数据技术课堂菜菜九天PyTorch深度学习实战

01 LESSON 0.1 GPU购买与GPU白嫖指南 · 02 LESSON 0.2 PyTorch安装与部署（CPU版本） · 03 LESSON 0.3

* 01 LESSON 0.1 GPU购买与GPU白嫖指南

* 02 LESSON 0.2 PyTorch安装与部署（CPU版本）

* 03 LESSON 0.3 PyTorch安装与配置（GPU版本）

* 04 LESSON 1 张量的创建与常用方法

* 05 LESSON 2 张量的索引、分片、合并及维度调整

* 06 LESSON 3.张量的广播和科学运算

* 07 LESSON 4.张量的线性代数运算

* 08 LESSON 5.基本优化方法与最小二乘法

* 09 LESSON 6.动态计算图与梯度下降入门

* 10 LESSON 7.1 神经网络的诞生与发展

* 11 LESSON 7.2 机器学习中的基本概念

* 12 LESSON 7.3 深入理解PyTorch框架

* 13 LESSON 8.1单层回归神经网络 & Tensor新手避坑指南

* 14 LESSON 8.2 torch.nn.Linear实现单层回归网络的正向传播

* 15 LESSON 8.3 二分类神经网络的原理与实现

* 16 LESSON 8.4 torch.nn.functional实现单层二分类网络的正向传播

* 17 LESSON 8.5 多分类神经网络

* 18 LESSON 9.1 从异或门问题认识多层神经网络

* 19 LESSON 9.2 黑箱：深度神经网络的不可解释性

* 20 LESSON 9.3 & 9.4 层与激活函数

* 21 LESSON 9.5 从0实现深度神经网络的正向传播

* 22 LESSON 10.1 SSE与二分类交叉熵损失

* 23 LESSON 10.2 二分类交叉熵的原理与实现

* 24 LEESON 10.3 多分类交叉熵的原理与实现

* 25 LEESON 11.1 梯度下降中的两个关键问题

* 26 LESSON 11.2(1) 反向传播的原理

* 27 LESSON 11.2(2) 反向传播的实现

* 28 LESSON 11.3 走出第一步：动量法Momentum

* 29 LESSON 11.4 开始迭代：batch与epochs

* 30 LESSON 11.5 在Fashion-MNIST数据集上实现完整的神经网络（上）

* 31 LESSON 11.5 在Fashion-MNIST上实现完整的神经网络（下）

* 32 LESSON 12.0 深度学习基础网络手动搭建与快速实现

* 33 LESSON 12.1 深度学习建模实验中数据集生成函数的创建与使用

* 34 LESSON 12.2 可视化工具TensorBoard的安装与使用

* 35 LESSON 12.3 线性回归建模实验

* 36 LESSON 12.4 逻辑回归建模实验

* 37 LESSON 12.5 softmax回归建模实验

* 38 LESSON 13.1 深度学习建模目标与性能评估理论

* 39 LESSON 13.2 模型拟合度概念介绍与欠拟合模型的结构调整策略

* 40 LESSON 13 【加餐】损失函数的随机创建现象详解

* 41 LESSON 13.3 梯度不平稳性与Glorot条件（1）

* 42 LESSON 13.3 梯度不平稳性与Glorot条件（2）

* 43 LESSON 13.3 梯度不平稳性与Glorot条件（3）

* 44 LESSON 13.4 Dead ReLU Problem与学习率优化

* 45 LESSON 13.5 Xavier方法与kaiming方法（HE初始化）

* 46 LESSON 14.1 数据归一化与Batch Normalization基础理论

* 47 LESSON 14.2 Batch Normalization在PyTorch中的实现

* 48 LESSON 14.3 Batch Normalization综合调参实战

* 49 LESSON 15.1 学习率调度基本概念与手动实现方法

* 50 LESSON 15.2 学习率调度在PyTorch中的实现方法

* 51 LESSON 16.1 配置环境，计算机视觉行业综述

* 52 LESSON 16.2 图像的基本操作

* 53 LESSON 16.3 卷积操作与边缘检测

* 54 LESSON 16.4 卷积遇见深度学习

* 55 Lesson 16.5 在Pytorch中实现卷积网络（上）：卷积核、输入通道与特征图

* 56 Lesson 16.5 在PyTorch中实现卷积网络（中）：步长与填充

* 57 Lesson 16.5 在PyTorch中实现卷积网络（下）：池化层，BN与Dropout

* 58 Lesson 16.6 复现经典架构(1)：LeNet5

* 59 Lesson 16.6 复现经典架构 (2)：AlexNet

* 60 Lesson 16.7 如何拓展网络深度：VGG架构

* 61 Lesson 16.8 感受野（上）：定义与性质

* 62 Lesson 16.8 感受野（下）：膨胀卷积，计算感受野大小

* 63 Lesson 16.9 平移不变性

