File size: 7,277 Bytes
73f9b1b |
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 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 |
#
# Copyright (C) 2023, Inria
# GRAPHDECO research group, https://team.inria.fr/graphdeco
# All rights reserved.
#
# This software is free for non-commercial, research and evaluation use
# under the terms of the LICENSE.md file.
#
# For inquiries contact george.drettakis@inria.fr
#
import torch
import torch.nn.functional as F
from torch.autograd import Variable
from math import exp
def l1_loss(network_output, gt):
return torch.abs((network_output - gt)).mean()
def l2_loss(network_output, gt):
return ((network_output - gt) ** 2).mean()
def gaussian(window_size, sigma):
gauss = torch.Tensor([exp(-(x - window_size // 2) ** 2 / float(2 * sigma ** 2)) for x in range(window_size)])
return gauss / gauss.sum()
def create_window(window_size, channel):
_1D_window = gaussian(window_size, 1.5).unsqueeze(1)
_2D_window = _1D_window.mm(_1D_window.t()).float().unsqueeze(0).unsqueeze(0)
window = Variable(_2D_window.expand(channel, 1, window_size, window_size).contiguous())
return window
def ssim(img1, img2, window_size=11, size_average=True):
channel = img1.size(-3)
window = create_window(window_size, channel)
if img1.is_cuda:
window = window.cuda(img1.get_device())
window = window.type_as(img1)
return _ssim(img1, img2, window, window_size, channel, size_average)
def _ssim(img1, img2, window, window_size, channel, size_average=True):
mu1 = F.conv2d(img1, window, padding=window_size // 2, groups=channel)
mu2 = F.conv2d(img2, window, padding=window_size // 2, groups=channel)
mu1_sq = mu1.pow(2)
mu2_sq = mu2.pow(2)
mu1_mu2 = mu1 * mu2
sigma1_sq = F.conv2d(img1 * img1, window, padding=window_size // 2, groups=channel) - mu1_sq
sigma2_sq = F.conv2d(img2 * img2, window, padding=window_size // 2, groups=channel) - mu2_sq
sigma12 = F.conv2d(img1 * img2, window, padding=window_size // 2, groups=channel) - mu1_mu2
C1 = 0.01 ** 2
C2 = 0.03 ** 2
ssim_map = ((2 * mu1_mu2 + C1) * (2 * sigma12 + C2)) / ((mu1_sq + mu2_sq + C1) * (sigma1_sq + sigma2_sq + C2))
if size_average:
return ssim_map.mean()
else:
return ssim_map.mean(1).mean(1).mean(1)
import torch
import torch.nn as nn
from taming.modules.losses.vqperceptual import * # TODO: taming dependency yes/no?
class LPIPSWithDiscriminator(nn.Module):
def __init__(self, disc_start, logvar_init=0.0, kl_weight=1.0, pixelloss_weight=1.0,
disc_num_layers=3, disc_in_channels=3, disc_factor=1.0, disc_weight=1.0,
perceptual_weight=1.0, use_actnorm=False, disc_conditional=False,
disc_loss="hinge"):
super().__init__()
assert disc_loss in ["hinge", "vanilla"]
self.kl_weight = kl_weight
self.pixel_weight = pixelloss_weight
self.perceptual_loss = LPIPS().eval()
self.perceptual_weight = perceptual_weight
# output log variance
self.logvar = nn.Parameter(torch.ones(size=()) * logvar_init)
self.discriminator = NLayerDiscriminator(input_nc=disc_in_channels,
n_layers=disc_num_layers,
use_actnorm=use_actnorm
).apply(weights_init)
self.discriminator_iter_start = disc_start
self.disc_loss = hinge_d_loss if disc_loss == "hinge" else vanilla_d_loss
self.disc_factor = disc_factor
self.discriminator_weight = disc_weight
self.disc_conditional = disc_conditional
def calculate_adaptive_weight(self, nll_loss, g_loss, last_layer=None):
if last_layer is not None:
nll_grads = torch.autograd.grad(nll_loss, last_layer, retain_graph=True)[0]
g_grads = torch.autograd.grad(g_loss, last_layer, retain_graph=True)[0]
else:
nll_grads = torch.autograd.grad(nll_loss, self.last_layer[0], retain_graph=True)[0]
g_grads = torch.autograd.grad(g_loss, self.last_layer[0], retain_graph=True)[0]
d_weight = torch.norm(nll_grads) / (torch.norm(g_grads) + 1e-4)
d_weight = torch.clamp(d_weight, 0.0, 1e4).detach()
d_weight = d_weight * self.discriminator_weight
return d_weight
def forward(self, inputs, reconstructions, optimizer_idx,
global_step, last_layer=None, cond=None, split="train"):
rec_loss = torch.abs(inputs.contiguous() - reconstructions.contiguous())
if self.perceptual_weight > 0:
p_loss = self.perceptual_loss(inputs.contiguous(), reconstructions.contiguous())
rec_loss = rec_loss + self.perceptual_weight * p_loss
# nll_loss = rec_loss / torch.exp(self.logvar) + self.logvar
# now the GAN part
if optimizer_idx == 0:
# generator update
logits_fake = self.discriminator(reconstructions.contiguous())
# g_loss = -torch.mean(logits_fake)
g_loss = F.relu(1 - logits_fake).mean()
# if self.disc_factor > 0.0:
# try:
# d_weight = self.calculate_adaptive_weight(nll_loss, g_loss, last_layer=last_layer)
# except RuntimeError:
# assert not self.training
# d_weight = torch.tensor(0.0)
# else:
# d_weight = torch.tensor(0.0)
# disc_factor = adopt_weight(self.disc_factor, global_step, threshold=self.discriminator_iter_start)
# loss = d_weight * disc_factor * g_loss
# return loss, log
return g_loss
if optimizer_idx == 1:
# second pass for discriminator update
logits_real = self.discriminator(inputs.contiguous().detach())
logits_fake = self.discriminator(reconstructions.contiguous().detach())
# disc_factor = adopt_weight(self.disc_factor, global_step, threshold=self.discriminator_iter_start)
# d_loss = disc_factor * self.disc_loss(logits_real, logits_fake)
# log = {"{}/disc_loss".format(split): d_loss.clone().detach().mean(),
# "{}/logits_real".format(split): logits_real.detach().mean(),
# "{}/logits_fake".format(split): logits_fake.detach().mean()
# }
# return d_loss, log
d_loss = self.disc_loss(logits_real, logits_fake)
return d_loss
import torch
from chamfer_distance import ChamferDistance
# 初始化 Chamfer Distance 模块
chamfer_dist_module = ChamferDistance()
def calculate_chamfer_loss(pred, gt):
"""
计算 Chamfer Distance 损失
Args:
pred (torch.Tensor): 预测点云，维度为 (batch_size, num_points, 3)
gt (torch.Tensor): 真实点云，维度为 (batch_size, num_points, 3)
chamfer_dist_module (ChamferDistance): 预先初始化的 Chamfer Distance 模块
Returns:
torch.Tensor: Chamfer Distance 损失
"""
# 计算 Chamfer Distance
dist1, dist2, idx1, idx2 = chamfer_dist_module(pred, gt)
loss = (torch.mean(dist1) + torch.mean(dist2)) / 2
return loss
if __name__ == "__main__":
discriminator = LPIPSWithDiscriminator(disc_start=0, disc_weight=0.5)
|