This passage is to solve MNIST problem using CNN, Residual Net and Inception Module.
PyTorch Implementation of Softmax Multi-Classifier
We hope the outputs is competitive! Actually we hope the neural network outputs a distribution.
Pytorch实现Logistic Regression
将loss function改成-(y\log\hat{y}+(1-y)\log(1-\hat {y}))用以记录两个分布间的差异(二分类的交叉熵
pytorch实现SGD与Linear Regression
终于开始学pytorch啦!感觉一开始还是得熟悉python奇怪的代码风格(可能因为是面向对象的编程方式不太熟悉emmm 一切伟大的目标都有一个微不足道的开始