* 64 Lesson 16.10 卷积层的参数量计算，1x1卷积核

* 65 Lesson 16.11 分组卷积与深度可分离卷积

* 66 Lesson 16.12 全连接层的参数，用nn.Sequential复现VGG16

* 67 Lesson 16.13 全局平均池化，NiN网络的复现

* 68 Lesson 16.14 GoogLeNet：思想与具体架构

* 69 Lesson 16.15 GoogLeNet的复现

* 70 Lesson 16.16 残差网络：思想与具体架构

* 71 Lesson 16.17 ResNet的复现 (1) ：架构中的陷阱

* 72 Lesson 16.17 ResNet的复现 (2) ：卷积块、残差块、瓶颈架构

* 73 Lesson 16.17 ResNet的复现 (3)：完整的残差网络

* 74 Lesson 17.1 计算机视觉中的三种基本任务

* 75 Lesson 17.2 经典数据集(1)：入门数据集，新手读数据踩坑指南

* 76 Lesson 17.2 经典数据集(2)：竞赛数据与其他常用数据

* 77 Lesson 17.3(1) 使用自己的图像创造数据集

* 78 Lesson 17.3 (2) & (3) 将二维表及其他结构转化为四维tensor

* 79 Lesson 17.4 图像数据的数据预处理

* 80 Lesson 17.5 数据增强

* 81 Lesson 17.6 更强大的优化算法 (1) AdaGrad

* 82 Lesson 17.6 更强大的Lesson 17优化算法(2) RMSprop与Adam

* 83 Lesson 17.7 调用经典架构

* 84 Lesson 17.8 (1) 基于ResNet与VGG16自建架构

* 85 Lesson 17.8 (2) 基于普通卷积层和池化层自建架构

* 86 Lesson 17.9 有监督算法的预训练迁移学习

* 87 Lesson 17.10 深度学习中的模型选择

* 88 Lesson 17.11(1) 案例1：项目背景完整流程概述

* 89 Lesson 17.11(2) 案例1：数据与架构

* 90 Lesson 17.11(3) 案例1：提前停止

* 91 Lesson 17.11(4) 案例1：一个完整的训练函数

* 92 Lesson 17.11(5) 准备训练函数所需的全部参数

* 93 Lesson 17.11(6) GPU内存管理机制、训练函数的GPU版本

* 94 Lesson 17.11(7) 初步训练：模型选择

* 95 Lesson 17.11(8) 模型调优(1)：增加迭代次数，让迭代更稳定

* 96 Lesson 17.11(9) 模型调优(2)：对抗过拟合，其他可探索的方向

* 97 LESSON 20.1字符串的常用操作与计算机字符编码

* 98 LESSON 20.2 字符串实用处理方法：正则表达式（上）

* 99 LESSON 18.1 案例背景与benchmark建立

* 100 LESSON 18.2.1 使用OpenCV批量分片高像素图像（上）

* 101 LESSON 18.2.2 使用OpenCV批量分片高像素图像（下）

* 102 LESSON 18.3.1 数据探索（上）：数据结构与病理图像可视化

* 103 LESSON 18.3.2 数据探索（下）：标签探索与恶性率可视化

* 104 LESSON 18.4.1 自定义数据集导入类与数据集分割

* 105 LESSON 18.4.2 医疗数据的数据增强 (1) 10项色彩增强手段

* 106 LESSON 18.4.2 医疗数据的数据增强 (2) 生成对抗网络与染色标准化

* 107 LESSON 18.4.3 实现色彩增强 (1) 认识imgaug与skimage

* 108 LESSON 18.4.3 实现色彩增强 (2) imgaug中的仿射变换与随机增强

* 109 LESSON 18.4.3 实现色彩增强 (3) imgaug中的线性变换与色彩加乘

* 110 LESSON 18.4.3 实现色彩增强 (4) 基于苏木素H与伊红E的色彩空间转换

* 111 LESSON 18.4.3 数据增强方案 (5)：imgaug嵌入PyTorch运行

* 112 LESSON 18.4.3 数据增强方案 (6)：HED单通道操作嵌入PyTorch运行

* 113 LESSON 18.4.4.1 生成对抗网络的基本原理与损失函数

* 114 LESSON 18.4.4.2 (1) 从0实现GAN的反向传播与训练

* 115 LESSON 18.4.4.2 (2) 判别器的反向传播

* 116 LESSON 18.4.4.2 (3) 生成器的反向传播

* 117 LESSON 18.4.4.3 转置卷积层与DCGAN(1)：基本原理与实现

* 118 LESSON 18.4.4.3 转置卷积层与DCGAN(2)：带步长与填充的转置卷积层（上

* 119 LESSON 18.4.4.3 转置卷积层与DCGAN(2)：带步长与填充的转置卷积层（下

* 120 LESSON 18.4.4.3 转置卷积层与DCGAN(3)：DCGAN架构复现 (上)

* 121 LESSON 18.4.4.3 转置卷积层与DCGAN(3)：DCGAN架构复现 (下)

