Logistic Regression on MNIST with PyTorch | by Asad Mahmood | Towards Data Science
3 种方法实现逻辑回归多分类 - 知乎 (zhihu.com)
python逻辑回归分类MNIST数据集 - 林木子 - 博客园 (cnblogs.com)
https://zhuanlan.zhihu.com/p/169470634
cross entropy in Pytorch
$$ \ell(x, y) = L = \{l_1,\dots,l_N\}^\top, \quad l_n = - w_{y_n} \log \frac{\exp(x_{n,y_n})}{\sum_{c=1}^C \exp(x_{n,c})} \cdot \mathbb{1}\{y_n \not= \text{ignore\_index}\} $$
Softmax理解之二分类与多分类 - 知乎 (zhihu.com)
(48条消息) 浅谈Pytorch中的Variable的使用方法_Yale曼陀罗的博客-CSDN博客_pytorch中variable
(48条消息) pytorch中的Variable()_你吃过卤汁牛肉吗的博客-CSDN博客_pytorch中variable
你必须要知道CNN模型:ResNet - 知乎 (zhihu.com)
[1512.03385] Deep Residual Learning for Image Recognition (arxiv.org)
图神经网络(Graph Neural Networks,GNN)综述 - 知乎 (zhihu.com)
FL with information-extraction attacks through generative methods
Deep Leakage from Gradients (nips.cc)(nips2019)