pytorch 自定义函数

介绍：https://zhuanlan.zhihu.com/p/344802526
主要构建 static method forward 和 backward

比如 layernorm: 参考：https://github.com/zhangyi-3/KBNet/blob/main/basicsr/models/archs/kb_utils.py

导数的推导：https://blog.csdn.net/qinduohao333/article/details/132309091

import torch
import torch.nn as nn
import torch.nn.functional as Fclass LayerNormFunction(torch.autograd.Function):@staticmethoddef forward(ctx, x, weight, bias, eps):ctx.eps = epsN, C, H, W = x.size()mu = x.mean(1, keepdim=True)var = (x - mu).pow(2).mean(1, keepdim=True)# print('mu, var', mu.mean(), var.mean())# d.append([mu.mean(), var.mean()])y = (x - mu) / (var + eps).sqrt()weight, bias, y = weight.contiguous(), bias.contiguous(), y.contiguous()  # avoid cuda errorctx.save_for_backward(y, var, weight)y = weight.view(1, C, 1, 1) * y + bias.view(1, C, 1, 1)return y@staticmethoddef backward(ctx, grad_output):eps = ctx.epsN, C, H, W = grad_output.size()# y, var, weight = ctx.saved_variablesy, var, weight = ctx.saved_tensorsg = grad_output * weight.view(1, C, 1, 1)mean_g = g.mean(dim=1, keepdim=True)mean_gy = (g * y).mean(dim=1, keepdim=True)gx = 1. / torch.sqrt(var + eps) * (g - y * mean_gy - mean_g)return gx, (grad_output * y).sum(dim=3).sum(dim=2).sum(dim=0), grad_output.sum(dim=3).sum(dim=2).sum(dim=0), Noneclass LayerNorm2d(nn.Module):def __init__(self, channels, eps=1e-6, requires_grad=True):super(LayerNorm2d, self).__init__()self.register_parameter('weight', nn.Parameter(torch.ones(channels), requires_grad=requires_grad))self.register_parameter('bias', nn.Parameter(torch.zeros(channels), requires_grad=requires_grad))self.eps = epsdef forward(self, x):return LayerNormFunction.apply(x, self.weight, self.bias, self.eps)