* 122 LESSON 18.4.4.3 转置卷积层与DCGAN(4) 声明：从DCGAN到pix2

* 123 LESSON 18.4.4.4 cGAN与infoGAN(1)：基本运行原理

* 124 LESSON 18.4.4.4 cGAN与infoGAN(2)：标签输入与Embed

* 125 LESSON 18.4.4.4 cGAN与infoGAN(3)：复现一个cGAN架构

* 126 Lesson 18.4.5.1 自动编码器家族(1)：认识自动编码器_batch

* 127 Lesson 18.4.5.1 自动编码器家族(2)：三大类自动编码器_batch

* 128 Lesson 18.4.5.1 自动编码器家族(3)：自动编码器的应用场景_batch

* 129 Lesson 18.4.5.2【加餐】变分自动编码器(1)：数据流与细节梳理_batch

* 130 Lesson 18.4.5.2【加餐】变分自动编码器(2)：损失函数详解_batch

* 131 Lesson 18.4.5.2【加餐】变分自动编码器(3)：重参数化技巧_batch

* 课程资料/

* WEEK 1/

* GPU购买指南 + PyTorch安装及环境搭建 V4.pdf

* Lesson 1.张量（Tensor）的创建和索引.ipynb

* Lesson 2.张量的索引、分片、合并以及维度调整.ipynb

* Lesson 3.张量的广播和科学运算.ipynb

* Lesson 4.张量的线性代数运算.ipynb

* Python的安装与环境配置.pdf

* 启发/

* MAC及其他操作系统走这里.txt

* 启发（win电脑适用）.exe

* WEEK 2/

* LESSON 7 认识深度学习，认识PyTorch.pdf

* LESSON 8 单层神经网络.pdf

* Lesson 5.基本优化思想与最小二乘法.ipynb

* Lesson 6.动态计算图与梯度下降入门.ipynb

* WEEK 3、4/

* Lesson 9 深层神经网络.pdf

* Lesson 10 神经网络的损失函数.pdf

* Lesson 11 神经网络的学习.pdf

* MINST-FASHION数据集/

* FashionMNIST/

* processed/

* test.pt

* training.pt

* raw/

* t10k-images-idx3-ubyte

* t10k-images-idx3-ubyte.gz

* t10k-labels-idx1-ubyte

* t10k-labels-idx1-ubyte.gz

* train-images-idx3-ubyte

* train-images-idx3-ubyte.gz

* train-labels-idx1-ubyte

* train-labels-idx1-ubyte.gz

* creditcard.csv

* WEEK 5/

* Lesson 12.0 深度学习基础网络手动搭建与快速实现.ipynb

* Lesson 12.1 深度学习建模实验中数据集创建函数的创建与使用.ipynb

* Lesson 12.2 PyTorch深度学习建模可视化工具TensorBoard的安装与使用.ipynb

* Lesson 12.3 线性回归建模实验.ipynb

* Lesson 12.4 逻辑回归建模实验.ipynb

* Lesson 12.5 softmax回归建模实验.ipynb

* torchLearning.py

* WEEK 6/

* Lesson 13.1 深度学习建模目标与性能评估理论.ipynb

* Lesson 13.2 模型拟合度概念介绍与欠拟合模型的结构调整策略.ipynb

* WEEK 7（5月20日更新torchlearning.py/

* Lesson 13.3 梯度不平稳性与Glorot条件.ipynb

* Lesson 13.4 Dead ReLU Problem与学习率优化.ipynb

* Lesson 13.5 Xavier方法与kaiming方法（HE初始化）.ipynb

* torchLearning.py

* 【加餐】损失函数的随机创建现象详解.ipynb

* WEEK 8/

* Lesson 14.1 数据归一化与Batch Normalization理论基础.ipynb

* Lesson 14.2 Batch Normalization在PyTorch中的实现.ipynb

* Lesson 14.3 Batch Normalization综合调参实战.ipynb

* WEEK 9 & WEEK 10/

* Lesson 15.1 学习率调度基本概念与手动实现方法.ipynb

* Lesson 15.2 学习率调度在PyTorch中的实现方法.ipynb

* Lesson 16 计算机视觉入门（上）.pdf

* Lesson 16.1~16.6.ipynb

* 图像/

* blue-peacock.jpg

* edge detection.PNG

* WEEK 10-WEEK 14 CV数据包/

* datasets/

* FashionMNIST.zip

* SVHN.zip

* omniglot-py.zip

* datasets2/

* ImageNet2012/

* ILSVRC2012_img_train/

* n04523525.tar

* n04525038.tar

* n04525305.tar

* n04532106.tar

* n04532670.tar

* n04536866.tar

* n04540053.tar

* n04542943.tar

* n04548280.tar

* n04548362.tar

* n04550184.tar

* n04552348.tar

* n04553703.tar

* n04554684.tar

* n04557648.tar

* n04560804.tar

* n04562935.tar

* n04579145.tar

* n04579432.tar

* n04584207.tar

* n04589890.tar

* n04590129.tar

* n04591157.tar

* n04591713.tar

* n04592741.tar

* n04596742.tar

* n04597913.tar

* n04599235.tar

* n04604644.tar

* n04606251.tar

* n04612504.tar

* n04613696.tar

* n06359193.tar

* n06596364.tar

* n06785654.tar

* n06794110.tar

* n06874185.tar

* n07248320.tar

* n07565083.tar

* n07579787.tar

* n07583066.tar

* n07584110.tar

* n07590611.tar

* n07613480.tar

* n07614500.tar

* n07615774.tar

* n07684084.tar

* n07693725.tar

* n07695742.tar

* n07697313.tar

* n07697537.tar

* n07711569.tar

* n07714571.tar

* n07714990.tar

* n07715103.tar

* n07716358.tar

* n07716906.tar

* n07717410.tar

* n07717556.tar

* n07718472.tar

* n07718747.tar

* n07720875.tar

* n07730033.tar

* n07734744.tar

* n07742313.tar

* n07745940.tar

* n07747607.tar

* n07749582.tar

* n07753113.tar

* n07753275.tar

* n07753592.tar

* n07754684.tar

* n07760859.tar

