CenterPoint 工程复现
注意:本文中使用版本:BEVerse工程下的mmdet3d (MMDet3d v0.17.3)版本,MMDetection3D中其他版本的使用大同小异。
欢迎有疑问的同学在下方留言,如果觉得有用的话,可以点赞+收藏,再次表示感谢!
参考:
1. nuscenes官方使用举例
2. CenterPoint 论文速读
3. BEVerse 论文速读
一. 下载和安装工程
详细参考:
注意:本文中使用版本:BEVerse工程下的mmdet3d (MMDet3d v0.17.3)版本,MMDetection3D中其他版本的使用大同小异。
欢迎有疑问的同学在下方留言,如果觉得有用的话,可以点赞+收藏,再次表示感谢!
参考:
1. nuscenes官方使用举例
2. CenterPoint 论文速读
3. BEVerse 论文速读
详细参考:
CVPR 2021目标检测与语义分割论文分类与复现指南
计算机视觉中,目标检测与语义分割是两大核心任务,而每年顶会论文的梳理能高效指引算法演进方向。从深度学习基础原理看,检测与分割模型经历了从卷积到Transformer的范式迁移,使端到端训练与集合预测成为主流。这类技术革新不仅提升精度,还催生出统一的多任务框架,在自动驾驶与智能安防有广泛应用。CVPR 2021正值Transformer在视觉领域爆发,大量论文围绕稀疏查询、标签分配优化、半监督学习及3D感知展开。这里将检测与分割论文按问题类型归档,梳理代表工作与源码信息,并分享复现中的环境配置、指标对齐等实操
从代码到部署:手把手复现CenterPoint(PyTorch版)在KITTI数据集上的完整流程
本文详细介绍了如何在KITTI数据集上从零实现CenterPoint(PyTorch版)的完整流程,包括环境配置、数据处理、模型训练与调优、评估可视化及部署优化。CenterPoint作为CVPR 2021提出的3D目标检测方法,以其旋转不变性和高效跟踪能力在自动驾驶领域表现卓越。通过实战指南,读者可快速掌握点云数据处理和模型部署技巧。
CVPR2021 CenterPoint源码解读:从VoxelNet到两阶段优化的完整实现细节
本文深度解析了CVPR 2021 CenterPoint模型的完整实现细节,从VoxelNet体素化、稀疏卷积Backbone,到基于中心点的检测头与两阶段精修机制。文章提供了从环境搭建、数据预处理到核心代码模块(如热力图生成、关键点特征提取与MLP Refiner)的实战指南,并分享了训练策略、多任务损失调优及可视化调试等关键工程实践,助力开发者深入理解并复现这一高效的3D目标检测框架。
避坑指南:MM3D+CenterPoint环境配置中的5个常见错误及解决方法(附NuScenes mini数据集处理技巧)
本文详细解析了在MMDetection3D框架中部署CenterPoint算法并处理NuScenes Mini数据集时常见的5个环境配置错误及解决方法。内容涵盖从Python虚拟环境搭建、PyTorch与MMCV版本精确匹配,到破解数据集预处理脚本的版本断言错误等关键步骤,旨在帮助开发者高效避坑,快速启动3D目标检测模型的训练与验证流程。
120、基于点云的3D检测:从VoxelNet到CenterPoint的演进
深夜两点,盯着屏幕上那个mAP卡在68.3%的曲线,我第无数次怀疑是不是点云预处理出了问题。这是我在做园区无人配送车时遇到的真实场景——激光雷达扫出来的点云明明很干净,但3D检测网络就是学不进去。后来发现,问题出在体素化时那个该死的体素尺寸上,0.1米和0.2米的差距,直接让模型对远处小目标的召回率掉了15个点。今天这篇笔记,就从这个坑聊起,把从VoxelNet到CenterPoint这条3D检测演进路线掰开揉碎了讲清楚。先说VoxelNet。2017年那会儿,大家还在用手工特征(比如统计每个体素内的点云高
YOLOv8【第十八章:3D 目标检测与点云处理篇·第12节】端到端 3D 检测头改造:CenterPoint + YOLOv8 解耦!
