以对比一下以下代码和论文代码：

Line 78 in aa5fb63

    
           self.register_buffer('weight', self.get_dct_filter(height, width, mapper_x, mapper_y, channel))

FcaNet/model/layer.py

Lines 91 to 98 in aa5fb63

    
           def forward(self, x): 
        
               assert len(x.shape) == 4, 'x must been 4 dimensions, but got ' + str(len(x.shape)) 
        
               # n, c, h, w = x.shape 
        
               x = x * self.weight 
        
               result = torch.sum(x, dim=[2,3]) 
        
               return result

	def forward(self, x):
	assert len(x.shape) == 4, 'x must been 4 dimensions, but got ' + str(len(x.shape))
	# n, c, h, w = x.shape

	x = x * self.weight

	result = torch.sum(x, dim=[2,3])
	return result

代码好像和论文里说的不太一样也？