* n07768694.tar

* n07802026.tar

* n07831146.tar

* n07836838.tar

* n07860988.tar

* n07871810.tar

* n07873807.tar

* n07875152.tar

* n07880968.tar

* n07892512.tar

* n07920052.tar

* n07930864.tar

* n07932039.tar

* n09193705.tar

* n09229709.tar

* n09246464.tar

* n09256479.tar

* n09288635.tar

* n09332890.tar

* n09399592.tar

* n09421951.tar

* n09428293.tar

* n09468604.tar

* n09472597.tar

* n09835506.tar

* n10148035.tar

* n10565667.tar

* n11879895.tar

* n11939491.tar

* n12057211.tar

* n12144580.tar

* n12267677.tar

* n12620546.tar

* n12768682.tar

* n12985857.tar

* n12998815.tar

* n13037406.tar

* n13040303.tar

* n13044778.tar

* n13052670.tar

* n13054560.tar

* n13133613.tar

* n15075141.tar

* ImageNet_Train/

* n01440764.tar

* n01443537.tar

* n01484850.tar

* n01491361.tar

* n01494475.tar

* n01496331.tar

* n01498041.tar

* n01514668.tar

* n01514859.tar

* n01518878.tar

* n01530575.tar

* n01531178.tar

* n01532829.tar

* n01534433.tar

* n01537544.tar

* n01558993.tar

* n01560419.tar

* n01580077.tar

* n01582220.tar

* n01592084.tar

* n01601694.tar

* n01608432.tar

* n01614925.tar

* n01616318.tar

* n01622779.tar

* n01629819.tar

* n01630670.tar

* n01631663.tar

* n01632458.tar

* n01632777.tar

* n01641577.tar

* n01644373.tar

* n01644900.tar

* n01664065.tar

* n01665541.tar

* n01667114.tar

* n01667778.tar

* n01669191.tar

* n01675722.tar

* n01677366.tar

* n01682714.tar

* n01685808.tar

* n01687978.tar

* n01688243.tar

* n01689811.tar

* n01692333.tar

* n01693334.tar

* n01694178.tar

* n01695060.tar

* n01697457.tar

* n01698640.tar

* n01704323.tar

* n01728572.tar

* n01728920.tar

* n01729322.tar

* n01729977.tar

* n01734418.tar

* n01735189.tar

* n01737021.tar

* n01739381.tar

* n01740131.tar

* n01742172.tar

* n01744401.tar

* n01748264.tar

* n01749939.tar

* n01751748.tar

* n01753488.tar

* n01755581.tar

* n01756291.tar

* n01768244.tar

* n01770081.tar

* n01770393.tar

* n01773157.tar

* n01773549.tar

* n01773797.tar

* n01774384.tar

* n01774750.tar

* n01775062.tar

* n01776313.tar

* n01784675.tar

* n01795545.tar

* n01796340.tar

* n01797886.tar

* n01798484.tar

* n01806143.tar

* n01806567.tar

* n01807496.tar

* n01817953.tar

* n01818515.tar

* n01819313.tar

* n01820546.tar

* n01824575.tar

* n01828970.tar

* n01829413.tar

* n01833805.tar

* n01843065.tar

* n01843383.tar

* n01847000.tar

* n01855032.tar

* n01855672.tar

* n01860187.tar

* n01871265.tar

* n01872401.tar

* n01873310.tar

* n01877812.tar

* n01882714.tar

* n01883070.tar

* n01910747.tar

* n01914609.tar

* n01917289.tar

* n01924916.tar

* n01930112.tar

* n01943899.tar

* n01944390.tar

* n01945685.tar

* n01950731.tar

* n01955084.tar

* n01968897.tar

* n01978287.tar

* n01978455.tar

* n01980166.tar

* n01981276.tar

* n01983481.tar

* n01984695.tar

* n01985128.tar

* n01986214.tar

* n01990800.tar

* n02002556.tar

* n02002724.tar

* n02006656.tar

* n02007558.tar

* n02009229.tar

* n02009912.tar

* n02011460.tar

* n02012849.tar

* n02013706.tar

* n02017213.tar

* n02018207.tar

* n02018795.tar

* n02025239.tar

* n02027492.tar

* n02028035.tar

* n02033041.tar

* n02037110.tar

* n02051845.tar

* n02056570.tar

* n02058221.tar

* n02066245.tar

* n02071294.tar

* n02074367.tar

* n02077923.tar

* n02085620.tar

* n02085782.tar

* n02085936.tar

* n02086079.tar

* n02086240.tar

* n02086646.tar

* n02086910.tar

* n02087046.tar

* n02087394.tar

* n02088094.tar

* n02088238.tar

* n02088364.tar

* n02088466.tar

* n02088632.tar

* n02089078.tar

* n02089867.tar

* n02089973.tar

