models/lrm/online_render/utils/loss_utils.py

#
# 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)