李宏毅 DeepLearning -2017-Hello world of deep learning (keras)and Demo

最新推荐文章于 2023-07-11 15:58:41 发布
最新推荐文章于 2023-07-11 15:58:41 发布
阅读量279 收藏
点赞数
分类专栏： DeepLearning
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/zjguilai/article/details/89977910
版权

在这里插入图片描述

第一步：搭积木：设置神经网络框架（k re a s）新版的keras2.0将output_dim改成了unit，最后选择输出的activation为softmax保证输出介于（0～1）之间

在这里插入图片描述

第二步：设置loss function来衡量model的优越性和学习走向

在这里插入图片描述

第三步：Train部分，设置优化方法opt（都是gradient 的方法），batchSize:实际中是把训练数据分成随机的等分块进行训练，batchSize指的是这个块的大小，在这里指100张图片，把100个example放到一个batch当中。把所有的batch都做一次叫做一个epoch，一次迭代。

在这里插入图片描述
在这里插入图片描述
**数据处理，把训练数据放入numpy arrray中：x_train输入10000张2828图片，那么数据维数是10000784，属于二维的matrix

y_train输入10000张图片的标签，每一列代表一个标签，图中第一个标签是｛0，0，0，0，0，1，0，0，0，0｝，代表数字“5”**
在这里插入图片描述
****第4步：自己调节Min-batch,会影响运算时间和运算结果batch_size的大小设置有所讲究，对于GPU来说，设置太小的话，batch数量就多，就要分很多次计算，运算时间会比较长，设置太大的话，每个batch里面一次调整很多参数可能会出错。