* n02090379.tar

* n02090622.tar

* n02090721.tar

* n02091032.tar

* n02091134.tar

* n02091244.tar

* n02091467.tar

* n02091635.tar

* n02091831.tar

* n02092002.tar

* n02092339.tar

* n02093256.tar

* n02093428.tar

* n02093647.tar

* n02093754.tar

* n02093859.tar

* n02093991.tar

* n02094114.tar

* n02094258.tar

* n02094433.tar

* n02095314.tar

* n02095570.tar

* n02095889.tar

* n02096051.tar

* n02096177.tar

* n02096294.tar

* n02096437.tar

* n02096585.tar

* n02097047.tar

* n02097130.tar

* n02097209.tar

* n02097298.tar

* n02097474.tar

* n02097658.tar

* n02098105.tar

* n02098286.tar

* n02098413.tar

* n02099267.tar

* n02099429.tar

* n02099601.tar

* n02099712.tar

* n02099849.tar

* n02100236.tar

* n02100583.tar

* n02100735.tar

* n02100877.tar

* n02101006.tar

* n02101388.tar

* n02101556.tar

* n02102040.tar

* n02102177.tar

* n02102318.tar

* n02102480.tar

* n02102973.tar

* n02104029.tar

* n02104365.tar

* n02105056.tar

* n02105162.tar

* n02105251.tar

* n02105412.tar

* n02105505.tar

* n02105641.tar

* n02105855.tar

* n02106030.tar

* n02106166.tar

* n02106382.tar

* n02106550.tar

* n02106662.tar

* n02107142.tar

* n02107312.tar

* n02107574.tar

* n02107683.tar

* n02107908.tar

* n02108000.tar

* n02108089.tar

* n02108422.tar

* n02108551.tar

* n02108915.tar

* n02109047.tar

* n02109525.tar

* n02109961.tar

* n02110063.tar

* n02110185.tar

* n02110341.tar

* n02110627.tar

* n02110806.tar

* n02110958.tar

* n02111129.tar

* n02111277.tar

* n02111500.tar

* n02111889.tar

* n02112018.tar

* n02112137.tar

* n02112350.tar

* n02112706.tar

* n02113023.tar

* n02113186.tar

* n02113624.tar

* n02113712.tar

* n02113799.tar

* n02113978.tar

* n02114367.tar

* n02114548.tar

* n02114712.tar

* n02114855.tar

* n02115641.tar

* n02115913.tar

* n02116738.tar

* n02117135.tar

* n02119022.tar

* n02119789.tar

* n02120079.tar

* n02120505.tar

* n02123045.tar

* n02123159.tar

* n02123394.tar

* n02123597.tar

* n02124075.tar

* n02125311.tar

* n02127052.tar

* n02128385.tar

* n02128757.tar

* n02128925.tar

* n02129165.tar

* n02129604.tar

* ImageNet_Train1/

* n02130308.tar

* n02132136.tar

* n02133161.tar

* n02134084.tar

* n02134418.tar

* n02137549.tar

* n02138441.tar

* n02165105.tar

* n02165456.tar

* n02167151.tar

* n02168699.tar

* n02169497.tar

* n02172182.tar

* n02174001.tar

* n02177972.tar

* n02190166.tar

* n02206856.tar

* n02219486.tar

* n02226429.tar

* n02229544.tar

* n02231487.tar

* n02233338.tar

* n02236044.tar

* n02256656.tar

* n02259212.tar

* n02264363.tar

* n02268443.tar

* n02268853.tar

* n02276258.tar

* n02277742.tar

* n02279972.tar

* n02280649.tar

* n02281406.tar

* n02281787.tar

* n02317335.tar

* n02319095.tar

* n02321529.tar

* n02325366.tar

* n02326432.tar

* n02328150.tar

* n02342885.tar

* n02346627.tar

* n02356798.tar

* n02361337.tar

* n02363005.tar

* n02364673.tar

* n02389026.tar

* n02391049.tar

* n02395406.tar

* n02396427.tar

* n02397096.tar

* n02398521.tar

* n02403003.tar

* n02408429.tar

* n02410509.tar

* n02412080.tar

* n02415577.tar

* n02417914.tar

* n02422106.tar

* n02422699.tar

* n02423022.tar

* n02437312.tar

* n02437616.tar

* n02441942.tar

* n02442845.tar

* n02443114.tar

* n02443484.tar

* n02444819.tar

* n02445715.tar

* n02447366.tar

* n02454379.tar

* n02457408.tar

* n02480495.tar

* n02480855.tar

* n02481823.tar

* n02483362.tar

* n02483708.tar

* n02484975.tar

* n02486261.tar

* n02486410.tar

* n02487347.tar

* n02488291.tar

* n02488702.tar

* n02489166.tar

* n02490219.tar

* n02492035.tar

