大佬教程收集整理的这篇文章主要介绍了Pointnet_part_seg,大佬教程大佬觉得挺不错的,现在分享给大家,也给大家做个参考。
下面的代码与之前的代码有很多重复之处,就不在一一注释,只注释个人还不太熟悉的
import torch.nn as nn
import torch.utils.data
import torch.nn.functional as F
from models.pointnet_utils import PointNetEncoder,feature_transform_reguliarzer
class get_model(nn.ModulE):
def __init__(self, k=40, normal_chAnnel=falsE):
super(get_model, self).__init__()
if normal_chAnnel:
chAnnel = 6
else:
chAnnel = 3
self.feat = PointNetEncoder(global_feat=True, feature_transform=True, chAnnel=chAnnel)
self.fc1 = nn.Linear(1024, 512)
self.fc2 = nn.Linear(512, 256)
self.fc3 = nn.Linear(256, k)
self.dropout = nn.Dropout(p=0.4) #修改了将p=0.4修改成论文中的0.7
self.bn1 = nn.batchNorm1d(512)
self.bn2 = nn.batchNorm1d(256)
self.relu = nn.ReLU()
def forWARD(self, X):
x, trans, trans_feat = self.feat(X)
x = F.relu(self.bn1(self.fc1(X)))
x = F.relu(self.bn2(self.dropout(self.fc2(X)))) #nn.Dropout-使每个位置的元素都有一定概率归0,以此来模拟现实生活中的某些频道的数据缺失,以达到数据增强的目的
x = self.fc3(X)
x = F.log_softmax(x, dim=1) #F.softmax-按照行(1)或者列(0)来做归一化,F.log_softmax-在softmax的结果上做一次log运算
return x, trans_feat
class get_loss(torch.nn.ModulE):
def __init__(self, mat_diff_loss_scale=0.001):
super(get_loss, self).__init__()
self.mat_diff_loss_scale = mat_diff_loss_scale
def forWARD(self, pred, target, trans_feat):
loss = F.nll_loss(pred, target) #F.nll_loss()-nn.CrossEntropyLoss()与NLLLoss()相同,唯一不同的是前者为我们去做log_softmax
mat_diff_loss = feature_transform_reguliarzer(trans_feat)
@R_762_10586@l_loss = loss + mat_diff_loss * self.mat_diff_loss_scale
return @R_762_10586@l_loss
以上是大佬教程为你收集整理的Pointnet_part_seg全部内容,希望文章能够帮你解决Pointnet_part_seg所遇到的程序开发问题。
如果觉得大佬教程网站内容还不错,欢迎将大佬教程推荐给程序员好友。
本图文内容来源于网友网络收集整理提供,作为学习参考使用,版权属于原作者。
如您有任何意见或建议可联系处理。小编QQ:384754419,请注明来意。