您好，我有个问题想问下，关于scaling calibration中，您对偏置b的参数初始化为1，这是有什么根据吗

self.scale_weight.data.fill_(0)
self.scale_bias.data.fill_(1)

因为根据你的公式 在限制函数中（沿用你代码的sigmoid函数），你先让可学习参数w初始化为0，那么整个限制函数中一开始就是

R(wb)

而wb一开始为1的时候，对应sigmoid的值约为0.731，把他提到方差外部，则方差变为原始方差的0.73*0.73 = 0.5329，相当于方差减半了。若一开始训练就做这么剧烈的变化，是不是对后续训练有一定影响？

我能理解权重w初始化为0，可以根据centering calibration那一节有

When the absolute value of wm is close to zero, the centering operation still relies on the running statistics.

针对这两个可学习参数的初始值设定，有进行过相关实验探讨吗

def fuse_conv_and_bn(conv, bn): # https://tehnokv.com/posts/fusing-batchnorm-and-conv/ with torch.no_grad(): # init fusedconv = torch.nn.Conv2d(conv.in_channels, conv.out_channels, kernel_size=conv.kernel_size, stride=conv.stride, padding=conv.padding, bias=True)

    # prepare filters
    w_conv = conv.weight.clone().view(conv.out_channels, -1)
    w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var)))
    fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.size()))

    # prepare spatial bias
    if conv.bias is not None:
        b_conv = conv.bias
    else:
        b_conv = torch.zeros(conv.weight.size(0))
    b_bn = bn.bias - bn.weight.mul(bn.running_mean).div(torch.sqrt(bn.running_var + bn.eps))
    fusedconv.bias.copy_(torch.mm(w_bn, b_conv.reshape(-1, 1)).reshape(-1) + b_bn)

    return fusedconv

Fusing layers... Traceback (most recent call last): File "test.py", line 263, in opt.augment) File "test.py", line 45, in test model.fuse() File "/home/zzf/Desktop/yolov3-dbb+representbatchnorm/models.py", line 402, in fuse fused = torch_utils.fuse_conv_and_bn(conv, b) File "/home/zzf/Desktop/yolov3-dbb+representbatchnorm/utils/torch_utils.py", line 83, in fuse_conv_and_bn w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var))) RuntimeError: matrix or a vector expected

把自己网络的batchnorm 改变后会报错麻烦解决以下。

您好，感谢您的工作！论文里的一些地方我没有明白，希望您能解答一下，谢谢。 ① When the Km in Eqn.(5) is set to Uc，the running mean of Km is equal to E(X) 请问这句话应该怎么理解呢？ ②在Choice of Instance Statistics中，你提到的the mean and standard division over spatial dimensions, denoted by 请问这两个值具体怎么计算？ ③ ”Since scaling calibration only restricts the feature intensity while not changing the amount of information, scaling with both channel and spatial statistics results in a similar performance.”，请问改变信息的数量是什么意思呢？