在这里插入图片描述
在这里插入图片描述
加入gpu的计算方法：

在这里插入图片描述第五步：模型的保存和测试

在这里插入图片描述
第六步：调参数
模型需要调整Loss Function，梯度下降方法以及层数获得最好的效果

zjguilai
关注
  • 0
    点赞
  • 踩
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
专栏目录
台大李宏毅Machine Learning学习笔记（七）——深度学习（Deep Learning）简介
既往不恋未来不迎
07-31 433
深度学习发展历程 图1 深度学习发展历程 图2 深度学习的步骤  深度学习的三个步骤和前面机器学习几乎一样，讲起来比较简单，就像把大象放进冰箱的三个步骤一样：第一步打开门；第二步把大象放进去；第三步关门。但是做起来会遇到各种各样的问题。   第一步里面的函数其实就是神经网络，在上一讲的最后说过，神经网络其实就是逻辑回归单元的级联， 图3 神经网络  神经元之间连接方式需要人工拟定，最常见的方式...
Deep Learning Tutorial by 李宏毅 (Hung-yi Lee)
03-13
《李宏毅深度学习教程》是由台湾大学的著名教授李宏毅（Hung-yi Lee）提供的深度学习资源，因其深入浅出的讲解而备受推崇。这份教程覆盖了深度学习的基础到高级概念，对于想要理解并掌握这一领域的学习者来说，无疑...
深度学习Deep learning小白入门笔记——李宏毅深度学习 逻辑回归笔记
weixin_45698813的博客
07-11 218
if Pw,b(C1∣x)≥0.5,output C1 Otherwise,output C2 if \ \ P_{w,b}(C_1|x)\geq 0.5 ,output \ C_1 \\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ Otherwise,output \ C_2 if Pw,b​(C1​∣x)≥0.5,output C1​ Otherwise,output C2​Pw,b(C1∣x)=σ(z)z=w⋅x+b=∑iw
【深度学习】李宏毅2021/2022春深度学习课程笔记 - Deep Learning Introduction
知不足而奋进，望远山而前行
12-10 2万+
这一步骤在 Deep Learning 中通常表现为建立Model。比如，建立了一个3层的全连接网络，每一层是由线性层+ReLu激活函数构成的，这就是我们定义的函数表达式。在每一个线性层中，都有未知的参数 w 和 b损失函数的值代表了真实值与预测值之间的差距，通常来说，损失函数值越小，代表模型的预测就越接近真实值。常用的损失函数如下图所示：MAE、MSE 等案例介绍已知2017年-2020年的播放量数据，通过已知的数据，训练一个模型（拟合一个函数），预测未来的播放量思路分析建立参数未知的函数表达式。
【机器学习】李宏毅 - 04 深度学习介绍和反向传播机制
wyw970624的博客
10-17 977
神经网络结构；完全连接前馈神经网络；矩阵运算；反向传播；链式法则
《Deep Learning with keras》翻译连载
我爱花生米的专栏
01-04 1212
这边，解释一下，将会连载关于《Deep learning with keras》一书的翻译版及一些自己的认识。如有侵权，请联系删除。若有错误，请指出，多谢关照。由于翻译水平有限，有兴趣的同行可以阅读原版书籍。如果连载的文章会给您多少带来帮助，倍感荣幸。 翻译版从原著的第12页开始，关于前面的内容，如果有必要的话，在全部翻译完之后会进行补充。 正文开始： *******************...
李宏毅-Deep Learning Tutorial-300页的PPT
09-26
注意：此为PPT，不是PDF格式。李宏毅-Deep Learning Tutorial-300页的PPT，这个PPT介绍了一些关于深度学习的知识，适合深度学习入门级阅读。
Deep Learning Tutorial 李宏毅 Hung-yi Lee
03-22
Deep Learning Tutorial 李宏毅 Hung-yi Lee
李宏毅教授ML-2022Spring-HW1-SampleCode-TrainingData
01-17
2022年春季，台湾大学的李宏毅教授开设了一门面向深度学习（Deep Learning）和机器学习的课程，旨在让学生掌握这一领域的核心概念和技术。本篇将详细探讨该课程的第一次作业，包括提供的Sample Code和训练数据。 ...
Deep Learning with Keras.azw3电子书下载
05-03
Deep Learning with Keras by Antonio Gulli English | 26 Apr. 2017 | ASIN: B06Y2YMRDW | 318 Pages | AZW3 | 10.56 MB Key Features Implement various deep-learning algorithms in Keras and see how deep-learning can be used in games See how various deep-learning models and practical use-cases can be implemented using Keras A practical, hands-on guide with real-world examples to give you a strong foundation in Keras Book Description This book starts by introducing you to supervised learning algorithms such as simple linear regression, the classical multilayer perceptron and more sophisticated deep convolutional networks. You will also explore image processing with recognition of hand written digit images, classification of images into different categories, and advanced objects recognition with related image annotations. An example of identification of salient points for face detection is also provided. Next you will be introduced to Recurrent Networks, which are optimized for processing sequence data such as text, audio or time series. Following that, you will learn about unsupervised learning algorithms such as Autoencoders and the very popular Generative Adversarial Networks (GAN). You will also explore non-traditional uses of neural networks as Style Transfer. Finally, you will look at Reinforcement Learning and its application to AI game playing, another popular direction of research and application of neural networks. What you will learn Optimize step-by-step functions on a large neural network using the Backpropagation Algorithm Fine-tune a neural network to improve the quality of results Use deep learning for image and audio processing Use Recursive Neural Tensor Networks (RNTNs) to outperform standard word embedding in special cases Identify problems for which Recurrent Neural Network (RNN) solutions are suitable Explore the process required to implement Autoencoders Evolve a deep neural network using reinforcement learning About the Author Antonio Gulli is a software executive and business leader with a passion for establishing and managing global technological talent, innovation, and execution. He is an expert in search engines, online