PyTorch 中 BatchNorm2d 的导数

Question

在我的网络中，我想在正向传播中计算我的网络的正向传播和反向传播。为此，我必须手动定义前向传递层的所有后向传递方法。
对于激活函数，这很简单。对于线性层和转换层，它也运行良好。但我真的在与 BatchNorm 作斗争。由于 BatchNorm 论文仅讨论一维情况：到目前为止，我的实现如下所示：

def backward_batchnorm2d(input, output, grad_output, layer):
    gamma = layer.weight
    beta = layer.bias
    avg = layer.running_mean
    var = layer.running_var
    eps = layer.eps
    B = input.shape[0]

    # avg, var, gamma and beta are of shape [channel_size]
    # while input, output, grad_output are of shape [batch_size, channel_size, w, h]
    # for my calculations I have to reshape avg, var, gamma and beta to [batch_size, channel_size, w, h] by repeating the channel values over the whole image and batches

    dL_dxi_hat = grad_output * gamma
    dL_dvar = (-0.5 * dL_dxi_hat * (input - avg) / ((var + eps) ** 1.5)).sum((0, 2, 3), keepdim=True)
    dL_davg = (-1.0 / torch.sqrt(var + eps) * dL_dxi_hat).sum((0, 2, 3), keepdim=True) + dL_dvar * (-2.0 * (input - avg)).sum((0, 2, 3), keepdim=True) / B
    dL_dxi = dL_dxi_hat / torch.sqrt(var + eps) + 2.0 * dL_dvar * (input - avg) / B + dL_davg / B # dL_dxi_hat / sqrt()
    dL_dgamma = (grad_output * output).sum((0, 2, 3), keepdim=True)
    dL_dbeta = (grad_output).sum((0, 2, 3), keepdim=True)
    return dL_dxi, dL_dgamma, dL_dbeta

当我用 torch.autograd.grad() 检查梯度时，我注意到 dL_dgamma 和 dL_dbeta 是正确的，但是 dL_dxi 是不正确的（很多）。但我找不到我的错误。我的错误在哪里？

作为参考，这里是 BatchNorm 的定义：

下面是一维情况的导数公式：

Answer 1

def backward_batchnorm2d(input, output, grad_output, layer):
    gamma = layer.weight
    gamma = gamma.view(1,-1,1,1) # edit
    # beta = layer.bias
    # avg = layer.running_mean
    # var = layer.running_var
    eps = layer.eps
    B = input.shape[0] * input.shape[2] * input.shape[3] # edit

    # add new
    mean = input.mean(dim = (0,2,3), keepdim = True)
    variance = input.var(dim = (0,2,3), unbiased=False, keepdim = True)
    x_hat = (input - mean)/(torch.sqrt(variance + eps))
    
    dL_dxi_hat = grad_output * gamma
    # dL_dvar = (-0.5 * dL_dxi_hat * (input - avg) / ((var + eps) ** 1.5)).sum((0, 2, 3), keepdim=True) 
    # dL_davg = (-1.0 / torch.sqrt(var + eps) * dL_dxi_hat).sum((0, 2, 3), keepdim=True) + dL_dvar * (-2.0 * (input - avg)).sum((0, 2, 3), keepdim=True) / B
    dL_dvar = (-0.5 * dL_dxi_hat * (input - mean)).sum((0, 2, 3), keepdim=True)  * ((variance + eps) ** -1.5) # edit
    dL_davg = (-1.0 / torch.sqrt(variance + eps) * dL_dxi_hat).sum((0, 2, 3), keepdim=True) + (dL_dvar * (-2.0 * (input - mean)).sum((0, 2, 3), keepdim=True) / B) #edit
    
    dL_dxi = (dL_dxi_hat / torch.sqrt(variance + eps)) + (2.0 * dL_dvar * (input - mean) / B) + (dL_davg / B) # dL_dxi_hat / sqrt()
    # dL_dgamma = (grad_output * output).sum((0, 2, 3), keepdim=True) 
    dL_dgamma = (grad_output * x_hat).sum((0, 2, 3), keepdim=True) # edit
    dL_dbeta = (grad_output).sum((0, 2, 3), keepdim=True)
    return dL_dxi, dL_dgamma, dL_dbeta

因为你没有上传你的正向代码，所以如果你的伽马形状大小是1，你需要将它重新整形为[1,gamma.shape[0],1,1]。
公式遵循 1D，其中比例因子是批量大小的总和。然而，在 2D 中，总和应该在 3 个维度之间，所以 B = input.shape[0] * input.shape[2] * input.shape[3].
running_mean 和 running_var 仅在 test/inference 模式下使用，我们不会在训练中使用它们（您可以在 the paper 中找到它）。您需要的均值和方差是根据输入计算得出的，您可以将均值、方差和 x_hat = (x-mean)/sqrt(variance + eps) 存储到您的对象 layer 中，或者像我在上面的代码中所做的那样重新计算 # add new。然后将它们替换为dL_dvar, dL_davg, dL_dxi.
你的dL_dgamma应该是不正确的，因为你把output的梯度自己乘了，应该修改成grad_output * x_hat.

PyTorch 中 BatchNorm2d 的导数

Derivative of BatchNorm2d in PyTorch

derivative

pytorch

autograd