* n02492660.tar

* n02493509.tar

* n02493793.tar

* n02494079.tar

* n02497673.tar

* n02500267.tar

* n02504013.tar

* n02504458.tar

* n02509815.tar

* n02510455.tar

* n02514041.tar

* n02526121.tar

* n02536864.tar

* n02606052.tar

* n02607072.tar

* n02640242.tar

* n02641379.tar

* n02643566.tar

* n02655020.tar

* n02666196.tar

* n02667093.tar

* n02669723.tar

* n02672831.tar

* n02676566.tar

* n02687172.tar

* n02690373.tar

* n02692877.tar

* n02699494.tar

* n02701002.tar

* n02704792.tar

* n02708093.tar

* n02727426.tar

* n02730930.tar

* n02747177.tar

* n02749479.tar

* n02769748.tar

* n02776631.tar

* n02777292.tar

* n02782093.tar

* n02783161.tar

* n02786058.tar

* n02787622.tar

* n02788148.tar

* n02790996.tar

* n02791124.tar

* n02791270.tar

* n02793495.tar

* n02794156.tar

* n02795169.tar

* n02797295.tar

* n02799071.tar

* n02802426.tar

* n02804414.tar

* n02804610.tar

* n02807133.tar

* n02808304.tar

* n02808440.tar

* n02814533.tar

* n02814860.tar

* n02815834.tar

* n02817516.tar

* n02823428.tar

* n02823750.tar

* n02825657.tar

* n02834397.tar

* n02835271.tar

* n02837789.tar

* n02840245.tar

* n02841315.tar

* n02843684.tar

* n02859443.tar

* n02860847.tar

* n02865351.tar

* n02869837.tar

* n02870880.tar

* n02871525.tar

* n02877765.tar

* n02879718.tar

* n02883205.tar

* n02892201.tar

* n02892767.tar

* n02894605.tar

* n02895154.tar

* n02906734.tar

* n02909870.tar

* n02910353.tar

* n02916936.tar

* n02917067.tar

* n02927161.tar

* n02930766.tar

* n02939185.tar

* n02948072.tar

* n02950826.tar

* n02951358.tar

* n02951585.tar

* n02963159.tar

* n02965783.tar

* n02966193.tar

* n02966687.tar

* n02971356.tar

* n02974003.tar

* n02977058.tar

* n02978881.tar

* n02979186.tar

* n02980441.tar

* n02981792.tar

* n02988304.tar

* n02992211.tar

* n02992529.tar

* n02999410.tar

* n03000134.tar

* n03000247.tar

* n03000684.tar

* n03014705.tar

* n03016953.tar

* n03017168.tar

* n03018349.tar

* n03026506.tar

* n03028079.tar

* n03032252.tar

* n03041632.tar

* n03042490.tar

* n03045698.tar

* n03047690.tar

* n03062245.tar

* n03063599.tar

* n03063689.tar

* n03065424.tar

* n03075370.tar

* n03085013.tar

* n03089624.tar

* n03095699.tar

* n03100240.tar

* n03109150.tar

* n03110669.tar

* n03124043.tar

* n03124170.tar

* n03125729.tar

* n03126707.tar

* n03127747.tar

* n03127925.tar

* n03131574.tar

* n03133878.tar

* n03134739.tar

* n03141823.tar

* n03146219.tar

* n03160309.tar

* n03179701.tar

* n03180011.tar

* n03187595.tar

* n03188531.tar

* n03196217.tar

* n03197337.tar

* n03201208.tar

* n03207743.tar

* n03207941.tar

* n03208938.tar

* n03216828.tar

* n03218198.tar

* n03220513.tar

* n03223299.tar

* n03240683.tar

* n03249569.tar

* n03250847.tar

* n03255030.tar

* n03259280.tar

* n03271574.tar

* n03272010.tar

* n03272562.tar

* n03290653.tar

* n03291819.tar

* n03297495.tar

* n03314780.tar

* n03325584.tar

* n03337140.tar

* n03344393.tar

* n03345487.tar

* n03347037.tar

* n03355925.tar

* n03372029.tar

* n03376595.tar

* n03379051.tar

* n03384352.tar

* n03388043.tar

* n03388183.tar

* n03388549.tar

* n03393912.tar

* n03394916.tar

* n03400231.tar

* n03404251.tar

* n03417042.tar

* n03424325.tar

* n03425413.tar

* n03443371.tar

* n03444034.tar

* n03445777.tar

* n03445924.tar

* n03447447.tar

* n03447721.tar

* n03450230.tar

* n03452741.tar

* n03457902.tar

* n03459775.tar

* n03461385.tar

* n03467068.tar

* n03476684.tar

* n03476991.tar

* n03478589.tar

* n03481172.tar

* ImageNet_Train2/

* n03482405.tar

* n03483316.tar

* n03485407.tar

