Commit cad93b5

committed

finish cnn architecture

1 parent c0eb032 commit cad93b5Copy full SHA for cad93b5

File tree

17 files changed

+1960

-640

lines changed

README.md
chapter3_NN
- deep-nn.ipynb
chapter4_CNN
- basic_conv.ipynb
- cat.png
- cifar10
  - main.py
- convolution_network
- densenet.ipynb
- googlenet.ipynb
- mnist
  - main.py
- resnet.ipynb
- utils.py
- vgg.ipynb

17 files changed

+1960

-640

lines changed

`‎README.md‎`

Lines changed: 15 additions & 17 deletions

Original file line number	Diff line number	Diff line change
`@@ -28,23 +28,14 @@ Learn Deep Learning with PyTorch`
`28`	`28`	`- [多层神经网络,Sequential 和 Module](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_NN/nn-sequential-module.ipynb)`
`29`	`29`	`- [深度神经网络](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_NN/deep-nn.ipynb)`
`30`	`30`	`- [参数初始化方法](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_NN/param_initialize.ipynb)`
`31`		`- - 优化算法`
`32`		`- - [SGD](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_NN/optimizer/sgd.ipynb)`
`33`		`- - [动量法](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_NN/optimizer/momentum.ipynb)`
`34`		`- - [Adagrad](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_NN/optimizer/adagrad.ipynb)`
`35`		`- - [RMSProp](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_NN/optimizer/rmsprop.ipynb)`
`36`		`- - [Adadelta](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_NN/optimizer/adadelta.ipynb)`
`37`		`- - [Adam](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_NN/optimizer/adam.ipynb)`
`38`		`-`
	`31`	`+`
`39`	`32`	`- Chapter 4: 卷积神经网络`
`40`		`- - PyTorch 中的卷积模块`
`41`		`- - 使用重复元素的深度网络,VGG`
`42`		`- - 更加丰富化结构的网络,GoogLeNet`
`43`		`- - 深度残差网络,ResNet`
`44`		`- - 稠密连接的卷积网络,DenseNet`
`45`		`- - 更好的训练卷积网络:数据增强、批标准化、dropout和正则化方法`
`46`		`- - 灵活的数据读取介绍`
`47`		`- - Fine-tuning: 通过微调进行迁移学习`
	`33`	`+ - [PyTorch 中的卷积模块](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter4_CNN/basic_conv.ipynb)`
	`34`	`+ - [使用重复元素的深度网络,VGG](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_CNN/vgg.ipynb)`
	`35`	`+ - [更加丰富化结构的网络,GoogLeNet](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_CNN/googlenet.ipynb)`
	`36`	`+ - [深度残差网络,ResNet](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_CNN/resnet.ipynb)`
	`37`	`+ - [稠密连接的卷积网络,DenseNet](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_CNN/densenet.ipynb)`
	`38`	`+ - 更好的训练卷积网络:数据增强、批标准化、dropout、正则化方法以及学习率衰减`
`48`	`39`
`49`	`40`	`- Chapter 5: 循环神经网络`
`50`	`41`	`- LSTM 和 GRU`
`@@ -62,6 +53,13 @@ Learn Deep Learning with PyTorch`
`62`	`53`	`- Chapter 7: PyTorch高级`
`63`	`54`	`- tensorboard 可视化`
`64`	`55`	`- 优化算法`
	`56`	`+ - [SGD](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_NN/optimizer/sgd.ipynb)`
	`57`	`+ - [动量法](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_NN/optimizer/momentum.ipynb)`
	`58`	`+ - [Adagrad](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_NN/optimizer/adagrad.ipynb)`
	`59`	`+ - [RMSProp](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_NN/optimizer/rmsprop.ipynb)`
	`60`	`+ - [Adadelta](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_NN/optimizer/adadelta.ipynb)`
	`61`	`+ - [Adam](https://github.com/SherlockLiao/code-of-learn-deep-learning-with-pytorch/blob/master/chapter3_NN/optimizer/adam.ipynb)`
	`62`	`+ - 灵活的数据读取介绍`
`65`	`63`	`- autograd.function 的介绍`
`66`	`64`	`- 数据并行和多 GPU`
`67`	`65`	`- PyTorch 的分布式应用`
`@@ -70,14 +68,14 @@ Learn Deep Learning with PyTorch`
`70`	`68`
`71`	`69`	`### part2: 深度学习的应用`
`72`	`70`	`- Chapter 8: 计算机视觉`
`73`		`- - 图像增强的方法`
`74`	`71`	`- Fine-tuning: 通过微调进行迁移学习`
`75`	`72`	`- 语义分割: 通过 FCN 实现像素级别的分类`
`76`	`73`	`- Neural Transfer: 通过卷积网络实现风格迁移`
`77`	`74`	`- Deep Dream: 探索卷积网络眼中的世界`
`78`	`75`
`79`	`76`	`- Chapter 9: 自然语言处理`
`80`	`77`	`- char rnn 实现文本生成`
	`78`	`+ - Image Caption: 实现图片字幕生成`
`81`	`79`	`- seq2seq 实现机器翻译`
`82`	`80`	`- cnn+rnn+attention 实现文本识别`
`83`	`81`