![](https://img-blog.csdnimg.cn/20201014180756757.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
深度学习
ai-exception
Github: https://github.com/DmrfCoder;
Gmail: xuefanggang97@gmail.com;
QQ:2296452542
展开
-
分别使用C语言和Python实现矩阵归一化
直接上代码: C语言:#include <stdio.h>#include <algorithm>void mean(float *data,int len,float &mean,float &max,float &min){ float sum=data[0]; max=data[0]; min=data[...原创 2018-03-29 13:20:28 · 7425 阅读 · 1 评论 -
What is RNN and LSTM?
摘要本文将介绍一种常用的神经网络—循环神经网络(recurrent neural network,RNN)以及循环神经网络的一个重要的变体—长短时记忆网络(long short-term memory,LSTM).循环神经网络简介循环神经网络的主要用途是处理和预测序列数据.传统的卷积神经网络(CNN)或者全连接神经网络(FC)都是从输入层到隐含层再到输出层,层与层之间是全连接或部分...原创 2018-06-22 00:13:03 · 351 阅读 · 0 评论 -
Planar data classification with one hidden layer
From Logistic Regression with a Neural Network mindset, we achieved the Neural Network which use Logistic Regression to resolve the linear classification . In this blog ,we will achieve a Neural Netwo...原创 2018-11-13 17:57:41 · 201 阅读 · 0 评论 -
Logistic Regression with a Neural Network mindset
General Architecture of the learning algorithmIt’s time to design a simple algorithm to distinguish cat images from non-cat images.I will build a Logistic Regression, using a Neural Network mindset....原创 2018-11-10 23:51:18 · 292 阅读 · 0 评论 -
Normalizing rows with Python
A common technique we use in Machine Learning and Deep Learning is to normalize our data. It often leads to a better performance because gradient descent converges faster after normalization. Here, by...原创 2018-11-09 00:11:51 · 471 阅读 · 0 评论 -
libcudart.so.8.0: cannot open shared object file解决方案
error while loading shared libraries: libcudart.so.8.0: cannot open shared object file: No such file or directory解决方案:sudo ldconfig /usr/local/cuda/lib64原创 2018-05-22 22:57:25 · 1103 阅读 · 0 评论 -
使用python绘制混淆矩阵(confusion_matrix)
Summary涉及到分类问题,我们经常需要通过可视化混淆矩阵来分析实验结果进而得出调参思路,本文介绍如何利用python绘制混淆矩阵(confusion_matrix),本文只提供代码,给出必要注释。Code# -*-coding:utf-8-*-from sklearn.metrics import confusion_matriximport matplotlib.pyplot...原创 2018-04-22 13:46:00 · 76003 阅读 · 56 评论