File size: 2,300 Bytes
1d409a9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 |
#!/usr/bin/env python3
# -*- coding:utf-8 -*-
#############################################################
# File: layernorm.py
# Created Date: Tuesday April 28th 2022
# Author: Chen Xuanhong
# Email: chenxuanhongzju@outlook.com
# Last Modified: Thursday, 20th April 2023 9:28:20 am
# Modified By: Chen Xuanhong
# Copyright (c) 2020 Shanghai Jiao Tong University
#############################################################
import torch
import torch.nn as nn
class LayerNormFunction(torch.autograd.Function):
@staticmethod
def forward(ctx, x, weight, bias, eps):
ctx.eps = eps
N, C, H, W = x.size()
mu = x.mean(1, keepdim=True)
var = (x - mu).pow(2).mean(1, keepdim=True)
y = (x - mu) / (var + eps).sqrt()
ctx.save_for_backward(y, var, weight)
y = weight.view(1, C, 1, 1) * y + bias.view(1, C, 1, 1)
return y
@staticmethod
def backward(ctx, grad_output):
eps = ctx.eps
N, C, H, W = grad_output.size()
y, var, weight = ctx.saved_variables
g = 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 = 1.0 / 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),
None,
)
class LayerNorm2d(nn.Module):
def __init__(self, channels, eps=1e-6):
super(LayerNorm2d, self).__init__()
self.register_parameter("weight", nn.Parameter(torch.ones(channels)))
self.register_parameter("bias", nn.Parameter(torch.zeros(channels)))
self.eps = eps
def forward(self, x):
return LayerNormFunction.apply(x, self.weight, self.bias, self.eps)
class GRN(nn.Module):
"""GRN (Global Response Normalization) layer"""
def __init__(self, dim):
super().__init__()
self.gamma = nn.Parameter(torch.zeros(1, dim, 1, 1))
self.beta = nn.Parameter(torch.zeros(1, dim, 1, 1))
def forward(self, x):
Gx = torch.norm(x, p=2, dim=(2, 3), keepdim=True)
Nx = Gx / (Gx.mean(dim=1, keepdim=True) + 1e-6)
return self.gamma * (x * Nx) + self.beta + x
|