📜  组规范化 - 无论代码示例

📅  最后修改于: 2022-03-11 14:59:37.857000             🧑  作者: Mango

代码示例1
由此可以看出,GN和BN是有很多相似之处的,代码相比较BN改动只有一两行而已,论文给出的代码实现如下:
def GroupNorm(x, gamma, beta, G, eps=1e-5):
    # x: input features with shape [N,C,H,W]
    # gamma, beta: scale and offset, with shape [1,C,1,1]
    # G: number of groups for GN
    N, C, H, W = x.shape
    x = tf.reshape(x, [N, G, C // G, H, W])
    mean, var = tf.nn.moments(x, [2, 3, 4], keep dims=True)
    x = (x - mean) / tf.sqrt(var + eps)
    x = tf.reshape(x, [N, C, H, W])
    return x * gamma + beta