🏆 本文收录于 《YOLOv8实战:从入门到深度优化》 专栏。该专栏系统复现并梳理全网各类 YOLOv8 改进与实战案例(当前已覆盖分类 / 检测 / 分割 / 追踪 / 关键点 / OBB 检测等方向),坚持持续更新 + 深度解析,质量分长期稳定在 97 分以上,可视为当前市面上 覆盖较全、更新较快、实战导向极强 的 YOLO 改进系列内容之一。
nuScenes自动驾驶数据集深度学习全流程实战项目
这意味着:若需将。
nusc_centerpoint_voxelnet_0075voxel_fix_bn_z.zip
centerpoint voxelnet 0075 centerpoint_voxel_1440 配置文件
怀旧党必备!用iPhone4s重温iOS6的保姆级教程(含游戏资源包)
本文提供了一份详细的iPhone4s降级至iOS6.1.3的保姆级教程,包括设备准备、越狱操作、系统降级及资源优化全流程。通过自制固件和越狱工具,用户可以重温经典的拟物化设计和流畅体验,同时获取经典游戏资源包,打造复古游戏神器。
Ascend C 算子开发遇到的问题及解决方法
在学习Ascend C算子开发进阶课程的时候,进行Ascend C自定义算子工程、算子调用等实验,在开发环境中遇到了一些问题,在这里记录一下。首先如果在启智社区CANN版本为6.3 ,要进行Ascend C算子开发,需要更新CANN版本。
语义通信高斯信道仿真代码
【代码】语义通信高斯信道仿真代码。
完美解决 mysql 报错ERROR 1524 (HY000): Plugin ‘mysql_native_password‘ is not loaded
mysql 报错ERROR 1524 (HY000): Plugin 'mysql_native_password' is not loaded
WPF vs Avalonia: 跨入C#桌面应用现代化的大门
请注意,这只是一个目录,详细内容将根据这个结构逐步展开。如果您需要某个特定部分的详细内容,请告知我,我将为您提供深入的解析和示例代码。WPF,全称Windows Presentation Foundation,是微软为Windows平台量身打造的UI框架。自2006年发布以来,它就像一位经验丰富的老船长,引领着桌面应用的航船在技术的海洋中乘风破浪。Avalonia,一个新兴的跨平台UI框架,它像一位年轻的探险家,勇敢地探索着桌面应用的新世界。
MATLAB 与 STK 互联导出导弹轨迹及速度数据(csv导出)
本文介绍了如何通过 MATLAB 脚本连接 STK 提取导弹三维轨迹数据,并以 CSV 格式导出,包含以下关键内容:自动连接 STK 场景;获取所有导弹对象;提取 J2000 坐标系下的位置和速度;加入任务优先级与状态;导出为标准 CSV 文件;
【肌电处理】肌电信号EMG积分肌电值+均方根值+中值频率+平均功率频率【含Matlab源码 3386期】
肌电信号EMG积分肌电值+均方根值+中值频率+平均功率频率 完整的代码,方可运行;可提供运行操作视频!适合小白!
YOLO26剪枝 lamp剪枝测试精度仅掉0.7个点,速度提高11.8fps!