* n03485794.tar

* n03492542.tar

* n03494278.tar

* n03495258.tar

* n03496892.tar

* n03498962.tar

* n03527444.tar

* n03529860.tar

* n03530642.tar

* n03532672.tar

* n03534580.tar

* n03535780.tar

* n03538406.tar

* n03544143.tar

* n03584254.tar

* n03584829.tar

* n03590841.tar

* n03594734.tar

* n03594945.tar

* n03595614.tar

* n03598930.tar

* n03599486.tar

* n03602883.tar

* n03617480.tar

* n03623198.tar

* n03627232.tar

* n03630383.tar

* n03633091.tar

* n03637318.tar

* n03642806.tar

* n03649909.tar

* n03657121.tar

* n03658185.tar

* n03661043.tar

* n03662601.tar

* n03666591.tar

* n03670208.tar

* n03673027.tar

* n03676483.tar

* n03680355.tar

* n03690938.tar

* n03691459.tar

* n03692522.tar

* n03697007.tar

* n03706229.tar

* n03709823.tar

* n03710193.tar

* n03710637.tar

* n03710721.tar

* n03717622.tar

* n03720891.tar

* n03721384.tar

* n03724870.tar

* n03729826.tar

* n03733131.tar

* n03733281.tar

* n03733805.tar

* n03742115.tar

* n03743016.tar

* n03759954.tar

* n03761084.tar

* n03763968.tar

* n03764736.tar

* n03769881.tar

* n03770439.tar

* n03770679.tar

* n03773504.tar

* n03775071.tar

* n03775546.tar

* n03776460.tar

* n03777568.tar

* n03777754.tar

* n03781244.tar

* n03782006.tar

* n03785016.tar

* n03786901.tar

* n03787032.tar

* n03788195.tar

* n03788365.tar

* n03791053.tar

* n03792782.tar

* n03792972.tar

* n03793489.tar

* n03794056.tar

* n03796401.tar

* n03803284.tar

* n03804744.tar

* n03814639.tar

* n03814906.tar

* n03825788.tar

* n03832673.tar

* n03837869.tar

* n03838899.tar

* n03840681.tar

* n03841143.tar

* n03843555.tar

* n03854065.tar

* n03857828.tar

* n03866082.tar

* n03868242.tar

* n03868863.tar

* n03871628.tar

* n03873416.tar

* n03874293.tar

* n03874599.tar

* n03876231.tar

* n03877472.tar

* n03877845.tar

* n03884397.tar

* n03887697.tar

* n03888257.tar

* n03888605.tar

* n03891251.tar

* n03891332.tar

* n03895866.tar

* n03899768.tar

* n03902125.tar

* n03903868.tar

* n03908618.tar

* n03908714.tar

* n03916031.tar

* n03920288.tar

* n03924679.tar

* n03929660.tar

* n03929855.tar

* n03930313.tar

* n03930630.tar

* n03933933.tar

* n03935335.tar

* n03937543.tar

* n03938244.tar

* n03942813.tar

* n03944341.tar

* n03947888.tar

* n03950228.tar

* n03954731.tar

* n03956157.tar

* n03958227.tar

* n03961711.tar

* n03967562.tar

* n03970156.tar

* n03976467.tar

* n03976657.tar

* n03977966.tar

* n03980874.tar

* n03982430.tar

* n03983396.tar

* n03991062.tar

* n03992509.tar

* n03995372.tar

* n03998194.tar

* n04004767.tar

* n04005630.tar

* n04008634.tar

* n04009552.tar

* n04019541.tar

* n04023962.tar

* n04026417.tar

* n04033901.tar

* n04033995.tar

* n04037443.tar

* n04039381.tar

* n04040759.tar

* n04041544.tar

* n04044716.tar

* n04049303.tar

* n04065272.tar

* n04067472.tar

* n04069434.tar

* n04070727.tar

* n04074963.tar

* n04081281.tar

* n04086273.tar

* n04090263.tar

* n04099969.tar

* n04111531.tar

* n04116512.tar

* n04118538.tar

* n04118776.tar

* n04120489.tar

* n04125021.tar

* n04127249.tar

* n04131690.tar

* n04133789.tar

* n04136333.tar

* n04141076.tar

* n04141327.tar

* n04141975.tar

* n04146614.tar

* n04147183.tar

* n04149813.tar

* n04152593.tar

* n04153751.tar

* n04154565.tar

* n04162706.tar

* n04179913.tar

* n04192698.tar

* n04200800.tar

* n04201297.tar

* n04204238.tar

* n04204347.tar

* n04208210.tar

* n04209133.tar

* n04209239.tar

* n04228054.tar

* n04229816.tar

* n04235860.tar

* n04238763.tar

* n04239074.tar

* n04243546.tar

* n04251144.tar

* n04252077.tar

