jiang-wu-19 / learndeeplearning

This is the learning of PyTorch

studyDeepLearning

深度学习计算DLC

笔记地址 | Note Address：深度学习计算 | J&Ocean BLOG (jiangwu.xyz)

MLP作为切入点学习深度学习计算

Learn Deep-Learning-Calculation based on MLP, using PyTorch

MLP

• 运行mnist.py和fashion_mnist.py以获取图像数据集
• run mnist.py and fashion_mnist.py to fetch the image-datasets

layer and block

学习深度学习中的层和块，并在PyTorch中体现，

在block中实现自定义块、顺序块和块内前向传播

learn the concepts of layer and block in DL,

implement self-defined block, sequential block and forward function in block

implement no-parameter layer and self-defined layer in layer

parameter

参数管理，包括访问参数，参数初始化

implement the initiation and the access of parameters

IO

模型参数的保存与加载

save and load the parameters of the model

GPU

深度学习需要GPU

DL uses GPU to calculate

CNN

笔记地址 | Note Address：卷积神经网络 | J&Ocean BLOG (jiangwu.xyz)

学习了卷积神经网络的定义和细节

learn the detail of CNN

学习了卷积层，池化层和经典CNN-LeNet

including convolution layer, pooling layer and the ordinary CNN --- LeNet

mCNN

笔记地址 | Note Address：现代卷积神经网络 | J&Ocean BLOG (jiangwu.xyz)

现代卷积神经网络 modern CNN

AlexNet

实现了单GPU的AlexNet，在Fashion-MNIST/MNIST上测试

implement the AlexNet on single GPU, testing on Fashio-MNIST/MNIST

VGG

NiN

GoogLeNet

Batch Normalization

ResNet

DenseNet