针对没有如何去选择剪枝的内容LAMP是层自适应幅度调整剪枝,无需任何参数,通过算法内部自己计算每个层的重要程度进行剪枝。基于权重重要程度和该层权重大小关系,权重越大表明该层越重要的思想进行优化。这个跟我前面说的非结构化全局剪枝是一个解法(MP),也就是lamp是在我前面那个非结构化剪枝的基础上进行优化的。但是这个逐层进行非结构剪枝目前还没有一个清晰的概念,确定每个层要剪枝多少。LAMP得分是一个平方权重大小,由层中所有“幸存权重”的总和归一化。
Devexpress16.2.6破解工具
Devexpress16.2.6破解工具Devexpress16.2.6破解工具Devexpress16.2.6破解工具Devexpress16.2.6破解工具
廖雪峰Python教程[完整版]
廖雪峰的python教程整理的,已经排好版了,而且还是完整的,适合小白
NTscan扫描工具
ntscan是一个扫描器,可以扫描没有密码和弱密码的共享,先到配置文件中填写猜测的用户名和密码,扫描过程中右侧出现的是扫描日志。
深度学习工具包 DeepLearningToolbox
深度学习工具包Deprecation notice.-----This toolbox is outdated and no longer maintained.There are much better tools available for deep learning than this toolbox, e.g. [Theano](http://deeplearning.net/software/theano/), [torch](http://torch.ch/) or [tensorflow](http://www.tensorflow.org/)I would suggest you use one of the tools mentioned above rather than use this toolbox.Best, Rasmus.DeepLearnToolbox================A Matlab toolbox for Deep Learning.Deep Learning is a new subfield of machine learning that focuses on learning deep hierarchical models of data.It is inspired by the human brain's apparent deep (layered, hierarchical) architecture.A good overview of the theory of Deep Learning theory is[Learning Deep Architectures for AI](http://www.iro.umontreal.ca/~bengioy/papers/ftml_book.pdf)For a more informal introduction, see the following videos by Geoffrey Hinton and Andrew Ng.* [The Next Generation of Neural Networks](http://www.youtube.com/watch?v=AyzOUbkUf3M) (Hinton, 2007)* [Recent Developments in Deep Learning](http://www.youtube.com/watch?v=VdIURAu1-aU) (Hinton, 2010)* [Unsupervised Feature Learning and Deep Learning](http://www.youtube.com/watch?v=ZmNOAtZIgIk) (Ng, 2011)If you use this toolbox in your research please cite [Prediction as a candidate for learning deep hierarchical models of data](http://www2.imm.dtu.dk/pubdb/views/publication_details.php?id=6284)```@MASTERSTHESIS\{IMM2012-06284, author = "R. B. Palm", title = "Prediction as a candidate for learning deep hierarchical models of data", year = "2012",}```Contact: rasmusbergpalm at gmail dot comDirectories included in the toolbox-----------------------------------`NN/` - A library for Feedforward Backpropagation Neural Networks`CNN/` - A library for Convolutional Neural Networks`DBN/` - A library for Deep Belief Networks`SAE/` - A library for Stacked Auto-Encoders`CAE/` - A library for Convolutional Auto-Encoders`util/` - Utility functions used by the libraries`data/` - Data used by the examples`tests/` - unit tests to verify toolbox is workingFor references on each library check REFS.mdSetup-----1. Download.2. addpath(genpath('DeepLearnToolbox'));Example: Deep Belief Network---------------------```matlabfunction test_example_DBNload mnist_uint8;train_x = double(train_x) / 255;test_x = double(test_x) / 255;train_y = double(train_y);test_y = double(test_y);%% ex1 train a 100 hidden unit RBM and visualize its weightsrand('state',0)dbn.sizes = [100];opts.numepochs = 1;opts.batchsize = 100;opts.momentum = 0;opts.alpha = 1;dbn = dbnsetup(dbn, train_x, opts);dbn = dbntrain(dbn, train_x, opts);figure; visualize(dbn.rbm{1}.W'); % Visualize the RBM weights%% ex2 train a 100-100 hidden unit DBN and use its weights to initialize a NNrand('state',0)%train dbndbn.sizes = [100 100];opts.numepochs = 1;opts.batchsize = 100;opts.momentum = 0;opts.alpha = 1;dbn = dbnsetup(dbn, train_x, opts);dbn = dbntrain(dbn, train_x, opts);%unfold dbn to nnnn = dbnunfoldtonn(dbn, 10);nn.activation_function = 'sigm';%train nnopts.numepochs = 1;opts.batchsize = 100;nn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.10, 'Too big error');```Example: Stacked Auto-Encoders---------------------```matlabfunction test_example_SAEload mnist_uint8;train_x = double(train_x)/255;test_x = double(test_x)/255;train_y = double(train_y);test_y = double(test_y);%% ex1 train a 100 hidden unit SDAE and use it to initialize a FFNN% Setup and train a stacked denoising autoencoder (SDAE)rand('state',0)sae = saesetup([784 