services, machine learning, information retrieval, analytics, and cloud computing. So far, he has been lucky enough to gain professional experience in four different countries in Europe and managed people in six different countries in Europe and America. Antonio served as CEO, GM, CTO, VP, director, and site lead in multiple fields spanning from publishing (Elsevier) to consumer internet (Ask.com and Tiscali) and high-tech R&D (Microsoft and Google). Sujit Pal is a technology research director at Elsevier Labs, working on building intelligent systems around research content and metadata. His primary interests are information retrieval, ontologies, natural language processing, machine learning, and distributed processing. He is currently working on image classification and similarity using deep learning models. Prior to this, he worked in the consumer healthcare industry, where he helped build ontology-backed semantic search, contextual advertising, and EMR data processing platforms. He writes about technology on his blog at Salmon Run. Table of Contents Neural Networks Foundations Keras Installation and API Deep Learning with ConvNets Generative Adversarial Networks and WaveNet Word Embeddings Recurrent Neural Network — RNN Additional Deep Learning Models AI Game Playing Conclusion
Deep_Learning_with_Python_Keras PDF高清版
10-23
深度学习的概念源于人工神经网络的研究。含多隐层的多层感知器就是一种深度学习结构。深度学习通过组合低层特征形成更加抽象的高层表示属性类别或特征，以发现数据的分布式特征表示。
Deep Learning with Keras+标签完整无水印+文字可编辑复制
05-23
Implement neural networks with Keras on Theano and TensorFlow The book presents more than 20 working deep neural networks coded in Python using Keras, a modular neural network library that runs on top of either Google's TensorFlow or Lisa Lab's Theano backends. The reader is introduced step by step to supervised learning algorithms such as simple linear regression, classical multilayer perceptron, and more sophisticated deep convolutional networks and generative adversarial networks. In addition, the book covers unsupervised learning algorithms such as autoencoders and generative networks. Recurrent networks and long short-term memory (LSTM) networks are also explained in detail. The book goes on to cover the Keras functional API and how to customize Keras in case the reader's use case is not covered by Keras's extensive functionality. It also looks at larger, more complex systems composed of the building blocks covered previously. The book concludes with an introduction to deep reinforcement learning and how it can be used to build game playing AIs. Practical applications include code for the classification of news articles into predefined categories, syntactic analysis of texts, sentiment analysis, synthetic generation of texts, and parts of speech annotation. Image processing is also explored, with recognition of handwritten digit images, classification of images into different categories, and advanced object recognition with related image annotations. An example of identification of salient points for face detection will be also provided. Sound analysis comprises recognition of discrete speeches from multiple speakers. Reinforcement learning is used to build a deep Q-learning network capable of playing games autonomously. Experiments are the essence of the book. Each net is augmented by multiple variants that progressively improve the learning performance by changing the input parameters, the shape of the network, loss functions, and algorithms used for optimizations. Several comparisons between training on CPUs and GPUs are also provided. 全书8章310页，主要聚焦于keras api的使用，推荐给炼丹的同学
《Deep Learning with Keras》随书的源代码
05-04