* n04252225.tar

* n04254120.tar

* n04254680.tar

* n04254777.tar

* n04258138.tar

* n04259630.tar

* n04263257.tar

* n04264628.tar

* n04265275.tar

* n04266014.tar

* n04270147.tar

* n04273569.tar

* n04275548.tar

* n04277352.tar

* n04285008.tar

* n04286575.tar

* n04296562.tar

* n04310018.tar

* n04311004.tar

* n04311174.tar

* n04317175.tar

* n04325704.tar

* n04326547.tar

* n04328186.tar

* n04330267.tar

* n04332243.tar

* n04335435.tar

* n04336792.tar

* n04344873.tar

* n04346328.tar

* n04347754.tar

* n04350905.tar

* n04355338.tar

* n04355933.tar

* n04356056.tar

* n04357314.tar

* n04366367.tar

* n04367480.tar

* n04370456.tar

* n04371430.tar

* n04371774.tar

* n04372370.tar

* n04376876.tar

* n04380533.tar

* n04389033.tar

* n04392985.tar

* n04398044.tar

* n04399382.tar

* n04404412.tar

* n04409515.tar

* n04417672.tar

* n04418357.tar

* n04423845.tar

* n04428191.tar

* n04429376.tar

* n04435653.tar

* n04442312.tar

* n04443257.tar

* n04447861.tar

* n04456115.tar

* n04458633.tar

* n04461696.tar

* n04462240.tar

* n04465501.tar

* n04467665.tar

* n04476259.tar

* n04479046.tar

* n04482393.tar

* n04483307.tar

* n04485082.tar

* n04486054.tar

* n04487081.tar

* n04487394.tar

* n04493381.tar

* n04501370.tar

* n04505470.tar

* n04507155.tar

* n04509417.tar

* n04515003.tar

* n04517823.tar

* n04522168.tar

* ImageNet_valid/

* ImageNET1.zip

* ImageNET2.zip

* ImageNET.zip

* VOC.zip

* lsun-master.zip

* datasets3/

* celeba.zip

* cifar.zip

* sbd.zip

* sbu.zip

* datasets4.zip

* 必须下载datasets4和datasets2中的LSUN，其他按需下载.txt

* WEEK 10-WEEK 14 CV论文包/

* Recent Advances in Convolutional Neural Networks.pdf

* Striving for Simplicity The All Convolutional Net.pdf

* Xception Deep Learning with Depthwise Separable Convolutions.pdf

* [1998 LeNet5 Original Paper]Gradient-Based Learning Applied to Document Recognition.pdf

* [2012 AlexNet Original Paper]NIPS-2012-imagenet-classification-with-deep-convolutional-neural-networks-Paper.pdf

* [2014 GoogLeNet Original Paper]Going deeper with convolutions.pdf

* [2014 NiN Original Paper]Network in Network.pdf

* [2014 VGG Original Paper]Very deep convolutional networks for large-scale image recognition.pdf

* [2015 ResNet Original Paper]Deep Residual Learning for Image Recognition.pdf

* 从数学的角度理解卷积&卷积神经网络/

* The Loss Surfaces of Multilayer Networks.pdf

* understanding convolutional neural networks with a mathematical model.pdf

* 关于深层神经网络vs浅层神经网络的研究/

* Comparing Shallow versus Deep Neural Network Architectures for autometic music genre classification.pdf

* Deep vs. Shallow Networks_ an Approximation Theory Perspective.pdf

* Layers_Modification_of_Convolutional_Neural_Networ.pdf

* Learning Functions_ When Is Deep Better Than Shallow arXiv.pdf

* On the Complexity of shallow and deep neural network classifiers.pdf

* When and Why are Deep Networks better than shallow ones_.pdf

* Why_and_when_can_deep-but_not_shallow-networks_avo.pdf

* 卷积神经网络的优化/

* Comparative_Study_of_First_Order_Optimizers_for_Im.pdf

* Evaluation of Pooling Operations in.pdf

* Improving_the_Separability_of_Deep_Features_with_Discriminative Convolution Filters for.pdf

* effects of padding on LSTM and CNNs.pdf

* understand the effective receptive field in deep CNN.pdf

* 卷积神经网络的可视化/

* Visualizing and Understanding Convolutional Networks.pdf

* WEEK 11 - WEEK 14/

* 16.7~16.13.ipynb

* 16.14 - END（5月9日更新）.ipynb

* 17.1 - 17.3.ipynb

* 17.4 & 17.5.ipynb

* Lesson 16 计算机视觉开篇（下）（5月9日更新）.pdf

* Lesson 17 深度视觉进阶（上）V7 6月16日更新.pdf

* torch_receptive_field/

* __init__.py

* receptive_field.py