3D点云重建原理及Pytorch实现 Pytorch: Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction 一种Pytorch实现方法:学习高效的点云生成方法用于稠密三维物体重建 Article: https://chenhsuanlin.bitbucket.io/3D-point-cloud-generation/paper.pdf Original TF implementation: ht
import numpy import numpy as np import torch import matplotlib.pyplot as plt import torch.nn as nn import torch.nn.functional as F import torch.optim as optim import torchvision import torchvision.transforms as transforms import tensorboard from torc
1. UserWarning: Implicit dimension choice for log_softmax has been deprecated. Change the call to include dim=X as an argument. return F.log_softmax(x) 解决方法:把 F.log_softmax(x)改为F.log_softmax(x,dim=0) , 而且我发现改为F.log_softmax(x,dim=1),这个到底哪个更合理需要进一步确认.
步骤零:安装anaconda.opencv.pytorch(这些不详细说明).复制运行代码,如果没有报错,说明已经可以了.不过大概率不行,我的会报错提示AssertionError: Torch not compiled with CUDA enabled.说明需要安装CUDA,或者安装的pytorch版本是不带CUDA的版本,需要按照以下步骤操作. 步骤一:安装CUDA 步骤二:安装cuDDN 步骤三:测试运行代码 附:电脑不支持CUDA或者不想用gpu加速深度学习的 安装CUDA 这就是用来