图书可以从下面的链接下载 http://download.csdn.net/detail/u013003382/9832573 Deep Learning with Keras by Antonio Gulli English | 26 Apr. 2017 | ASIN: B06Y2YMRDW | 318 Pages | AZW3 | 10.56 MB Key Features Implement various deep-learning algorithms in Keras and see how deep-learning can be used in games See how various deep-learning models and practical use-cases can be implemented using Keras A practical, hands-on guide with real-world examples to give you a strong foundation in Keras Book Description This book starts by introducing you to supervised learning algorithms such as simple linear regression, the classical multilayer perceptron and more sophisticated deep convolutional networks. You will also explore image processing with recognition of hand written digit images, classification of images into different categories, and advanced objects recognition with related image annotations. An example of identification of salient points for face detection is also provided. Next you will be introduced to Recurrent Networks, which are optimized for processing sequence data such as text, audio or time series. Following that, you will learn about unsupervised learning algorithms such as Autoencoders and the very popular Generative Adversarial Networks (GAN). You will also explore non-traditional uses of neural networks as Style Transfer. Finally, you will look at Reinforcement Learning and its application to AI game playing, another popular direction of research and application of neural networks. What you will learn Optimize step-by-step functions on a large neural network using the Backpropagation Algorithm Fine-tune a neural network to improve the quality of results Use deep learning for image and audio processing Use Recursive Neural Tensor Networks (RNTNs) to outperform standard word embedding in special cases Identify problems for which Recurrent Neural Network (RNN) solutions are suitable Explore the process required to implement Autoencoders Evolve a deep neural network using reinforcement learning About the Author Antonio Gulli is a software executive and business leader with a passion for establishing and managing global technological talent, innovation, and execution. He is an expert in search engines, online services, machine learning, information retrieval, analytics, and cloud computing. So far, he has been lucky enough to gain professional experience in four different countries in Europe and managed people in six different countries in Europe and America. Antonio served as CEO, GM, CTO, VP, director, and site lead in multiple fields spanning from publishing (Elsevier) to consumer internet (Ask.com and Tiscali) and high-tech R&D (Microsoft and Google). Sujit Pal is a technology research director at Elsevier Labs, working on building intelligent systems around research content and metadata. His primary interests are information retrieval, ontologies, natural language processing, machine learning, and distributed processing. He is currently working on image classification and similarity using deep learning models. Prior to this, he worked in the consumer healthcare industry, where he helped build ontology-backed semantic search, contextual advertising, and EMR data processing platforms. He writes about technology on his blog at Salmon Run. Table of Contents Neural Networks Foundations Keras Installation and API Deep Learning with ConvNets Generative Adversarial Networks and WaveNet Word Embeddings Recurrent Neural Network — RNN Additional Deep Learning Models AI Game Playing Conclusion
李宏毅机器学习之Tips of Deep Learning
Trony的博客
06-19 217
建立deep learning的三个步骤 define a set function goodness of function pick the best function 做完这些事之后我们可以得到一个neural network。在得到neural network之后，我们需要判断神经网络的表现。 一、判断神经网络的表现 1.1 神经网络的表现以及解决方案 首先我们需要检查，这个神经网络在我们的training set上有没有好的结果（是否陷入局部最优），没有的话，回头看，是那个..
李宏毅：deep learning（一）
jiaojiaolou的博客
05-18 446
1、fully connected 2、recurrent neural network（同一个structure反复应用） 双向RNN RNN中每个neural的计算 3、LSTM 三个门控机制的importance： 4、GRU GRU是LSTM网络的一种效果很好的变体，GRU的运算量比LSTM小，它比LSTM少一个gate...
[搬运]台湾大学机器学习课程 by 李宏毅
热门推荐
lgnlgn的专栏
04-03 2万+
台湾大学电机系李宏毅老师讲的机器学习课程，含有deep learning相关内容，深入浅出，建议选择性学习。
李宏毅 DeepLearning-2017-简述DP
zjguilai的博客
05-08 154
先画的连接图，决定了function set(Model),的structure 如何决定layer的数目和层数：直觉，经验 DeepLearning 制造的问题： 如何制造transform structure 变成了 如何创建network structure，自己去寻找best function set ...
Deep Learning学习资源
Yaphat的博客
11-24 6308
1、Deep Learning相关书籍1、Neural Networks and Deep Learning ，一本免费的在线书，极客学院有相应的中文翻译版，不是很全。2、教程1、 最为知名的一个教程是Stanford大学Andrew Ng大牛的UFLDL Tutorial,这个教程也有相应的中文版本 2、李宏毅的ppt，这里下载,300多页，通俗易懂。还有相应的视频，youtube链接 ，还有
李宏毅2021deep learning15个houmework都是什么
最新发布
12-19
李宏毅2021年的深度学习课程的作业涵盖了多个主题和领域。其中包括了神经网络的基础知识与原理，如前向传播和反向传播算法等。还涉及了深度学习模型的搭建和调参，例如卷积神经网络、循环神经网络等。作业还包括了...

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值