django学习笔记（非常详细）

利用Python获取海康威视摄像头的源码

Dive Into Deep Learning

kaggle上对旧金山城市的犯罪案件进行分类，属于多分类问题，提供的数据特征包含时间、地点、描述等。本实例包含数据集和代码，机器学习方法是朴素贝叶斯和逻辑回归

SSD: Single Shot MultiBox Object Detector, in PyTorch

LSTM入门学习，正弦波序列预测         for i, input_t in enumerate(input.chunk(input.size(1), dim=1)):             h_t, c_t = self.lstm1(input_t, (h_t, c_t))             h_t2, c_t2 = self.lstm2(h_t, (h_t2, c_t2))             output = self.linear(h_t2)  # output.shape:[batch,1]             outputs = [output]  # outputs.shape:[[batch,1],...[batch,1]], list composed of n [batch,1],         for i in range(future):  # if we should predict the future             h_t, c_t = self.lstm1(output, (h_t, c_t))             h_t2, c_t2 = self.lstm2(h_t, (h_t2, c_t2))             output = self.linear(h_t2)  # output.shape:[batch,1]             outputs = [output]  # outputs.shape:[[batch,1],...[batch,1]], list composed of n [batch,1],         outputs = torch.stack(outputs, 1).squeeze(2)  # shape after stack:[batch, n, 1], shape after squeeze: [batch,n]         return outputs

适合爬虫初学者的必备入门demo，效果如下： 要求环境python3.7,安装库requests，xlwt，re，os采用新手友好的原始正则对文本进行筛选，爬取豆瓣top250电影信息，生成excel表格，可在pycharm中直接运行，默认保存目录D:/test

12306春运抢票

SVM支持向量机的实现

《生成对抗网络入门指南》随书源码

动手学习深度学习——pytorch版本