100]);sae.ae{1}.activation_function = 'sigm';sae.ae{1}.learningRate = 1;sae.ae{1}.inputZeroMaskedFraction = 0.5;opts.numepochs = 1;opts.batchsize = 100;sae = saetrain(sae, train_x, opts);visualize(sae.ae{1}.W{1}(:,2:end)')% Use the SDAE to initialize a FFNNnn = nnsetup([784 100 10]);nn.activation_function = 'sigm';nn.learningRate = 1;nn.W{1} = sae.ae{1}.W{1};% Train the FFNNopts.numepochs = 1;opts.batchsize = 100;nn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.16, 'Too big error');```Example: Convolutional Neural Nets---------------------```matlabfunction test_example_CNNload mnist_uint8;train_x = double(reshape(train_x',28,28,60000))/255;test_x = double(reshape(test_x',28,28,10000))/255;train_y = double(train_y');test_y = double(test_y');%% ex1 Train a 6c-2s-12c-2s Convolutional neural network %will run 1 epoch in about 200 second and get around 11% error. %With 100 epochs you'll get around 1.2% errorrand('state',0)cnn.layers = { struct('type', 'i') %input layer struct('type', 'c', 'outputmaps', 6, 'kernelsize', 5) %convolution layer struct('type', 's', 'scale', 2) %sub sampling layer struct('type', 'c', 'outputmaps', 12, 'kernelsize', 5) %convolution layer struct('type', 's', 'scale', 2) %subsampling layer};cnn = cnnsetup(cnn, train_x, train_y);opts.alpha = 1;opts.batchsize = 50;opts.numepochs = 1;cnn = cnntrain(cnn, train_x, train_y, opts);[er, bad] = cnntest(cnn, test_x, test_y);%plot mean squared errorfigure; plot(cnn.rL);assert(er<0.12, 'Too big error');```Example: Neural Networks---------------------```matlabfunction test_example_NNload mnist_uint8;train_x = double(train_x) / 255;test_x = double(test_x) / 255;train_y = double(train_y);test_y = double(test_y);% normalize[train_x, mu, sigma] = zscore(train_x);test_x = normalize(test_x, mu, sigma);%% ex1 vanilla neural netrand('state',0)nn = nnsetup([784 100 10]);opts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samples[nn, L] = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.08, 'Too big error');%% ex2 neural net with L2 weight decayrand('state',0)nn = nnsetup([784 100 10]);nn.weightPenaltyL2 = 1e-4; % L2 weight decayopts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samplesnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex3 neural net with dropoutrand('state',0)nn = nnsetup([784 100 10]);nn.dropoutFraction = 0.5; % Dropout fraction opts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samplesnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex4 neural net with sigmoid activation functionrand('state',0)nn = nnsetup([784 100 10]);nn.activation_function = 'sigm'; % Sigmoid activation functionnn.learningRate = 1; % Sigm require a lower learning rateopts.numepochs = 1; % Number of full sweeps through dataopts.batchsize = 100; % Take a mean gradient step over this many samplesnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex5 plotting functionalityrand('state',0)nn = nnsetup([784 20 10]);opts.numepochs = 5; % Number of full sweeps through datann.output = 'softmax'; % use softmax outputopts.batchsize = 1000; % Take a mean gradient step over this many samplesopts.plot = 1; % enable plottingnn = nntrain(nn, train_x, train_y, opts);[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');%% ex6 neural net with sigmoid activation and plotting of validation and training error% split training data into training and validation datavx = train_x(1:10000,:);tx = train_x(10001:end,:);vy = train_y(1:10000,:);ty = train_y(10001:end,:);rand('state',0)nn = nnsetup([784 20 10]); nn.output = 'softmax'; % use softmax outputopts.numepochs = 5; % Number of full sweeps through dataopts.batchsize = 1000; % Take a mean gradient step over this many samplesopts.plot = 1; % enable plottingnn = nntrain(nn, tx, ty, opts, vx, vy); % nntrain takes validation set as last two arguments (optionally)[er, bad] = nntest(nn, test_x, test_y);assert(er < 0.1, 'Too big error');```[](https://bitdeli.com/free "Bitdeli Badge")
429

被折叠的 条评论
为什么被折叠?



